CN110765627B - Intelligent operation optimization system and method for thermoelectric enterprise steam turbine unit based on big data - Google Patents
Intelligent operation optimization system and method for thermoelectric enterprise steam turbine unit based on big data Download PDFInfo
- Publication number
- CN110765627B CN110765627B CN201911045804.2A CN201911045804A CN110765627B CN 110765627 B CN110765627 B CN 110765627B CN 201911045804 A CN201911045804 A CN 201911045804A CN 110765627 B CN110765627 B CN 110765627B
- Authority
- CN
- China
- Prior art keywords
- steam
- turbine
- data
- unit
- extraction
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000005457 optimization Methods 0.000 title claims abstract description 115
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000000605 extraction Methods 0.000 claims abstract description 87
- 238000004458 analytical method Methods 0.000 claims abstract description 22
- 230000001105 regulatory effect Effects 0.000 claims abstract description 9
- 238000004140 cleaning Methods 0.000 claims abstract description 6
- 230000001276 controlling effect Effects 0.000 claims abstract description 3
- 230000006870 function Effects 0.000 claims description 36
- 238000010248 power generation Methods 0.000 claims description 30
- 238000007726 management method Methods 0.000 claims description 16
- 238000010438 heat treatment Methods 0.000 claims description 12
- 230000001174 ascending effect Effects 0.000 claims description 10
- 238000007667 floating Methods 0.000 claims description 10
- 230000035772 mutation Effects 0.000 claims description 9
- 238000005516 engineering process Methods 0.000 claims description 8
- 239000006185 dispersion Substances 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000004891 communication Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 3
- 230000008901 benefit Effects 0.000 abstract description 10
- 238000009826 distribution Methods 0.000 abstract description 5
- 230000000694 effects Effects 0.000 abstract description 4
- 238000004519 manufacturing process Methods 0.000 description 13
- 238000007405 data analysis Methods 0.000 description 4
- 238000007418 data mining Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000013461 design Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000009412 basement excavation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000010977 unit operation Methods 0.000 description 1
Images
Landscapes
- Control Of Turbines (AREA)
Abstract
The invention discloses a thermoelectric enterprise turbine unit intelligent operation optimization system and method based on big data, wherein the system comprises the following steps: collecting original data of a turbine unit in real time; cleaning original data of the turbine set to obtain accurate original data of the turbine set; excavating the turbine steam inlet amount, the generated energy, the steam extraction amount and the steam discharge amount data in the turbine set accurate original data, analyzing the operation characteristics of the turbine set accurate original data, and establishing a characteristic model of the turbine set; performing deep analysis on accurate original data of the turbine unit on the basis of the characteristic model of the turbine unit, and establishing a general intelligent optimization model of the turbine unit; and solving a general intelligent optimization model of the turbine unit through a queuing competition algorithm to obtain optimized values of steam inlet quantity, generated energy, steam extraction quantity and steam discharge quantity of the turbine unit, and further regulating and controlling the system. The invention can optimize the thermoelectric load distribution operation of the turbine unit, achieves the effect of energy saving of the system, does not need to transform equipment, reduces the cost, has high optimizing benefit, and is safe and stable.
Description
Technical Field
The invention relates to the technical field of turboset optimization, in particular to an intelligent operation optimization system and method for a thermoelectric enterprise turboset based on big data.
Background
Aiming at the problems that the energy consumption of a turbine unit is high, and the thermoelectric supply and demand balance is difficult to reach quickly and accurately in real time, the following problems exist: firstly, for the operation of the turbine unit, on the premise of meeting the requirements of heat supply and power supply, as the operation efficiency of each turbine has a difference, the total steam consumed by different thermoelectric load distribution operation schemes is different, and a large optimization space exists for the thermoelectric load distribution operation optimization of the turbine unit; secondly, the thermoelectric demand is changed frequently, and is adjusted only by conventional experience, so that the supply and demand balance is difficult to reach quickly and accurately in real time.
The present domestic thermoelectric enterprise optimization software system mainly comprises Inplant software of Zhejiang center control technology division limited company and Syncplant software of Nanjing remote automation group division limited company, which belong to general software and informatization software, and the software has the advantages of multiple functions and wider application range, but only realizes simple data informatization, has insufficient data mining depth, can not realize accurate sensing of production data of a turbine set, optimizes production process and reduces manual intervention.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides an intelligent operation optimization system and method for a thermoelectric enterprise turbine unit based on big data.
The technical scheme adopted for solving the technical problems is as follows:
the invention provides an intelligent operation optimization system of a thermoelectric enterprise turbine unit based on big data, which comprises: the intelligent operation optimization guidance unit comprises an industrial data intelligent acquisition unit, a special database management unit, a turbine unit characteristic analysis unit and a turbine unit intelligent operation optimization guidance unit; wherein:
the industrial data intelligent acquisition unit is used for constructing an OPC industrial data acquisition network through an OPC communication protocol so as to acquire original data of the turbine unit in real time;
the special database management unit is used for storing and managing the original data of the turbine set, the analysis result data of the turbine set characteristic analysis unit and the optimization data of the turbine set intelligent operation optimization guiding unit, which are acquired by the industrial data intelligent acquisition unit; the original data of the turbine unit is cleaned to obtain accurate original data of the turbine unit;
the turbine unit characteristic analysis unit is used for excavating turbine steam inflow, generated energy, steam extraction and steam exhaust data in the turbine unit accurate original data and analyzing the operation characteristics of the turbine steam inflow, generated energy, steam extraction and steam exhaust data to obtain the relationship between the turbine steam inflow and the generated energy, the steam extraction and the steam exhaust, and establishing a characteristic model of the turbine unit;
The intelligent operation optimization guiding unit of the turbine unit is used for carrying out deep analysis on accurate original data of the turbine unit on the basis of the characteristic model of the turbine unit, and establishing a general intelligent optimization model of the turbine unit; the optimization target is that under the premise of meeting the heat supply and power generation demands, the total main steam flow is minimum, corresponding constraint conditions are established, and a general intelligent optimization model of the turbine set is solved through a queuing competition algorithm to obtain a global optimal solution and a global optimal approximate solution, namely, the optimization values of the steam inlet quantity, the generated energy, the steam extraction quantity and the steam discharge quantity of each turbine of the turbine set are obtained, and then the system is regulated and controlled.
Further, the original data of the turbine unit collected in the intelligent industrial data collection unit of the invention comprises: steam turbine inlet flow, steam turbine inlet temperature, steam turbine inlet pressure, steam turbine generating capacity, steam turbine extraction flow, steam turbine extraction pressure, steam turbine extraction temperature, condenser vacuum, condensate water, exhaust temperature, exhaust flow, exhaust pressure, high heating flow, low heating flow, deaerator flow, heating flow and heating temperature.
Further, the specific method for cleaning the data in the special database management unit comprises the following steps:
When the original data of the turbine unit is stored, an ETL method is adopted, namely the original data of the turbine unit is extracted from a DCS system or an unstructured document, the original data format is uniformly converted into a floating point type, then chi-square distributed data preprocessing is carried out on the converted floating point type turbine data, naN null data and data with random errors larger than a threshold value in the result data are deleted, and the accurate original data of the turbine unit are obtained and are all loaded into a special database management system.
Further, the turbine unit characteristic model established in the turbine unit characteristic analysis unit of the present invention is:
analyzing the relation between the steam turbine inlet amount D and the generated energy W, the extracted steam amount E and the exhausted steam amount F, and establishing a characteristic model of the turbine unit as follows:
the characteristic model of the back pressure unit is shown in the formula:
D＝a+b×W
F＝a′+b′×D
the characteristic model of the extraction condensing unit is shown in the formula:
D＝a+b×W+c×E
wherein a, b, c, a ', b' are characteristic coefficients for reflecting turbine efficiency; and solving by a statistical regression method based on the data of the steam turbine steam inlet D, the generated energy W, the steam extraction E and the steam discharge F in the accurate original data of the steam turbine set to obtain a characteristic coefficient.
Further, the general intelligent optimization model of the turboset established in the intelligent operation optimization guiding unit of the turboset is as follows:
The thermoelectric enterprise turbine sets share n turbines, including m back presses, k extraction condensing machines, each turbine steam inlet amount shares a turbine steam inlet main pipe, each turbine generating capacity shares a bus, each turbine steam discharge amount or extraction amount shares a heat supply main pipe;
the purpose of optimizing the general intelligent optimization model of the steam turbine set is as follows: on the premise of meeting the heat supply and power generation requirements, the total main steam flow used is minimum, and the heat supply requirements comprise the steam discharge quantity F and the steam extraction quantity E; wherein the objective function is:
min(D 1 +D 2 +D 3 +…+D n )
setting constraint conditions:
the first constraint is: w (W) 1 +W 2 +…+W n ＝W，F 1 +F 2 +…+F m +E 1 +E 2 +…+E k The total turbine unit power generation amount W is constant, and the total turbine unit heat supply amount G is constant;
the second constraint is:
namely, the characteristic model of the turbine unit is built;
the third constraint is:
the operation constraint back pressure machine exhaust steam quantity is smaller than or equal to the steam inlet quantity, the extraction condensing machine exhaust steam quantity is smaller than or equal to the steam inlet quantity, and the steam turbine inlet steam quantity, the generated energy, the extraction steam quantity and the exhaust steam quantity are within the upper limit value and the lower limit value;
wherein W is the total generated energy; g is the total heat supply; d (D) i (i= … n) is the steam inlet amount of the ith turbine; w (W) i (i= … n) is the power generation amount of the i-th turbine; e (E) i (i= … m) is the low-pressure steam extraction amount of the ith extraction condenser; f (F) j (j= … k) is the exhaust steam amount of the j-th back press; d (D) i,min And D i,max A lower limit value and an upper limit value of the steam inlet amount of the ith (i= … n) turbine; w (W) i,min And W is i,max Lower and upper limit values of the power generation amount of the ith (i= … n) turbine; e (E) i,min And E is i,max A lower limit value and an upper limit value of the extraction amount of the ith (i= … m) turbine; f (F) i,min And F i,max The lower limit value and the upper limit value of the exhaust steam amount of the ith (i= … k) turbine.
Further, the method for solving the general intelligent optimization model of the turbine unit comprises the following steps:
solving a general intelligent optimization model of the steam turbine unit by adopting an optimization tool box and combining a queuing competition algorithm to obtain a global optimal solution and a global optimal approximate solution, wherein the optimization tool box is realized by adopting MATLAB software, R language or Python language; the specific steps of the queuing competition algorithm are as follows:
(1) Taking constraint conditions as a search space, generating m families in the search space according to uniform dispersion, wherein each family comprises k individuals, namely, the k families comprise steam inlet quantity D, steam inlet pressure P, power generation quantity W, steam turbine steam extraction quantity E or steam turbine exhaust quantity F of each steam turbine of a steam turbine unit, forming an initial solution group, calculating objective function values of each family, wherein the objective function values are F (m, k) =D 1 +D 2 +D 3 +…+D n N represents the number of turbines in the turbine unit;
(2) According to the magnitude of the objective function value f (m, k), sorting the m families in ascending order, and adopting the ascending order when the global minimum value of the total intake steam is obtained;
(3) According to the position of each family in the queue, calculating according to constraint conditions in the first calculation, re-calculating the corresponding search space according to the step (5), and proportionally re-determining the corresponding search space, wherein the family search space at the first position in the queue is the smallest, and the search space at the last position in the queue is the largest;
(4) The m families perform asexual propagation variation in the respective corresponding search spaces, and k individuals randomly derive values in the corresponding search spaces, so as to generate g offspring family groups g=m with the greatest difference from each other;
(5) The corresponding search space of g sub-generation family groups is shrunk again, and whether each family in the g sub-generation family groups after mutation meets the termination condition is checked;
if the termination condition is satisfied, the mutation is effectively reserved, the number of the reserved subfamilies of each subfamilies group is denoted by c, and the objective function values f (g, c, k) =d of the reserved subfamilies in the g subfamilies groups are calculated respectively 1 +D 2 +D 3 +…+D n The offspring families with small objective function values f (g, c, k) in each offspring family group are reserved to form a new family group, the number of families in the new family group is counted, and the value of m is updated;
If the termination condition is not met, the next queue status competition is participated, namely, the step (2) is carried out;
termination condition: the search space shrinks to a point or reaches a given evolution algebra.
The invention provides a thermoelectric enterprise turbine unit intelligent operation optimization method based on big data, which comprises the following steps:
s1, an industrial data intelligent acquisition unit acquires original data of a turbine set through an OPC data acquisition network based on a real-time data acquisition program of an OPC technology;
s2, summarizing the data required by the whole system from an industrial data intelligent acquisition system, extracting original data of the turboset from a DCS system or an unstructured document by adopting an ETL method in the data cleaning and processing process, uniformly converting the original data format into a floating point type, then carrying out chi-square distributed data preprocessing on the converted floating point type turbine data, deleting NaN null data and data with larger random errors in the result data, obtaining accurate original data of the turboset, and fully loading the accurate original data into a special database management unit;
s3, excavating the turbine steam inlet amount, the generated energy, the extracted steam amount and the discharged steam amount data in the turbine unit accurate original data, analyzing the operation characteristics of the turbine steam inlet amount, the generated energy, the extracted steam amount and the discharged steam amount data to obtain the relation between the turbine steam inlet amount and the generated energy, the extracted steam amount and the discharged steam amount, and establishing a characteristic model of the turbine unit;
S4, deeply analyzing original data of the turboset on the basis of the characteristic model of the turboset, and establishing a general intelligent optimization model of the turboset; the optimization target is that under the premise of meeting the heat supply and power generation demands, the total main steam flow is minimum, corresponding constraint conditions are established, and a general intelligent optimization model of the turbine set is solved through a queuing competition algorithm to obtain a global optimal solution and a global optimal approximate solution, namely, the optimization values of the steam inlet quantity, the generated energy, the steam extraction quantity and the steam discharge quantity of each turbine of the turbine set are obtained, and then the system is regulated and controlled.
Further, the general intelligent optimization model of the turboset established in the step S4 is as follows:
the thermoelectric enterprise turbine sets share n turbines, including m back presses, k extraction condensing machines, each turbine steam inlet amount shares a turbine steam inlet main pipe, each turbine generating capacity shares a bus, each turbine steam discharge amount or extraction amount shares a heat supply main pipe;
the purpose of optimizing the general intelligent optimization model of the steam turbine set is as follows: on the premise of meeting the heat supply and power generation requirements, the total main steam flow used is minimum, and the heat supply requirements comprise the steam discharge quantity F and the steam extraction quantity E; wherein the objective function is:
min(D 1 +D 2 +D 3 +…+D n )
Setting constraint conditions:
the first constraint is: w (W) 1 +W 2 +…+W n ＝W，F 1 +F 2 +…+F m +E 1 +E 2 +…+E k The total turbine unit power generation amount W is constant, and the total turbine unit heat supply amount G is constant;
the second constraint is:
namely, the characteristic model of the turbine unit is built;
the third constraint is:
the operation constraint back pressure machine exhaust steam quantity is smaller than or equal to the steam inlet quantity, the extraction condensing machine exhaust steam quantity is smaller than or equal to the steam inlet quantity, and the steam turbine inlet steam quantity, the generated energy, the extraction steam quantity and the exhaust steam quantity are within the upper limit value and the lower limit value;
wherein W is the total generated energy; g is the total heat supply; d (D) i (i= … n) is the steam inlet amount of the ith turbine; w (W) i (i= … n) is the power generation amount of the i-th turbine; e (E) i (i= … m) is the low-pressure steam extraction amount of the ith extraction condenser; f (F) j (j= … k) is the exhaust steam amount of the j-th back press; d (D) i,min And D i,max A lower limit value and an upper limit value of the steam inlet amount of the ith (i= … n) turbine; w (W) i,min And W is i,max Lower and upper limit values of the power generation amount of the ith (i= … n) turbine; e (E) i,min And E is i,max A lower limit value and an upper limit value of the extraction amount of the ith (i= … m) turbine; f (F) i,min And F i,max The lower limit value and the upper limit value of the exhaust steam amount of the ith (i= … k) turbine.
Further, the specific method for solving the general intelligent optimization model of the turbine unit in the step S4 of the invention comprises the following steps:
Solving a general intelligent optimization model of the steam turbine unit by adopting an optimization tool box and combining a queuing competition algorithm to obtain a global optimal solution and a global optimal approximate solution, wherein the optimization tool box is realized by adopting MATLAB software, R language or Python language; the specific steps of the queuing competition algorithm are as follows:
(1) Taking constraint conditions as a search space, generating m families in the search space according to uniform dispersion, wherein each family comprises k individuals, namely, the k families comprise steam inlet quantity D, steam inlet pressure P, power generation quantity W, steam turbine steam extraction quantity E or steam turbine exhaust quantity F of each steam turbine of a steam turbine unit, forming an initial solution group, calculating objective function values of each family, wherein the objective function values are F (m, k) =D 1 +D 2 +D 3 +…+D n N represents the number of turbines in the turbine unit;
(2) According to the magnitude of the objective function value f (m, k), sorting the m families in ascending order, and adopting the ascending order when the global minimum value of the total intake steam is obtained;
(3) According to the position of each family in the queue, calculating according to constraint conditions in the first calculation, re-calculating the corresponding search space according to the step (5), and proportionally re-determining the corresponding search space, wherein the family search space at the first position in the queue is the smallest, and the search space at the last position in the queue is the largest;
(4) The m families perform asexual propagation variation in the respective corresponding search spaces, and k individuals randomly derive values in the corresponding search spaces, so as to generate g offspring family groups g=m with the greatest difference from each other;
(5) The corresponding search space of g sub-generation family groups is shrunk again, and whether each family in the g sub-generation family groups after mutation meets the termination condition is checked;
if the termination condition is satisfied, the mutation is effectively reserved, the number of the reserved subfamilies of each subfamilies group is denoted by c, and the objective function values f (g, c, k) =d of the reserved subfamilies in the g subfamilies groups are calculated respectively 1 +D 2 +D 3 +…+D n The offspring families with small objective function values f (g, c, k) in each offspring family group are reserved to form a new family group, the number of families in the new family group is counted, and the value of m is updated;
if the termination condition is not met, the next queue status competition is participated, namely, the step (2) is carried out;
termination condition: the search space shrinks to a point or reaches a given evolution algebra.
Further, the method for regulating and controlling the system in the step S4 of the invention comprises the following steps:
the global optimization values of the steam inlet quantity, the generated energy, the extracted steam quantity and the exhausted steam quantity of each steam turbine of the steam turbine set are the steam inlet quantity Do, the generated energy Wo, the extracted steam quantity Eo and the exhausted steam quantity Fo, and the current values of the steam inlet quantity, the generated energy, the extracted steam quantity and the exhausted steam quantity of the steam turbine set, namely the steam inlet quantity Dt, the generated energy Wt, the extracted steam quantity Et and the exhausted steam quantity Ft, are judged through the global optimization values;
The current steam inlet quantity Dt, the generated energy Wt, the steam extraction quantity Et and the steam discharge quantity Ft of the steam turbine set are controlled and regulated to the optimized value steam inlet quantity Do, the generated energy Wo, the steam extraction quantity Eo and the steam discharge quantity Fo, and the whole system is gradually coordinated and controlled according to the current value and the execution depth of 10%, 30% and 50% …% 100% in the optimized value direction respectively.
The invention has the beneficial effects that: according to the intelligent operation optimization system and method for the thermoelectric enterprise turbine unit based on the big data, the big data analysis is combined with the production operation of the thermoelectric enterprise, the thermoelectric load distribution operation optimization is carried out on the turbine unit, and the effect of energy saving of the system is achieved; the characteristic model of each turbine is obtained by combining the operation data of the turbines by utilizing a big data analysis technology and a statistical regression method, and the accuracy meets the engineering requirements; through big data mining technology, intelligent optimization algorithms such as a queuing competition algorithm and the like can rapidly obtain valuable information from different types of data of the turbine unit, find out the internal rule of a researched object and provide theoretical support for improving economic benefits of thermoelectric enterprises; the energy-saving optimization of the thermoelectric enterprise turbine unit based on big data does not need to modify equipment, reduces the cost, has high optimization benefit, and is safe and stable.
Drawings
The invention will be further described with reference to the accompanying drawings and examples, in which:
FIG. 1 is a schematic diagram of a system architecture according to an embodiment of the present invention;
FIG. 2 is a workflow diagram of a turbine set intelligent operation optimization guidance system in accordance with an embodiment of the invention;
FIG. 3 is a system diagram of a turbine set requiring a customized intelligent optimization model in accordance with an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
As shown in FIG. 1, the intelligent operation optimization system for the thermoelectric enterprise turboset based on big data comprises an intelligent industrial data acquisition unit, a special database management unit, a turboset characteristic analysis unit and an intelligent operation optimization guiding unit for the turboset.
The industrial data intelligent acquisition unit acquires mass data of the DCS system turbine set in real time through an OPC communication protocol; the special database management unit is used for managing the data acquired by the industrial data intelligent acquisition system, the analysis result data of the turboset characteristic analysis system and the relevant data of the turboset intelligent operation optimization guidance system; the turbine unit characteristic analysis unit extracts turbine unit production data from the special database management system for mining and research to obtain the operation characteristics of the turbine unit in real time; the intelligent operation optimization guiding unit of the turbine unit is used for carrying out deep excavation and analysis on mass production data in a special data management system of the turbine unit in real time, and an intelligent optimization model is established by combining production reality and operation characteristics to the greatest extent, so that guidance is provided for operation optimization of the turbine unit of the DCS system.
The industrial data intelligent acquisition unit establishes an OPC industrial data acquisition network through an OPC communication protocol to acquire original data of the turbine unit in real time, wherein the acquired original data of the turbine unit comprise turbine inlet flow, turbine inlet temperature, turbine inlet pressure, turbine generating capacity, turbine extraction flow, turbine extraction pressure, turbine extraction temperature, condenser vacuum degree (condensing turbine), condensate water (condensing turbine), exhaust temperature (backpressure machine), exhaust flow (backpressure machine), exhaust pressure (backpressure machine), high heating flow, low heating flow, deaerator flow, heating flow and heating temperature.
The special database management unit stores and manages the original data of the turbine unit, the analysis result data of the turbine unit characteristic analysis system and the related data of the turbine unit intelligent operation optimization guidance system, which are acquired by the industrial data intelligent acquisition system, and can open a data interface to integrate with other informatization systems of a thermoelectric enterprise to form efficient business cooperation. When the original data of the turbine unit is stored, an ETL method is adopted, namely the original data of the turbine unit is extracted from a DCS system or an unstructured document, the original data format (character string or numerical data) is uniformly converted into floating point numbers with reserved 2-bit decimal, then chi-square distributed data preprocessing is carried out on the converted floating point type turbine data, naN null data and data with larger random errors in the result data are deleted, and the accurate original data of the turbine unit are obtained and are all loaded into a special database management system.
The turbine unit characteristic analysis system excavates the turbine steam inlet D, the generated energy W, the extracted steam E and the exhausted steam F in the turbine unit accurate original data and deeply researches the operation characteristics, namely the relation between the turbine steam inlet D, the generated energy W, the extracted steam E and the exhausted steam F, and establishes a characteristic model of the turbine unit as shown in formulas 1 to 3.
The characteristic model of the back pressure unit is shown in formula 1:
D＝a+b×W (1)
F＝a′+b′×D (2)
the characteristic model of the extraction condensing unit is shown in a formula 3:
D＝a+b×W+c×E (3)
wherein a, b, c, a ', b' are characteristic coefficients, which can reflect turbine efficiency. Based on the data of the steam turbine inlet amount D, the generated energy W, the extracted steam amount E and the exhausted steam amount F in the accurate original data of the steam turbine set, a statistical regression method (a programming language such as MATLAB, R, python and the like and a packaging function library with the method) is applied to solve and obtain characteristic coefficients. The operation characteristics of the turbine unit are obtained in real time as shown in formulas 1 to 3, so that technicians are helped to master the operation characteristics of the turbine, the safe production is helped, and modeling basis is provided for the intelligent operation optimization guidance system of the turbine unit.
The intelligent operation optimization guiding unit of the turbine unit further excavates and analyzes data such as turbine steam inlet D, steam inlet pressure P, power generation W, turbine steam extraction E, turbine steam discharge F and the like in accurate original data of the turbine unit in real time, and a customized intelligent optimization model is established by combining with the actual production of the turbine unit to the greatest extent. Because the types and combinations of turbines are different for each thermoelectric enterprise, the intelligent optimization model needs to be customized, and a simplest general intelligent optimization model of the turboset is listed here as shown in formulas 4 to 7, and a customized intelligent optimization model is further illustrated in the accompanying drawings.
The thermoelectric enterprise turbine sets share n turbines, including m back presses, k extraction condensing machines, each turbine steam inlet amount shares a turbine steam inlet main pipe, each turbine generating capacity shares a bus, each turbine steam discharge amount or extraction amount shares a heat supply main pipe;
the purpose of optimizing the general intelligent optimization model of the steam turbine set is as follows: on the premise of meeting the heat supply and power generation requirements, the total main steam flow used is minimum, and the heat supply requirements comprise the steam discharge quantity F and the steam extraction quantity E; wherein the objective function is:
min(D 1 +D 2 +D 3 +…+D n )(4)
setting constraint conditions:
the first constraint is:
W 1 +W 2 +…+W n ＝ W，F 1 +F 2 +…+F m +E 1 +E 2 +…+E k ＝ G (5)
the total generating capacity W of the turbine unit is fixed, and the heat supply quantity G of the turbine unit is fixed;
the second constraint is:
namely, the characteristic model of the turbine unit is built;
the third constraint is:
the operation constraint back pressure machine exhaust steam quantity is smaller than or equal to the steam inlet quantity, the extraction condensing machine exhaust steam quantity is smaller than or equal to the steam inlet quantity, and the steam turbine inlet steam quantity, the generated energy, the extraction steam quantity and the exhaust steam quantity are within the upper limit value and the lower limit value;
wherein W is the total generated energy; g is the total heat supply; d (D) i (i= … n) is the steam inlet amount of the ith turbine; w (W) i (i= … n) is the power generation amount of the i-th turbine; e (E) i (i= … m) is the low-pressure steam extraction amount of the ith extraction condenser; f (F) j (j= … k) is the exhaust steam amount of the j-th back press; d (D) i,min And D i,max A lower limit value and an upper limit value of the steam inlet amount of the ith (i= … n) turbine; w (W) i,min And W is i,max Lower and upper limit values of the power generation amount of the ith (i= … n) turbine; e (E) i,min And E is i,max A lower limit value and an upper limit value of the extraction amount of the ith (i= … m) turbine; f (F) i,min And F i,max The lower limit value and the upper limit value of the exhaust steam amount of the ith (i= … k) turbine.
And solving the general intelligent optimization model of the turboset by adopting an optimization tool kit such as MATLAB, R or Python and the like and combining a queuing competition algorithm (the algorithm solving step is described below), so as to obtain a global optimal solution and a global optimal approximate solution. The optimized values of the steam inlet quantity, the generated energy, the extracted steam quantity and the exhausted steam quantity of each steam turbine of the steam turbine unit are obtained, namely the steam inlet quantity D o W of electric power generation o Steam extraction quantity E o Steam exhaust quantity F o Judging the current value of the steam inlet, the generated energy, the extracted steam and the exhausted steam of the turbine set, namely the steam inlet D t W of electric power generation t Steam extraction quantity E t Steam exhaust quantity F t The current value of the steam turbine unit is fed by the steam quantity D t W of electric power generation t Steam extraction quantity E t Steam exhaust quantity F t Toward optimized value steam admission quantity D o W of electric power generation o Steam extraction quantity E o Steam exhaust quantity F o The control adjustment is carried out on the direction of the (2), and the whole system is coordinated and controlled according to the current value to the direction of the optimized value by 10%, 30% and 50% …% of execution depth respectively.
The queuing competition algorithm has the characteristics of group and parallel search, and the solving steps of the queuing competition algorithm for quickly solving the general intelligent optimization model of the turbine unit are described as follows:
(1) Generating m families (each family contains k individuals, namely, each family comprises steam turbine inlet D, steam inlet pressure P, generating capacity W, steam turbine extraction E or steam turbine exhaust F of a steam turbine unit) according to uniform dispersion in a search space (formulas 5 to 7), forming an initial solution group, and calculating objective function values of each family according to a formula 4, wherein the objective function values are represented by F (m, k) =D 1 +D 2 +D 3 +…+D n And n is the number of turbines in the turbine unit.
(2) The m families are sorted in ascending order according to the magnitude of the objective function value f (m, k) (the ascending order is adopted when the global minimum of the total intake steam is obtained).
(3) According to the position of each family in the queue, the reference constraint conditions 5 to 7 are calculated for the first time, the corresponding search space in the reference step (5) is calculated again to redefine the corresponding search space according to a certain proportion, the family search space at the first position in the queue is the smallest, and the search space at the last position in the queue is the largest (the global minimum is usually the smallest in the objective function value f (m, k) and is arranged near the family in front of the queue, which is the first coarse adjustment and then fine adjustment logic in analog control).
(4) The m families undergo asexual propagation variations in the respective corresponding search spaces (k individuals randomly derive values in the corresponding search spaces), yielding g populations of offspring families that differ as much as possible from each other (g=m).
(5) And (3) integrally shrinking the corresponding search space of the g sub-generation family groups again, checking whether each family in the mutated g sub-generation family groups meets corresponding requirements, if so, effectively reserving the mutation, and otherwise, checking whether each family in the mutated g sub-generation family groups meets the corresponding requirementsThe number of the child families reserved in the child family groups is denoted by c, and the objective function values f (g, c, k) =d of the child families reserved in the g child family groups are calculated respectively 1 +D 2 +D 3 +…+D n And (3) keeping the offspring families with small objective function values f (g, c, k) in each offspring family group to form a new family group, counting the number of families in the new family group and updating the m value, and if the termination condition is not met, participating in the competition of the next queuing position, namely, turning to the step (2).
Termination condition: the search space is contracted to close to a point or reaches a given evolution algebra. Each family should be bound to a search space.
As shown in fig. 2, the intelligent operation optimization method of the thermoelectric enterprise turbine unit based on big data in the embodiment of the invention is as follows:
The intelligent operation optimization guidance system of the turbine unit extracts important turbine unit operation data subjected to data cleaning from a special database management system, performs further data processing processes such as steady-state analysis and the like, automatically establishes an optimization model by combining design files, special operation requirements, actual production operation conditions and the like, predicts optimization points through a queuing competition algorithm and analyzes the feasibility of an optimization scheme, ensures that the optimal operation scheme is given to guide the production operation of the turbine unit, and meanwhile, checks the optimization effect and corrects parameters of the optimization model, thereby having a self-learning function.
A turbine set system diagram of a large-data-based intelligent operation optimization system of a thermoelectric enterprise turbine set, which needs to customize an intelligent optimization model, is shown in FIG. 3:
the turbine unit has 4 turbines, including 2 back pressure machines (No. 1, no. 3), 2 extraction condensing machines (No. 2, no. 4), 4 turbines with steam inlet amount being the main steam inlet pipe of the co-turbine, generating capacity of 4 turbines shares a bus, exhaust capacity of 2 back pressure machines shares a low-pressure heat supply main pipe, and exhaust capacity of 2 extraction condensing machines shares a medium-pressure heat supply main pipe.
The purpose of optimizing the intelligent optimization model of the turbine unit is to satisfy the heat supply (low pressure heat supply G 1 Medium-pressure heat supply G 2 ) On the premise of the power generation requirement W,the total main steam flow D used is minimal. Wherein the objective function is:
min(D 1 +D 2 +D 3 +D 4 )(8)
setting constraint conditions:
the first constraint is:
W 1 +W 2 +W 3 +W 4 ＝ W，F 1 +F 3 ＝ G 1 ，E 2 +E 4 ＝ G 2 (9)
i.e. the total generating capacity W of the turbine set is fixed, and the low-pressure heat supply quantity G of the turbine set 1 Certain, total turbine unit medium pressure heat supply G 2 And (3) certain.
Namely a back pressure machine characteristic model formula 1, a back pressure machine exhaust steam quantity and steam inlet quantity proportion formula 2 and a condensing machine characteristic model formula 3.
The third constraint is:
the operation constraint back pressure machine exhaust steam quantity is smaller than or equal to the steam inlet quantity, the extraction condensing machine exhaust steam quantity is smaller than or equal to the steam inlet quantity, and the steam turbine inlet steam quantity, the generated energy, the extraction steam quantity and the exhaust steam quantity are within the upper limit value and the lower limit value (the determination of the upper limit value and the lower limit value refers to the safety reliability, the operation actual demand and the design parameters of the steam turbine unit).
Wherein W is the total generated energy; g 1 Heat is supplied to the total low pressure; g 2 Heat is supplied to the total medium pressure; d (D) i (i=1, 2,3, 4) is the steam inlet of the ith turbine; w (W) i (i=1, 2,3, 4) is the power generation amount of the i-th turbine; e (E) i (i=2, 4) is the low-pressure steam extraction amount of the ith extraction condenser; f (F) j (j=1, 3) is the exhaust steam amount of the j-th back press; d (D) i,min And D i,max Lower limit value and upper limit value of steam inlet quantity of ith (i=1, 2,3, 4) turbine A limit value; w (W) i,min And W is i,max Lower and upper limit values of the power generation amount of the ith (i=1, 2,3, 4) turbine; e (E) i,min And E is i,max A lower limit value and an upper limit value of the extraction steam quantity of the ith (i=2, 4) turbine; f (F) i,min And F i,max The lower limit value and the upper limit value of the exhaust steam quantity of the ith (i=1, 3) turbine.
The invention has the following advantages:
(1) According to the invention, big data analysis is combined with production operation of a thermoelectric enterprise, and thermoelectric load distribution operation optimization is carried out on a turbine unit, so that the effect of energy saving of the system is achieved;
(2) According to the invention, a big data analysis technology is utilized, a statistical regression method is applied, and the operation data of the turbines are combined to obtain a characteristic model of each turbine, so that the accuracy meets the engineering requirements;
(3) According to the invention, through a big data mining technology, intelligent optimization algorithms such as a queuing competition algorithm and the like can rapidly obtain valuable information from different types of data of the turbine unit, find out the internal rules of a researched object, and provide theoretical support for improving the economic benefit of a thermoelectric enterprise;
(4) The invention has the advantages of energy saving and optimization of the turbine unit of the thermoelectric enterprise based on big data, no need of equipment reconstruction, cost reduction, high optimization benefit, safety and stability.
After the intelligent operation optimization system of the thermoelectric enterprise turbine unit based on big data is implemented, the total steam consumption of the turbine unit is reduced by 2%, and after data are cleaned, the error of an optimization model is lower than 2%. At present, domestic thermoelectric enterprise optimization software mainly comprises Inplant software of Zhejiang center control technology stock limited company and Syncplant software of Nanjing remote automation group stock limited company, which belong to general software and informatization software, and the software has the advantages of multiple functions and wider application range, but only realizes simple data informatization, has insufficient data mining depth, can not realize accurate sensing of production data of a turbine set, optimizes production process and reduces manual intervention.
It will be understood that modifications and variations will be apparent to those skilled in the art from the foregoing description, and it is intended that all such modifications and variations be included within the scope of the following claims.
Claims (7)
1. An intelligent operation optimization system of a thermoelectric enterprise turbine unit based on big data is characterized in that the system comprises: the intelligent operation optimization guidance unit comprises an industrial data intelligent acquisition unit, a special database management unit, a turbine unit characteristic analysis unit and a turbine unit intelligent operation optimization guidance unit; wherein:
the industrial data intelligent acquisition unit is used for constructing an OPC industrial data acquisition network through an OPC communication protocol so as to acquire original data of the turbine unit in real time;
the special database management unit is used for storing and managing the original data of the turbine set, the analysis result data of the turbine set characteristic analysis unit and the optimization data of the turbine set intelligent operation optimization guiding unit, which are acquired by the industrial data intelligent acquisition unit; the original data of the turbine unit is cleaned to obtain accurate original data of the turbine unit;
the turbine unit characteristic analysis unit is used for excavating turbine steam inflow, generated energy, steam extraction and steam exhaust data in the turbine unit accurate original data and analyzing the operation characteristics of the turbine steam inflow, generated energy, steam extraction and steam exhaust data to obtain the relationship between the turbine steam inflow and the generated energy, the steam extraction and the steam exhaust, and establishing a characteristic model of the turbine unit;
The intelligent operation optimization guiding unit of the turbine unit is used for carrying out deep analysis on accurate original data of the turbine unit on the basis of the characteristic model of the turbine unit, and establishing a general intelligent optimization model of the turbine unit; the optimization target is that under the premise of meeting the heat supply and power generation requirements, the total main steam flow is minimum, corresponding constraint conditions are established, and a general intelligent optimization model of the turbine set is solved through a queuing competition algorithm to obtain a global optimal solution and a global optimal approximate solution, namely, the optimization values of the steam inlet quantity, the generated energy, the steam extraction quantity and the steam discharge quantity of each turbine of the turbine set are obtained, and then the system is regulated and controlled;
the characteristic model of the turbine set established in the characteristic analysis unit of the turbine set is as follows:
analyzing the relation between the steam turbine inlet amount D and the generated energy W, the extracted steam amount E and the exhausted steam amount F, and establishing a characteristic model of the turbine unit as follows:
the characteristic model of the back pressure unit is shown in the formula:
D＝a+b×W
F＝a′+b′×D
the characteristic model of the extraction condensing unit is shown in the formula:
D＝a+b×W+c×E
wherein a, b, c, a ', b' are characteristic coefficients for reflecting turbine efficiency; based on the data of the steam turbine steam inlet D, the generated energy W, the steam extraction E and the steam discharge F in the accurate original data of the steam turbine set, a statistical regression method is applied to solve and obtain a characteristic coefficient;
The general intelligent optimization model of the turbine set established in the intelligent operation optimization guiding unit of the turbine set is as follows:
the thermoelectric enterprise turbine sets share n turbines, including m back presses, k extraction condensing machines, each turbine steam inlet amount shares a turbine steam inlet main pipe, each turbine generating capacity shares a bus, each turbine steam discharge amount or extraction amount shares a heat supply main pipe;
the purpose of optimizing the general intelligent optimization model of the steam turbine set is as follows: on the premise of meeting the heat supply and power generation requirements, the total main steam flow used is minimum, and the heat supply requirements comprise the steam discharge quantity F and the steam extraction quantity E; wherein the objective function is:
min(D 1 +D 2 +D 3 +…+D n )
setting constraint conditions:
the first constraint is: w (W) 1 +W 2 +…+W n ＝W，F 1 +F 2 +…+F m +E 1 +E 2 +…+E k The total turbine unit power generation amount W is constant, and the total turbine unit heat supply amount G is constant;
the second constraint is:
namely, establishing a characteristic model of the turbine unit;
the third constraint is:
the operation constraint back pressure machine exhaust steam quantity is smaller than or equal to the steam inlet quantity, the extraction condensing machine exhaust steam quantity is smaller than or equal to the steam inlet quantity, and the steam turbine inlet steam quantity, the generated energy, the extraction steam quantity and the exhaust steam quantity are within the upper limit value and the lower limit value;
wherein W is the total generated energy; g is the total heat supply; d (D) i The steam inlet amount of the ith steam turbine; w (W) i Generating power for the ith turbine; e (E) i The low-pressure steam extraction quantity of the ith extraction condenser is set; f (F) j The exhaust steam quantity of the j-th back press; d (D) i,min And D i,max The lower limit value and the upper limit value of the steam inlet quantity of the ith steam turbine are set; w (W) i,min And W is i,max The lower limit value and the upper limit value of the generated energy of the ith steam turbine are set; e (E) i,min And E is i,max The lower limit value and the upper limit value of the steam extraction quantity of the ith steam turbine are set; f (F) i,min And F i,max The lower limit value and the upper limit value of the exhaust steam quantity of the ith steam turbine.
2. The intelligent operation optimization system of a thermoelectric enterprise turbine set based on big data according to claim 1, wherein the turbine set raw data collected in the industrial data intelligent collection unit comprises: steam turbine inlet flow, steam turbine inlet temperature, steam turbine inlet pressure, steam turbine generating capacity, steam turbine extraction flow, steam turbine extraction pressure, steam turbine extraction temperature, condenser vacuum, condensate water, exhaust temperature, exhaust flow, exhaust pressure, high heating flow, low heating flow, deaerator flow, heating flow and heating temperature.
3. The intelligent operation optimization system of the thermoelectric enterprise turboset based on big data according to claim 1, wherein the specific method for cleaning the data in the dedicated database management unit is as follows:
When the original data of the turbine unit is stored, an ETL method is adopted, namely the original data of the turbine unit is extracted from a DCS system or an unstructured document, the original data format is uniformly converted into a floating point type, then chi-square distributed data preprocessing is carried out on the converted floating point type turbine data, naN null data and data with random errors larger than a threshold value in the result data are deleted, and the accurate original data of the turbine unit are obtained and are all loaded into a special database management system.
4. The intelligent operation optimization system of the thermoelectric enterprise turboset based on big data according to claim 1, wherein the method for solving the general intelligent optimization model of the turboset is as follows:
solving a general intelligent optimization model of the steam turbine unit by adopting an optimization tool box and combining a queuing competition algorithm to obtain a global optimal solution and a global optimal approximate solution, wherein the optimization tool box is realized by adopting MATLAB software, R language or Python language; the specific steps of the queuing competition algorithm are as follows:
(1) Taking constraint conditions as a search space, generating m families in the search space according to uniform dispersion, wherein each family comprises k individuals, namely, the k families comprise steam inlet quantity D, steam inlet pressure P, power generation quantity W, steam turbine steam extraction quantity E or steam turbine exhaust quantity F of each steam turbine of a steam turbine unit, forming an initial solution group, calculating objective function values of each family, wherein the objective function values are F (m, k) =D 1 +D 2 +D 3 +…+D n N represents the number of turbines in the turbine unit;
(2) According to the magnitude of the objective function value f (m, k), sorting the m families in ascending order, and adopting the ascending order when the global minimum value of the total intake steam is obtained;
(3) According to the position of each family in the queue, calculating according to constraint conditions in the first calculation, re-calculating the corresponding search space according to the step (5), and proportionally re-determining the corresponding search space, wherein the family search space at the first position in the queue is the smallest, and the search space at the last position in the queue is the largest;
(4) The m families perform asexual propagation variation in the respective corresponding search spaces, and k individuals randomly derive values in the corresponding search spaces, so as to generate g offspring family groups g=m with the greatest difference from each other;
(5) The corresponding search space of g sub-generation family groups is shrunk again, and whether each family in the g sub-generation family groups after mutation meets the termination condition is checked;
if the termination condition is satisfied, the mutation is effectively reserved, the number of the reserved subfamilies of each subfamilies group is denoted by c, and the objective function values f (g, c, k) =d of the reserved subfamilies in the g subfamilies groups are calculated respectively 1 +D 2 +D 3 +…+D n The offspring families with small objective function values f (g, c, k) in each offspring family group are reserved to form a new family group, the number of families in the new family group is counted, and the value of m is updated;
If the termination condition is not met, the next queue status competition is participated, namely, the step (2) is carried out;
termination condition: the search space shrinks to a point or reaches a given evolution algebra.
5. The intelligent operation optimization method of the thermoelectric enterprise turbine unit based on the big data is characterized by comprising the following steps of:
s1, an industrial data intelligent acquisition unit acquires original data of a turbine set through an OPC data acquisition network based on a real-time data acquisition program of an OPC technology;
s2, summarizing the data required by the whole system from an industrial data intelligent acquisition system, extracting original data of the turboset from a DCS system or an unstructured document by adopting an ETL method in the data cleaning and processing process, uniformly converting the original data format into a floating point type, then carrying out chi-square distributed data preprocessing on the converted floating point type turbine data, deleting NaN null data and data with larger random errors in the result data, obtaining accurate original data of the turboset, and fully loading the accurate original data into a special database management unit;
s3, excavating the turbine steam inlet amount, the generated energy, the extracted steam amount and the discharged steam amount data in the turbine unit accurate original data, analyzing the operation characteristics of the turbine steam inlet amount, the generated energy, the extracted steam amount and the discharged steam amount data to obtain the relation between the turbine steam inlet amount and the generated energy, the extracted steam amount and the discharged steam amount, and establishing a characteristic model of the turbine unit;
The built characteristic model of the turbine unit is as follows:
analyzing the relation between the steam turbine inlet amount D and the generated energy W, the extracted steam amount E and the exhausted steam amount F, and establishing a characteristic model of the turbine unit as follows:
the characteristic model of the back pressure unit is shown in the formula:
D＝a+b×W
F＝a′+b′×D
the characteristic model of the extraction condensing unit is shown in the formula:
D＝a+b×W+c×E
wherein a, b, c, a ', b' are characteristic coefficients for reflecting turbine efficiency; based on the data of the steam turbine steam inlet D, the generated energy W, the steam extraction E and the steam discharge F in the accurate original data of the steam turbine set, a statistical regression method is applied to solve and obtain a characteristic coefficient;
s4, deeply analyzing original data of the turboset on the basis of the characteristic model of the turboset, and establishing a general intelligent optimization model of the turboset; the optimization target is that under the premise of meeting the heat supply and power generation requirements, the total main steam flow is minimum, corresponding constraint conditions are established, and a general intelligent optimization model of the turbine set is solved through a queuing competition algorithm to obtain a global optimal solution and a global optimal approximate solution, namely, the optimization values of the steam inlet quantity, the generated energy, the steam extraction quantity and the steam discharge quantity of each turbine of the turbine set are obtained, and then the system is regulated and controlled;
the general intelligent optimization model of the turbine set established in the step S4 is as follows:
The thermoelectric enterprise turbine sets share n turbines, including m back presses, k extraction condensing machines, each turbine steam inlet amount shares a turbine steam inlet main pipe, each turbine generating capacity shares a bus, each turbine steam discharge amount or extraction amount shares a heat supply main pipe;
the purpose of optimizing the general intelligent optimization model of the steam turbine set is as follows: on the premise of meeting the heat supply and power generation requirements, the total main steam flow used is minimum, and the heat supply requirements comprise the steam discharge quantity F and the steam extraction quantity E; wherein the objective function is:
min(D 1 +D 2 +D 3 +…+D n )
setting constraint conditions:
the first constraint is: w (W) 1 +W 2 +…+W n ＝W，F 1 +F 2 +…+F m +E 1 +E 2 +…+E k ＝G
The total generating capacity W of the turbine unit is fixed, and the heat supply quantity G of the turbine unit is fixed;
the second constraint is:
namely, establishing a characteristic model of the turbine unit;
the third constraint is:
the operation constraint back pressure machine exhaust steam quantity is smaller than or equal to the steam inlet quantity, the extraction condensing machine exhaust steam quantity is smaller than or equal to the steam inlet quantity, and the steam turbine inlet steam quantity, the generated energy, the extraction steam quantity and the exhaust steam quantity are within the upper limit value and the lower limit value;
wherein W is the total generated energy; g is the total heat supply; d (D) i The steam inlet amount of the ith steam turbine; w (W) i Generating power for the ith turbine; e (E) i The low-pressure steam extraction quantity of the ith extraction condenser is set; f (F) j The exhaust steam quantity of the j-th back press; d (D) i,min And D i,max The lower limit value and the upper limit value of the steam inlet quantity of the ith steam turbine are set; w (W) i,min And W is i,max The lower limit value and the upper limit value of the generated energy of the ith steam turbine are set; e (E) i,min And E is i,max The lower limit value and the upper limit value of the steam extraction quantity of the ith steam turbine are set; f (F) i,min And F i,max The lower limit value and the upper limit value of the exhaust steam quantity of the ith steam turbine.
6. The intelligent operation optimization method for the thermoelectric enterprise turboset based on big data as claimed in claim 5, wherein the specific method for solving the general intelligent optimization model for the turboset in step S4 is as follows:
solving a general intelligent optimization model of the steam turbine unit by adopting an optimization tool box and combining a queuing competition algorithm to obtain a global optimal solution and a global optimal approximate solution, wherein the optimization tool box is realized by adopting MATLAB software, R language or Python language; the specific steps of the queuing competition algorithm are as follows:
(1) Taking constraint conditions as a search space, generating m families in the search space according to uniform dispersion, wherein each family comprises k individuals, namely, the k families comprise steam inlet quantity D, steam inlet pressure P, power generation quantity W, steam turbine steam extraction quantity E or steam turbine exhaust quantity F of each steam turbine of a steam turbine unit, forming an initial solution group, calculating objective function values of each family, wherein the objective function values are F (m, k) =D 1 +D 2 +D 3 +…+D n N represents the number of turbines in the turbine unit;
(2) According to the magnitude of the objective function value f (m, k), sorting the m families in ascending order, and adopting the ascending order when the global minimum value of the total intake steam is obtained;
(3) According to the position of each family in the queue, calculating according to constraint conditions in the first calculation, re-calculating the corresponding search space according to the step (5), and proportionally re-determining the corresponding search space, wherein the family search space at the first position in the queue is the smallest, and the search space at the last position in the queue is the largest;
(4) The m families perform asexual propagation variation in the respective corresponding search spaces, and k individuals randomly derive values in the corresponding search spaces, so as to generate g offspring family groups g=m with the greatest difference from each other;
(5) The corresponding search space of g sub-generation family groups is shrunk again, and whether each family in the g sub-generation family groups after mutation meets the termination condition is checked;
if the termination bar is satisfiedThe mutation is effectively reserved, the number of the reserved offspring families in each offspring family group is denoted by c, and the objective function values f (g, c, k) =d of the reserved offspring families in the g offspring family groups are calculated respectively 1 +D 2 +D 3 +…+D n The offspring families with small objective function values f (g, c, k) in each offspring family group are reserved to form a new family group, the number of families in the new family group is counted, and the value of m is updated;
If the termination condition is not met, the next queue status competition is participated, namely, the step (2) is carried out;
termination condition: the search space shrinks to a point or reaches a given evolution algebra.
7. The intelligent operation optimization method for the thermoelectric enterprise turbine set based on big data according to claim 6, wherein the method for regulating and controlling the system in step S4 is as follows:
the global optimization values of the steam inlet quantity, the generated energy, the extracted steam quantity and the exhausted steam quantity of each steam turbine of the steam turbine set are the steam inlet quantity Do, the generated energy Wo, the extracted steam quantity Eo and the exhausted steam quantity Fo, and the current values of the steam inlet quantity, the generated energy, the extracted steam quantity and the exhausted steam quantity of the steam turbine set, namely the steam inlet quantity Dt, the generated energy Wt, the extracted steam quantity Et and the exhausted steam quantity Ft, are judged through the global optimization values;
the current steam inlet quantity Dt, the generated energy Wt, the extracted steam quantity Et and the exhausted steam quantity Ft of the steam turbine set are controlled and regulated to the optimized value steam inlet quantity Do, the generated energy Wo, the extracted steam quantity Eo and the exhausted steam quantity Fo respectively, and the whole system is coordinated and controlled gradually according to the difference value from the current value to the optimized value and the execution depth of 10%, 30% and 50% …% of the difference value respectively.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911045804.2A CN110765627B (en) | 2019-10-30 | 2019-10-30 | Intelligent operation optimization system and method for thermoelectric enterprise steam turbine unit based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911045804.2A CN110765627B (en) | 2019-10-30 | 2019-10-30 | Intelligent operation optimization system and method for thermoelectric enterprise steam turbine unit based on big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110765627A CN110765627A (en) | 2020-02-07 |
| CN110765627B true CN110765627B (en) | 2023-07-14 |
Family
ID=69334588
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911045804.2A Active CN110765627B (en) | 2019-10-30 | 2019-10-30 | Intelligent operation optimization system and method for thermoelectric enterprise steam turbine unit based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110765627B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111950118B (en) * | 2020-06-29 | 2024-03-12 | 汉谷云智(武汉)科技有限公司 | Operation optimization method and equipment for gas-steam combined generator set |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107035430A (en) * | 2017-05-26 | 2017-08-11 | 国家电网公司 | A kind of steam turbine valve flowrate characteristic parameter optimization method analyzed based on big data |
| WO2019134532A1 (en) * | 2018-01-02 | 2019-07-11 | 佛山科学技术学院 | Operating method of combined heat and power system containing wind and light renewable energy |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102622530B (en) * | 2012-04-24 | 2015-07-01 | 华电能源股份有限公司哈尔滨第三发电厂 | Improved genetic algorithm-based method for distributing and optimizing thermal and electrical load of steam extraction and heating unit |
| CN105955210B (en) * | 2016-04-29 | 2018-07-24 | 湖南工业大学 | The dynamic optimization method of waste heat boiler and Industrial Boiler combined generating system |
| CN107133433B (en) * | 2017-07-10 | 2020-09-01 | 中国大唐集团科学技术研究院有限公司华东分公司 | Model-based adaptive steam turbine regulating valve flow characteristic optimization method |
-
2019
- 2019-10-30 CN CN201911045804.2A patent/CN110765627B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107035430A (en) * | 2017-05-26 | 2017-08-11 | 国家电网公司 | A kind of steam turbine valve flowrate characteristic parameter optimization method analyzed based on big data |
| WO2019134532A1 (en) * | 2018-01-02 | 2019-07-11 | 佛山科学技术学院 | Operating method of combined heat and power system containing wind and light renewable energy |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110765627A (en) | 2020-02-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113642803A (en) | An Optimal Scheduling Method of Water Supply Pump Group Considering Water Quantity Prediction | |
| WO2023024433A1 (en) | Gas-steam combined cycle generator set operation adjustment and control system, and adjustment and control method | |
| CN106094744A (en) | The determination method of thermoelectricity factory owner's operational factor desired value based on association rule mining | |
| CN101893877A (en) | Optimization operational method based on energy consumption analysis for power plant and system thereof | |
| CN107818409A (en) | The optimization method of manufacture of cement parameter and regulation section based on fuzzy association rules | |
| CN105868867B (en) | A kind of heating boiler cluster optimizing operation method | |
| CN111222717B (en) | Method for optimizing and scheduling in thermal power plant containing multi-type heat supply units and thermoelectric decoupling equipment | |
| CN114110716B (en) | Operation energy efficiency monitoring control system and method of thermoelectric unit, computer equipment and storage medium | |
| CN111082466A (en) | New energy access and grid expansion optimization method considering wind power uncertainty | |
| CN110765627B (en) | Intelligent operation optimization system and method for thermoelectric enterprise steam turbine unit based on big data | |
| Jin et al. | Multi-objective optimization of water supply network rehabilitation with non-dominated sorting genetic algorithm-II | |
| CN111950118B (en) | Operation optimization method and equipment for gas-steam combined generator set | |
| CN119602272A (en) | An optimization control method based on the source-load operation scenario model considering uncertainty | |
| CN119933824A (en) | Extracted steam energy storage and molten salt heat storage method and system under deep peak regulation of power grid | |
| CN118367556B (en) | Accelerated optimization method of power system unit commitment based on redundant constraint identification | |
| CN115438030A (en) | Wind turbine abnormal data cleaning method and device | |
| CN117791612B (en) | Resource cluster regulation and control method, system, storage medium and computer equipment | |
| CN116468137A (en) | An integrated optimization method for distributed process planning and workshop scheduling | |
| CN117175595B (en) | Power grid regulation and control method and system based on multi-level data | |
| CN116485156B (en) | Mining method for joint dispatching rules of regional water network backbone regulating and storage nodes | |
| CN118396806A (en) | Cascade reservoir group equal-storage flood control dispatching optimization system and optimization method thereof | |
| CN116454941A (en) | Energy storage configuration method based on new energy load growth prediction combination | |
| Marcelino et al. | Application of evolutionary multiobjective algorithms for solving the problem of energy dispatch in hydroelectric power plants | |
| CN110794688B (en) | Intelligent operation optimization method and system for gas boiler unit and storage medium | |
| CN112766733A (en) | Method and system for accelerating convergence of optimized scheduling algorithm by using improved K-means algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |