CN112906915A - Rail transit system fault diagnosis method based on deep learning - Google Patents
Rail transit system fault diagnosis method based on deep learning Download PDFInfo
- Publication number
- CN112906915A CN112906915A CN202110087150.0A CN202110087150A CN112906915A CN 112906915 A CN112906915 A CN 112906915A CN 202110087150 A CN202110087150 A CN 202110087150A CN 112906915 A CN112906915 A CN 112906915A
- Authority
- CN
- China
- Prior art keywords
- data
- rail transit
- fault diagnosis
- transit system
- deep learning
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/40—Business processes related to the transportation industry
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- General Engineering & Computer Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Primary Health Care (AREA)
- Train Traffic Observation, Control, And Security (AREA)
Abstract
The invention discloses a rail transit system fault diagnosis method based on deep learning, which comprises the steps of integrating rail transit data and carrying out normalization preprocessing; performing feature extraction on the preprocessed rail transit data; adjusting the distribution of the rail transit data to form a data set, and establishing a recurrent neural network model; inputting the data set into the recurrent neural network model for training, and outputting the data set meeting the requirements; the method has the advantages that the trained data set is utilized to diagnose the rail transit system faults, and the intelligent means is used for replacing manpower in the fault diagnosis of the rail transit system, so that the intellectualization, the datamation and the informatization of the maintenance system are improved, the personnel investment is greatly reduced, the labor cost is reduced, and the reliability, the effectiveness and the safety of the maintenance operation of the whole line are further improved.
Description
Technical Field
The invention relates to the technical field of rail transit operation and maintenance, in particular to a rail transit system fault diagnosis method based on deep learning.
Background
Through the development of the last decade, China has become the most rapid world-wide rail transit development, and the newly built railway and urban rail transit lines are far ahead every year, so that the operation mileage is continuously increased. The rail transit is a life line of national economy of China and a backbone network of traffic transportation, not only undertakes most national strategies and transportation of economic materials, but also undertakes the function of passenger transportation, and plays a great role in promoting resource transportation of China, strengthening communication of economic areas, solving the problem of urban traffic congestion and the like. With the formation and development of rail transit networks in China, the rail transit industry starts to gradually enter the repeated stage of construction, operation and maintenance at present, and the maintenance of rail transit is very important.
At present, the work of fault diagnosis of the rail transit system is also based on field operation of a large number of personnel, on one hand, along with the increase of the capacity of the rail transit system, a large amount of personnel investment needs to be allocated, and the labor cost is continuously increased; on the other hand, the field worker cannot always ensure the reliability of system fault diagnosis after heavy work, so that the effectiveness, safety and reliability of the whole line operation maintenance are greatly reduced.
Disclosure of Invention
This section is for the purpose of summarizing some aspects of embodiments of the invention and to briefly introduce some preferred embodiments. In this section, as well as in the abstract and the title of the invention of this application, simplifications or omissions may be made to avoid obscuring the purpose of the section, the abstract and the title, and such simplifications or omissions are not intended to limit the scope of the invention.
The invention is provided in view of the problems of the existing rail transit system fault diagnosis mode.
Therefore, the technical problem solved by the invention is as follows: the problem of current to rail system fault diagnosis work mainly based on the cost increase that a large amount of personnel field operations caused and can't guarantee fault diagnosis reliability all the time is solved.
In order to solve the technical problems, the invention provides the following technical scheme: a rail transit system fault diagnosis method based on deep learning comprises the steps of integrating rail transit data and carrying out normalization preprocessing; performing feature extraction on the preprocessed rail transit data; adjusting the distribution of the rail transit data to form a data set, and establishing a recurrent neural network model; inputting the data set into the recurrent neural network model for training, and outputting the data set meeting the requirements; and diagnosing the rail transit system fault by using the trained data set.
As a preferable scheme of the rail transit system fault diagnosis method based on deep learning of the present invention, wherein: integrating the rail traffic data and carrying out normalization preprocessing, wherein the normalization preprocessing comprises the step of acquiring the rail traffic data with different sources and different characteristics; sequentially carrying out reduction preprocessing according to the selected characteristic values corresponding to the track crossing data to obtain the reduced track crossing data; and sequentially carrying out normalization processing on each item of reduced track crossing data.
As a preferable scheme of the rail transit system fault diagnosis method based on deep learning of the present invention, wherein: performing reduction preprocessing on the track crossing data according to the following formula to obtain each reduced item of track crossing data,
wherein t is the acquired track crossing data, t' is each item of reduced track crossing data, and δ is a selected characteristic value corresponding to each item of track crossing data t.
As a preferable scheme of the rail transit system fault diagnosis method based on deep learning of the present invention, wherein: the extraction reference quantity when the feature extraction is carried out on the preprocessed rail transit data is,
wherein δ' is an extraction reference amount during feature extraction, and δ is a selected feature value corresponding to each item of the rail intersection data t.
As a preferable scheme of the rail transit system fault diagnosis method based on deep learning of the present invention, wherein: adjusting the distribution of the rail transit data comprises establishing a topological structure and inputting the extracted features into the topological structure; determining a reference sequence; acquiring comprehensive association degree among the extracted different features; arranging the data according to an outer loop from low to high comprehensive correlation degree among the characteristics; forming a balanced data set.
As a preferable scheme of the rail transit system fault diagnosis method based on deep learning of the present invention, wherein: defining the minimum of the extraction reference amount as a reference sequence.
As a preferable scheme of the rail transit system fault diagnosis method based on deep learning of the present invention, wherein: and inputting the data set into the recurrent neural network model for training, and verifying and adjusting the hyper-parameters of the recurrent neural network model after outputting the data set meeting the requirements.
As a preferable scheme of the rail transit system fault diagnosis method based on deep learning of the present invention, wherein: the recurrent neural network model function is as follows,
E＝t′·∑P·H(δ)
wherein t' is each reduced track-crossing data, δ is a selected characteristic value corresponding to each track-crossing data t, t is the track-crossing data, P is the comprehensive association function value, H is a selected characteristic value δ function value corresponding to each track-crossing data t, and E is the output quantity of the recurrent neural network model.
As a preferable scheme of the rail transit system fault diagnosis method based on deep learning of the present invention, wherein: and when the output quantity of the E value of the recurrent neural network model is greater than the corresponding t', defining the corresponding data in the data set to meet the requirement through the training of the recurrent neural network model.
The invention has the beneficial effects that: according to the invention, the intelligent means is used for replacing manual work in the fault diagnosis of the rail transit system, so that the intellectualization, the datamation and the informatization of the maintenance system are improved, the personnel investment is greatly reduced, the labor cost is reduced, the reliability, the effectiveness and the safety of the maintenance operation of the whole line are further improved, and the new space of intelligent operation and maintenance of rail transit is opened.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise. Wherein:
FIG. 1 is a flow chart of a method provided by the present invention;
FIG. 2 is a schematic view of the code interface operation of the present invention during the deletion operation of the database;
FIG. 3 is a schematic diagram of a sparse coding linear model according to the present invention;
FIG. 4 is a schematic diagram of the topology employed in the present invention;
FIG. 5 is a diagram illustrating the present invention after arranging data according to a low to high overall correlation between features.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, specific embodiments accompanied with figures are described in detail below, and it is apparent that the described embodiments are a part of the embodiments of the present invention, not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making creative efforts based on the embodiments of the present invention, shall fall within the protection scope of the present invention.
Example 1
At present, the work of fault diagnosis of the rail transit system is also based on field operation of a large number of personnel, on one hand, along with the increase of the capacity of the rail transit system, a large amount of personnel investment needs to be allocated, and the labor cost is continuously increased; on the other hand, the field worker cannot always ensure the reliability of system fault diagnosis after heavy work, so that the effectiveness, safety and reliability of the whole line operation maintenance are greatly reduced.
Therefore, referring to fig. 1 to 5, the present invention provides a rail transit system fault diagnosis method based on deep learning, including:
integrating rail traffic data and performing normalization pretreatment;
performing feature extraction on the preprocessed rail transit data;
adjusting the distribution of the rail transit data to form a data set, and establishing a recurrent neural network model;
inputting the data set into a recurrent neural network model for training, and outputting the data set meeting the requirements;
and diagnosing the rail transit system fault by using the trained data set.
Further, integrating the rail transit data and performing normalization preprocessing comprises:
acquiring rail transit data with different sources and different characteristics;
sequentially carrying out reduction preprocessing according to the selected characteristic values corresponding to the various track traffic data to obtain the reduced various track traffic data;
and sequentially carrying out normalization processing on each item of reduced track traffic data.
It should be noted that:
firstly, acquiring rail crossing data with different sources and different characteristics through a sensor. And different sensors acquire corresponding data and then are uniformly connected into a database system for classification processing.
It should be noted that, during the process of transmitting the different track-crossing data to the database, the different track-crossing data are transmitted after being averagely integrated according to the principle of "large storage amount + small storage amount" (i.e. maximum + minimum, second large + second small, third large + third small … …), so that the pressure of the transmitted data is reduced, and the occurrence of data turbulence is prevented.
And secondly, the acquired rail intersection data comprise anchor segments, positioning points and the like. Considering that the track traffic data acquired by the sensor is large in volume, and the overlarge miscellaneous data can increase the operation pressure of the database on one hand and reduce the operation accuracy on the other hand, a certain reduction processing is performed on a large amount of data transmitted to the database.
Wherein, the track traffic data is subjected to reduction preprocessing according to the following formula to obtain each reduced track traffic data,
wherein t is the acquired track crossing data, t' is each reduced track crossing data, and δ is the selected characteristic value corresponding to each track crossing data t.
Specifically, aiming at anchor section rail crossing data from different sources, selecting delta to be 1.2-1.3, and generally selecting 1.2 bits of optimal selection characteristic values; and selecting delta to be 0.8-1.1 and generally selecting 0.9 optimal selection characteristic value for the positioning point track intersection data of different sources.
Additionally, as shown in fig. 2, a code operation diagram when the database is run with corresponding deletion operations is shown, and the program algorithm for performing the reduction processing on the database is as follows:
Spring.datasource.url＝jdbc:mysql://localhost:3307/springboot-crud-mysql-vuejsserverTimezone＝UTC&useSSL＝false
Spring.datasource.username＝root
Spring.datasource.password＝(δ,δ＇)
Spring.datasource.driver-class-name＝com.mysql.jdbc.Driver
Spring.jpa.hibernate.ddl-auto＝create
Spring.jpa.database-platform＝org.hiberate.dialect.MySQL1.2Dialect
Spring.jpa.database-platform＝org.hiberate.dialect.MySQL0.9Dialect
Spring.jpa.generate-ddl＝true
Spring.jpa.show-sql＝true
Spring.freemarker.suffix＝.html
furthermore, self-encoder technologies such as sparse coding technology and the like are adopted to perform feature extraction on the adjusted data.
Referring to fig. 3, specifically, the sparse coding cost function model is:
the detailed algorithm is as follows:
inputting: signal f (t), dictionary D.
And (3) outputting: list of coefficients (an, g)rn).
Initialization:
R1——f(t)；
n——1；
repeating:
findgrn∈Dwith maximum inner product∣＜Rn,grn＞∣；
an——＜Rn,grn＞；
Rn+1——Rn-grn；
n——n+1；
until a sparse stop condition is reached, for example: | Rn∣∣＜threshold.
Wherein the extraction reference quantity when the feature extraction is carried out on the preprocessed rail transit data is,
wherein δ' is an extraction reference amount during feature extraction, and δ is a selected feature value corresponding to each item of rail data t.
Further, considering that the distribution of the collected fault data may be highly unbalanced due to the difference of the types and models of the devices, for better prediction capability of the generalization system, the unbalanced data set is balanced, and adjusting the distribution of the rail crossing data includes:
establishing a topological structure, and inputting the extracted features into the topological structure;
determining a reference sequence;
acquiring comprehensive association degree among the extracted different features;
arranging the data according to an outer loop from low to high comprehensive correlation degree among the characteristics;
forming a balanced data set.
Wherein, the minimum of the extracted reference quantity is defined as a reference sequence.
Referring to fig. 4, a schematic diagram of the topology adopted is shown.
Referring to FIG. 5, a diagram illustrating data arranged according to a low-to-high outer loop of the overall correlation between features is shown.
As shown in table 1 below, a comparison table of performance of the predicted results of the present invention without adjusting the distribution of the rail traffic data is shown:
table 1: predicted result performance comparison table
| Database operation rate (bytes/s) | Prediction accuracy (100%) | |
| Adjusting the distribution | 3062.8 | 94.87 |
| Without adjusting the distribution | 1022 | 73.25 |
As shown in table 1 above, the performance after adjusting the distribution is significantly better than the case without adjusting the distribution in terms of the database operation rate and the prediction accuracy.
Additionally, the data set is input into the recurrent neural network model for training, and the hyper-parameters of the recurrent neural network model are verified and adjusted after the data set meeting the requirements is output.
The technology of scimit-learn and the like are adopted to realize the traditional hidden Markov process, conditional random field and the like, and the deep learning method of the cyclic neural network and the like realized based on Tensorflow is adopted to train in the data set, and the hyper-parameters of the model are adjusted by cross validation.
Specifically, the recurrent neural network model function formula is,
E＝t′·∑P·H(δ)
wherein t' is each reduced rail traffic data, δ is a selected characteristic value corresponding to each rail traffic data t, t is rail traffic data, P is a comprehensive association degree function value, H is a selected characteristic value δ function value corresponding to each rail traffic data t, and E is a recurrent neural network model output quantity.
And when the output quantity of the E value of the recurrent neural network model is greater than the corresponding t', defining the corresponding data in the data set to meet the requirement through the training of the recurrent neural network model.
As shown in table 2 below, a comparison table of the performance of the rail transit system diagnosis using the present invention and the conventional method is shown:
table 2: performance comparison meter 2
Based on the ROS platform, the corresponding results are counted, as shown in table 2 above.
Because the traditional technology only detects 8 times in each quarter in a manual mode and does not detect the failure rate, the absolute accuracy of prediction reaches 100% of the virtual height, the invention realizes intelligent detection, and the statistical times and the relative accuracy of prediction are obviously higher than those of the traditional technology.
According to the invention, the intelligent means is used for replacing manual work in the fault diagnosis of the rail transit system, so that the intellectualization, the datamation and the informatization of the maintenance system are improved, the personnel investment is greatly reduced, the labor cost is reduced, the reliability, the effectiveness and the safety of the maintenance operation of the whole line are further improved, and the new space of intelligent operation and maintenance of rail transit is opened.
It should be noted that the above-mentioned embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, which should be covered by the claims of the present invention.
Claims (9)
1. A rail transit system fault diagnosis method based on deep learning is characterized in that: comprises the steps of (a) preparing a mixture of a plurality of raw materials,
integrating rail traffic data and performing normalization pretreatment;
performing feature extraction on the preprocessed rail transit data;
adjusting the distribution of the rail transit data to form a data set, and establishing a recurrent neural network model;
inputting the data set into the recurrent neural network model for training, and outputting the data set meeting the requirements;
and diagnosing the rail transit system fault by using the trained data set.
2. The deep learning-based rail transit system fault diagnosis method according to claim 1, characterized in that: integrating the rail traffic data and performing normalization pre-processing includes,
acquiring the rail transit data with different sources and different characteristics;
sequentially carrying out reduction preprocessing according to the selected characteristic values corresponding to the track crossing data to obtain the reduced track crossing data;
and sequentially carrying out normalization processing on each item of reduced track crossing data.
3. The deep learning-based rail transit system fault diagnosis method according to claim 2, characterized in that: performing reduction preprocessing on the track crossing data according to the following formula to obtain each reduced item of track crossing data,
wherein t is the acquired track crossing data, t' is each item of reduced track crossing data, and δ is a selected characteristic value corresponding to each item of track crossing data t.
4. The rail transit system fault diagnosis method based on deep learning according to any one of claims 1 to 3, characterized in that: the extraction reference quantity when the feature extraction is carried out on the preprocessed rail transit data is,
wherein δ' is an extraction reference amount during feature extraction, and δ is a selected feature value corresponding to each item of the rail intersection data t.
5. The deep learning-based rail transit system fault diagnosis method according to claim 4, characterized in that: adjusting the distribution of the track crossing data includes,
establishing a topological structure, and inputting the extracted features into the topological structure;
determining a reference sequence;
acquiring comprehensive association degree among the extracted different features;
arranging the data according to an outer loop from low to high comprehensive correlation degree among the characteristics;
forming a balanced data set.
6. The deep learning-based rail transit system fault diagnosis method according to claim 5, characterized in that: defining the minimum of the extraction reference amount as a reference sequence.
7. The rail transit system fault diagnosis method based on deep learning according to any one of claims 1 to 3, 5 or 6, characterized in that: and inputting the data set into the recurrent neural network model for training, and verifying and adjusting the hyper-parameters of the recurrent neural network model after outputting the data set meeting the requirements.
8. The deep learning based rail transit system fault diagnosis method according to claim 7, characterized in that: the recurrent neural network model function is as follows,
E＝t′·∑P·H(δ)
wherein t' is each reduced track-crossing data, δ is a selected characteristic value corresponding to each track-crossing data t, t is the track-crossing data, P is the comprehensive association function value, H is a selected characteristic value δ function value corresponding to each track-crossing data t, and E is the output quantity of the recurrent neural network model.
9. The deep learning based rail transit system fault diagnosis method according to claim 8, characterized in that: and when the output quantity of the E value of the recurrent neural network model is greater than the corresponding t', defining the corresponding data in the data set to meet the requirement through the training of the recurrent neural network model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110087150.0A CN112906915B (en) | 2021-01-22 | 2021-01-22 | Rail transit system fault diagnosis method based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110087150.0A CN112906915B (en) | 2021-01-22 | 2021-01-22 | Rail transit system fault diagnosis method based on deep learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112906915A true CN112906915A (en) | 2021-06-04 |
| CN112906915B CN112906915B (en) | 2024-03-22 |
Family
ID=76117517
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110087150.0A Active CN112906915B (en) | 2021-01-22 | 2021-01-22 | Rail transit system fault diagnosis method based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112906915B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114996258A (en) * | 2022-06-23 | 2022-09-02 | 中铁第四勘察设计院集团有限公司 | A Method of Catenary Fault Diagnosis Based on Data Warehouse |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170031329A1 (en) * | 2015-07-31 | 2017-02-02 | Fanuc Corporation | Machine learning method and machine learning device for learning fault conditions, and fault prediction device and fault prediction system including the machine learning device |
| CN107769972A (en) * | 2017-10-25 | 2018-03-06 | 武汉大学 | A kind of power telecom network equipment fault Forecasting Methodology based on improved LSTM |
| CN108960077A (en) * | 2018-06-12 | 2018-12-07 | 南京航空航天大学 | A kind of intelligent failure diagnosis method based on Recognition with Recurrent Neural Network |
| CN108985279A (en) * | 2018-08-28 | 2018-12-11 | 上海仁童电子科技有限公司 | The method for diagnosing faults and device of double-unit traction controller waveform |
| CN109959122A (en) * | 2019-03-11 | 2019-07-02 | 浙江工业大学 | An air conditioning energy consumption prediction method based on long short-term memory recurrent neural network |
| CN110033135A (en) * | 2019-04-15 | 2019-07-19 | 北京交通大学 | The train braking system failure prediction method that Multivariate Time Series feature is reinforced |
| CN110222844A (en) * | 2019-05-30 | 2019-09-10 | 西安交通大学 | A kind of compressor performance prediction technique based on artificial neural network |
| CN110348513A (en) * | 2019-07-10 | 2019-10-18 | 北京华电天仁电力控制技术有限公司 | A kind of Wind turbines failure prediction method based on deep learning |
| CN110659779A (en) * | 2019-09-26 | 2020-01-07 | 国网湖南省电力有限公司 | A Loss Prediction Method of Distribution System Based on Long Short-Term Memory Network |
| CN111060779A (en) * | 2019-11-20 | 2020-04-24 | 安徽大学 | Power grid partition fault diagnosis method and system based on probabilistic neural network |
| CN111505543A (en) * | 2020-03-18 | 2020-08-07 | 中国电力科学研究院有限公司 | Method and system for compensating dynamic hysteresis based on recurrent neural network |
| CN111813084A (en) * | 2020-07-10 | 2020-10-23 | 重庆大学 | A fault diagnosis method for mechanical equipment based on deep learning |
| CN111898802A (en) * | 2020-07-08 | 2020-11-06 | 贵州电网有限责任公司 | Power grid disaster situation evaluation method based on deep neural network |
-
2021
- 2021-01-22 CN CN202110087150.0A patent/CN112906915B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170031329A1 (en) * | 2015-07-31 | 2017-02-02 | Fanuc Corporation | Machine learning method and machine learning device for learning fault conditions, and fault prediction device and fault prediction system including the machine learning device |
| CN107769972A (en) * | 2017-10-25 | 2018-03-06 | 武汉大学 | A kind of power telecom network equipment fault Forecasting Methodology based on improved LSTM |
| CN108960077A (en) * | 2018-06-12 | 2018-12-07 | 南京航空航天大学 | A kind of intelligent failure diagnosis method based on Recognition with Recurrent Neural Network |
| CN108985279A (en) * | 2018-08-28 | 2018-12-11 | 上海仁童电子科技有限公司 | The method for diagnosing faults and device of double-unit traction controller waveform |
| CN109959122A (en) * | 2019-03-11 | 2019-07-02 | 浙江工业大学 | An air conditioning energy consumption prediction method based on long short-term memory recurrent neural network |
| CN110033135A (en) * | 2019-04-15 | 2019-07-19 | 北京交通大学 | The train braking system failure prediction method that Multivariate Time Series feature is reinforced |
| CN110222844A (en) * | 2019-05-30 | 2019-09-10 | 西安交通大学 | A kind of compressor performance prediction technique based on artificial neural network |
| CN110348513A (en) * | 2019-07-10 | 2019-10-18 | 北京华电天仁电力控制技术有限公司 | A kind of Wind turbines failure prediction method based on deep learning |
| CN110659779A (en) * | 2019-09-26 | 2020-01-07 | 国网湖南省电力有限公司 | A Loss Prediction Method of Distribution System Based on Long Short-Term Memory Network |
| CN111060779A (en) * | 2019-11-20 | 2020-04-24 | 安徽大学 | Power grid partition fault diagnosis method and system based on probabilistic neural network |
| CN111505543A (en) * | 2020-03-18 | 2020-08-07 | 中国电力科学研究院有限公司 | Method and system for compensating dynamic hysteresis based on recurrent neural network |
| CN111898802A (en) * | 2020-07-08 | 2020-11-06 | 贵州电网有限责任公司 | Power grid disaster situation evaluation method based on deep neural network |
| CN111813084A (en) * | 2020-07-10 | 2020-10-23 | 重庆大学 | A fault diagnosis method for mechanical equipment based on deep learning |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114996258A (en) * | 2022-06-23 | 2022-09-02 | 中铁第四勘察设计院集团有限公司 | A Method of Catenary Fault Diagnosis Based on Data Warehouse |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112906915B (en) | 2024-03-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111709244B (en) | Deep learning method for identifying cause and effect relationship of contradictory dispute | |
| WO2020244288A1 (en) | Method and apparatus for evaluating truck driving behaviour based on gps trajectory data | |
| CN113640380B (en) | Multi-level classification method and system for rail damage detection | |
| CN112529341A (en) | Drilling well leakage probability prediction method based on naive Bayesian algorithm | |
| CN104240030B (en) | Track traffic network dynamic security risk evaluation method | |
| CN108665191B (en) | Calculation method of associated area outside subway station based on aggregation effect | |
| CN105678481A (en) | Pipeline health state assessment method based on random forest model | |
| CN112650204B (en) | A method and system for identifying fault genes of intelligent rail unmanned vehicles | |
| CN113485863B (en) | Method for generating heterogeneous imbalance fault samples based on improved generation of countermeasure network | |
| CN114331221A (en) | Concrete engineering quantity index estimation method based on machine learning | |
| CN110555565A (en) | Decision tree model-based expressway exit ramp accident severity prediction method | |
| CN112612997B (en) | A method for calculating oil-water relative permeability curve based on deep learning | |
| CN113487855A (en) | Traffic flow prediction method based on EMD-GAN neural network structure | |
| CN119337273B (en) | Internal threat detection method based on user classification and behavior feature analysis | |
| CN112149750A (en) | Water supply network pipe burst identification data driving method | |
| CN117216490B (en) | Intelligent big data acquisition system | |
| CN114021758A (en) | Operation and maintenance personnel intelligent recommendation method and device based on fusion of gradient lifting decision tree and logistic regression | |
| CN113343640A (en) | Customs clearance commodity HS code classification method and device | |
| CN112906915A (en) | Rail transit system fault diagnosis method based on deep learning | |
| CN115841750B (en) | Rail transit fault prediction method, device, equipment and storage medium | |
| Liu et al. | A two-stage clustering ensemble algorithm applicable to risk assessment of railway signaling faults | |
| CN119829776A (en) | Fault rule learning method and system for railway motor train unit | |
| CN110879802A (en) | A log pattern extraction and matching method | |
| CN114444765B (en) | Method for predicting railway accident types based on KNN and AdaBoost | |
| CN115392371B (en) | Train traction energy consumption abnormality detection method based on Boosting and multi-predictor fusion |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20230704 Address after: Room 603a, building 7, 266 Chuangyan Road, Qilin hi tech Industrial Development Zone, Nanjing, Jiangsu, 211100 Applicant after: Jiangsu Anshi Intelligent Technology Co.,Ltd. Address before: Room 603a, building 7, 266 Chuangyan Road, Qilin hi tech Industrial Development Zone, Nanjing, Jiangsu, 211100 Applicant before: Jiangsu Anshi Intelligent Technology Co.,Ltd. Applicant before: Fang Jian |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |