CN119169791B - A method and system for monitoring safety during the production process of cylinder equipment - Google Patents
A method and system for monitoring safety during the production process of cylinder equipmentInfo
- Publication number
- CN119169791B CN119169791B CN202411664158.9A CN202411664158A CN119169791B CN 119169791 B CN119169791 B CN 119169791B CN 202411664158 A CN202411664158 A CN 202411664158A CN 119169791 B CN119169791 B CN 119169791B
- Authority
- CN
- China
- Prior art keywords
- safety
- segment
- welding
- monitoring
- production process
- 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
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B31/00—Predictive alarm systems characterised by extrapolation or other computation using updated historic data
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B3/00—Audible signalling systems; Audible personal calling systems
- G08B3/10—Audible signalling systems; Audible personal calling systems using electric transmission; using electromagnetic transmission
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Emergency Management (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Psychiatry (AREA)
- Databases & Information Systems (AREA)
- Social Psychology (AREA)
- Human Computer Interaction (AREA)
- Computational Linguistics (AREA)
- Signal Processing (AREA)
- Electromagnetism (AREA)
- Artificial Intelligence (AREA)
- Medical Informatics (AREA)
- Alarm Systems (AREA)
Abstract
本发明公开了一种筒类设备生产过程安全监控方法及系统，涉及工业安全监控技术领域，包括：实时采集筒类设备生产区域的视频流，并上传；根据视频流信息自动识别当前作业内容属于生产过程的哪个流程段，若没有识别结果，返回步骤一，持续循环监测；若有识别结果，根据识别出的流程段，调用对应的检测算法识别流程段生产中存在的安全风险；将得到的检测结果，根据设定的风险判断条件输出安全监测的结果；若监测结果为无安全风险，则返回步骤一；若监测结果为有安全风险，则触发安全报警。本发明通过对整个生产过程不同的场景，按其存在的风险特点进行分类识别，能够有效预防安全事故的发生，并降低误识率，进而提高整体生产安全水平和生产效率。
The present invention discloses a method and system for monitoring the safety of the production process of cylindrical equipment, which relates to the field of industrial safety monitoring technology, including: real-time acquisition of video streams of the production area of cylindrical equipment and uploading; automatic identification of which process segment of the production process the current operation content belongs to based on the video stream information; if no identification result is found, returning to step one and continuously looping monitoring; if there is an identification result, calling the corresponding detection algorithm based on the identified process segment to identify the safety risks existing in the production of the process segment; outputting the result of the safety monitoring based on the obtained detection result according to the set risk judgment conditions; if the monitoring result is that there is no safety risk, returning to step one; if the monitoring result is that there is a safety risk, triggering a safety alarm. The present invention can effectively prevent the occurrence of safety accidents and reduce the false recognition rate by classifying and identifying different scenarios in the entire production process according to their risk characteristics, thereby improving the overall production safety level and production efficiency.
Description
Technical Field
The invention relates to the technical field of industrial safety monitoring, in particular to a safety monitoring method and system for a production process of cylinder equipment.
Background
The cylinder type equipment is widely applied in the industrial field, such as hot air moistening She Jitong can be used for increasing the temperature and humidity of tobacco leaves in the tobacco processing industry, and the drying cylinder of the cut tobacco dryer can be used for uniformly drying cut tobacco.
Meanwhile, the production process of the cylinder equipment is also complex. Specifically, it is first necessary to curl the steel sheet into a roll by a plate bending machine. And then tightly splicing the plurality of reels into a large barrel by welding. And finally, welding required parts in the cylinder. There is a great potential safety risk in this process, and therefore some necessary protective measures need to be taken. For example, the hoisted objects can slide down during hoisting operation, so people cannot stand under the hoisted objects, operators wear goggles to avoid injury caused by splashes during operation of the veneer reeling machine, welding work clothes, protective gloves and protective masks are strictly worn during external welding, sundries are forbidden to be placed on the surface of a reel to prevent injury to people below due to sliding down, safety belts are strictly worn during ascending welding, and fans are required to assist ventilation during internal welding because the operation space is relatively closed, and welding work clothes, protective gloves and protective masks are strictly worn at the same time.
At present, the manual monitoring mode is difficult to realize real-time and accurate monitoring of the whole processing process, the phenomena of missing detection and false detection are easy to occur, and the safety monitoring method and system special for the production process of the cylinder equipment are not available. Meanwhile, most of the current visual detection methods cannot adapt to the requirements of multiple scenes and multiple changes, can only aim at a single scene, and are complex in operation and low in efficiency. For example, patent CN202310818645.5 proposes a safety welding system and method based on Yolov5, which includes a mechanical arm and a control module, wherein a welding gun is installed on the mechanical arm, the control module is connected with a control end of the mechanical arm to control the mechanical arm to weld a workpiece to be welded, a camera shooting input module is used for acquiring video source data of an operation site, a safety helmet detection module is installed on the safety helmet detection module and is used for identifying an operator in the video source data and identifying whether the operator wears a safety helmet or not, a safety helmet detection result is output, a workpiece quality detection module is installed on the workpiece quality detection module and is used for carrying out quality detection on a workpiece in the video source data and outputting a welding quality detection result, and a display module is used for visually displaying the safety helmet detection result and the welding quality detection result.
Therefore, a method dedicated to automatically identifying the safety risk in the whole production process of the cylindrical equipment is needed to improve the production safety and efficiency.
Disclosure of Invention
Aiming at the problems, the invention provides a safety monitoring method and a system special for the production process of cylinder equipment, which can effectively early warn and prevent the occurrence of safety accidents and further improve the overall production safety level and the production efficiency by monitoring the safety behavior of the whole production process of the cylinder equipment in real time in the whole process, and in the monitoring and identification, the process sections are firstly judged, and then the monitoring is further identified and carried out aiming at different safety risks of different process sections, so that the complexity of identification is effectively reduced, and the safety risks in the production process are identified more rapidly and accurately.
The technical scheme of the invention is as follows:
The invention discloses a safety monitoring method for a production process of barrel equipment, which comprises the following steps:
Firstly, collecting video streams of a production area of barrel equipment in real time and uploading the video streams;
Step two, automatically identifying which flow section of the production process the current operation content belongs to according to the video stream information, wherein the flow section comprises a hoisting section, a winding drum forming section, an external welding section and an internal welding section;
And thirdly, outputting the identification result obtained in the second step according to the set risk judging condition, returning to the first step for continuous cycle monitoring if the monitoring result is that the safety risk is not present, triggering safety alarm if the detection monitoring is that the safety risk is present, and returning to the first step for continuous cycle monitoring.
The second step is characterized in that the crane is in hoisting operation and is used for hoisting objects, the reel forming section is characterized in that the plate bending machine is in an operating state and the steel plate is curled, the outer welding section is characterized in that workers are in welding operation outside the reel, and the inner welding section is characterized in that workers are in welding operation inside the reel.
Further, the specific implementation method of the second step includes:
S21, extracting operation videos acquired in the first step, wherein the operation videos comprise hoisting operation, plate rolling of a plate rolling machine, external welding of a winding drum and internal welding of the winding drum;
S22, extracting target images including lifting hooks, winding drums, human bodies, goggles, protective masks, protective gloves, welding work clothes, safety belts, sundries and fans from the video acquired in the first step, marking targets in the target images, generating marking files including target positions and category information, and constructing a target detection data set;
S23, training the action recognition data set and the target detection data set by adopting an action recognition algorithm and a target detection algorithm respectively;
S24, identifying which flow section the current operation content belongs to and the security risk existing in the flow section by using the trained action identification model and the target detection model.
Further, in the second step, if the current flow section is a hoisting section, detecting whether a person stands under the hoisted object, specifically including:
Firstly, identifying a lifting hook and a person, and obtaining coordinate information of a human body detection frame [ X min-p,Ymin-p,Xmax-p,Ymax-p ], wherein the coordinate information of the lifting hook detection frame is [ X min-h,Ymin-h,Xmax-h,Ymaxh ];
secondly, calculating the horizontal Euclidean distance between the lifting hook detection frame and the center point of the human body detection frame,
Finally, if the horizontal Euclidean distance d is smaller than the specified threshold d th, the person under the suspended object is indicated, and if the horizontal Euclidean distance d is larger than the specified threshold d th, the person under the suspended object is indicated.
Further, in the second step, if the current flow section is a roll forming section, whether a veneer reeling machine operator wears goggles is detected, if the current flow section is an external welding section, whether sundries are placed on a roll or not is detected, whether welding personnel wear welding work clothes, protective gloves and protective masks or not is detected, whether safety risks are directly output if sundries are placed on the roll or the welding personnel wear protective equipment is detected, whether the welding personnel wear protective equipment is further judged, whether the safety risks are output if the welding personnel wear the protective equipment is not detected, whether the safety risks are output if the welding personnel do not wear the protective equipment is judged, whether the safety risks are output if the welding personnel do not wear the safety belts is further judged, and whether the safety belts are worn if the welding personnel do not wear the safety belts is judged.
Further, the method for judging and identifying the ascending operation comprises the following steps:
s31, acquiring coordinate information of a human body detection frame as [ X min-p,Ymin-p,Xmax-p,Ymax-p ], and acquiring coordinate information of a reel detection frame as [ X min-r,Ymin-r,Xmax-r,Ymax-r ];
S32, calculating the height difference between the human body and the central point of the winding drum: ;
S33, calculating the intersection ratio of the human body and the winding drum: , wherein, S P and S R are the areas of the human body detection frame and the reel detection frame respectively;
S32, judging whether a person is in ascending operation according to the intersection ratio IOU of the human body detection frame and the reel detection frame and the height difference h of the central point, wherein the judgment conditions of ascending operation of the person on the reel are that h > h th and 0< IOU th,hth are set human body and reel central point height difference threshold values, and IOU th is set human body and reel intersection ratio threshold value.
Further, in the second step, if the current flow section is an internal welding section, whether welding personnel wear welding work clothes, protective gloves and protective masks or not is detected, whether fan auxiliary ventilation is put outside the winding drum or not is judged, the welding work clothes, the protective gloves and the protective masks are worn, and the fans are arranged for parallel detection, and if the welding work clothes, the protective gloves and the protective masks are not detected, a safety alarm is triggered.
In the third step, risk judging conditions include that a person who hangs a object to be placed on the station, a veneer reeling machine operator does not wear goggles, a welder does not wear welding work clothes, protective gloves and protective masks, a welder ascends to work without wearing safety belts, and no fan is used for assisting ventilation during operation in a welder cylinder.
The invention also discloses a safety monitoring system for the production process of the cylinder equipment, which comprises a video acquisition module, a safety monitoring module and an alarm module;
the video acquisition module is used for acquiring the video stream of the production area in real time;
The safety monitoring module is used for identifying which flow section of the production process the current operation content belongs to, and detecting safety risks existing in the production of the flow section by adopting a corresponding method according to different flow sections;
And the alarm module is used for alarming according to the event type triggered by the safety risk.
Further, the safety monitoring module comprises a classification sub-module and a detection sub-module;
The classifying sub-module automatically identifies a current operation flow section, a hoisting section, a winding drum forming section, an external welding section or an internal welding section by adopting a video understanding algorithm;
And the detection submodule invokes a corresponding detection algorithm for each flow section to identify the security risk of different flow sections.
In summary, due to the adoption of the technical scheme, the beneficial effects of the invention are as follows:
1. The invention realizes the real-time and accurate monitoring of the whole production process of the cylinder equipment, is specially used for the production of the cylinder equipment, and solves the problem that no safety monitoring system specially used for the production process of the cylinder equipment exists.
2. The invention can automatically monitor and identify the safety risk existing in the production process, effectively early warn and prevent the occurrence of safety accidents, and solve the problems that the manual monitoring mode is difficult to realize real-time and accurate monitoring of the whole processing process and the phenomena of missing detection and false detection are easy to occur.
3. The invention improves the efficiency of video monitoring and identification, in the video identification process, the method is different from the existing method for judging and identifying all behaviors and characteristics in the production process, based on the characteristics of the production process of cylinder equipment, the process section is judged first, then the specific process section is judged, the whole process is carried out in sections, and the focusing process can be carried out during the analysis and the judgment, so that the judging and identification method is simplified, the pertinence is stronger, and the processing efficiency is higher.
4. The invention designs a detection algorithm special for the production process of the cylinder equipment, and the detection efficiency is obviously improved.
5. According to the invention, different scenes in the whole production process are classified and identified according to the existing risk characteristics, so that the occurrence of safety accidents can be effectively prevented, the false recognition rate is reduced, and the overall production safety level and the production efficiency are improved.
Drawings
The invention will now be described by way of example and with reference to the accompanying drawings in which:
FIG. 1 is a flow chart of a method for monitoring the safety of a production process of a cylinder device according to the present invention.
Fig. 2 is a schematic diagram of an external welding segment security risk identification step in an embodiment of the present invention.
FIG. 3 is a schematic flow chart of a system for monitoring the safety of a production process of a cylinder device according to the present invention.
Detailed Description
All of the features disclosed in this specification, or all of the steps in a method or process disclosed, may be combined in any combination, except for mutually exclusive features and/or steps.
Any feature disclosed in this specification (including any accompanying claims, abstract) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise. That is, each feature is one example only of a generic series of equivalent or similar features, unless expressly stated otherwise.
The features and capabilities of the present invention are described in further detail below in connection with examples.
The invention discloses a safety monitoring method for a production process of cylinder equipment, which comprises the following steps:
Firstly, collecting video streams of a production area of barrel equipment in real time and uploading the video streams;
Step two, automatically identifying which flow section of the production process the current operation content belongs to according to the video stream information, wherein the flow section comprises a hoisting section, a winding drum forming section, an external welding section and an internal welding section;
And thirdly, outputting the identification result obtained in the second step according to the set risk judging condition, returning to the first step for continuous cyclic monitoring if the monitoring result is that the safety risk is not present, triggering safety alarm if the monitoring result is that the safety risk is present, and returning to the first step for continuous cyclic monitoring.
As shown in fig. 1, in one embodiment, a method for monitoring the safety of a production process of a cylinder device is disclosed, which specifically includes the steps of:
step one, a video acquisition module acquires video streams of a production area of barrel equipment in real time and inputs the video streams into a safety monitoring module.
Step two, a classification submodule in the safety monitoring module automatically identifies a flow section of the current operation content according to video stream information, wherein the flow section comprises a hoisting section, a winding drum forming section, an external welding section and an internal welding section, if no classification result exists, the production area does not currently operate, and the step one is returned to for continuous cycle monitoring.
And thirdly, the detection sub-module invokes a detection algorithm corresponding to the current flow section to identify the security risk.
If the current flow section is a hoisting section, detecting whether a person stands under the hoisted object;
If the roll forming section is the roll forming section, detecting whether a veneer reeling machine operator wears goggles or not;
If the welding section is an external welding section, detecting whether sundries are placed on the winding drum, and whether welding personnel wear welding work clothes, protective gloves and protective masks or not;
If the welding section is the internal welding section, whether welding personnel wear welding work clothes, protective gloves and protective masks or not is detected, and whether a fan is arranged outside the winding drum for auxiliary ventilation or not is detected.
Analyzing the identification result output by the step three, outputting a safety monitoring result according to a set risk judging condition, returning to the step one for continuous cycle monitoring if the safety risk is absent, triggering a safety alarm if the safety risk is present, and returning to the step one for continuous cycle monitoring.
The risk judging conditions comprise that a person who hangs a object to get off the station, a veneer reeling machine operator does not wear goggles, a welder does not wear welding work clothes, protective gloves and protective masks, a welder ascends to work without wearing safety belts, and no fan is used for assisting ventilation during operation in a welder cylinder.
And fifthly, the alarm module performs voice broadcasting in a production area in a broadcasting mode according to the triggered event type, and simultaneously sends a notification to workshop management personnel so that the workshop management personnel can take corresponding measures in time.
The specific implementation method of the second step comprises the following steps:
1. and collecting data, namely collecting operation videos during hoisting operation, plate rolling by a plate rolling machine, external welding of a winding drum and internal welding of the winding drum.
2. And (3) data processing, namely dividing the video into a segment every 10 frames, labeling a category for each segment, and constructing an action recognition data set. The category labels of the video clips are a hoisting section, a winding drum forming section, an external welding section and an internal welding section. The hoisting section is characterized in that the crane is in hoisting operation and is hoisted with objects. The roll forming section is characterized in that the plate bending machine is in an operating state, and the steel plate is being curled. The external welding section is characterized by the fact that a worker is working on the outside of the reel. The internal welding section is characterized by the fact that the worker is working for welding inside the reel.
3. Model training, namely training the action recognition data set by adopting a TSM-ResNet action recognition algorithm, and using a weight model trained by a public data set Kinetics as a pre-training model.
4. And (3) identifying the flow section, namely using the trained action identification model to analyze the video stream information acquired in the step one in real time and identifying the flow section of the current operation content.
The specific implementation method of the third step comprises the following steps:
1. And data acquisition, namely extracting images of targets such as lifting hooks, winding drums, human bodies, goggles, protective masks, protective gloves, welding work clothes, safety belts, sundries, fans and the like from the video.
2. And (3) data processing, namely marking targets in the images by using an image marking tool, generating marking files containing target positions and category information, and constructing a target detection data set.
3. Training a target detection data set by adopting yolov n target detection algorithm, and using a weight model trained by a public data set coco128 as a pre-training model to obtain four algorithm models, wherein the four algorithm models comprise a hoisting section algorithm, a reel forming section algorithm, an external welding section algorithm and an internal welding section algorithm. The hoisting section algorithm trains targets such as human bodies, reels, lifting hooks and the like, the reel forming section algorithm trains targets such as goggles, human bodies and the like, and the external welding section algorithm trains targets such as human bodies, protective masks, protective gloves, welding work clothes, safety belts, sundries and the like. The internal welding segment algorithm trains targets such as human body, protective mask, protective glove, welding work clothes, fans and the like.
4. And (3) safety risk identification, namely enabling a corresponding detection algorithm to identify the safety risk existing in the production of the flow section according to the flow section identified in the step two.
As shown in fig. 2, in the external welding section in the third step, if no protective equipment (welding work clothes, protective gloves and protective masks) or sundries are detected to be placed on the winding drum, the safety risk is directly output, if no sundries are placed on the winding drum and the protective equipment is worn by the welding personnel, whether the ascending operation exists is further judged, if no ascending operation exists, the safety risk is output, if the ascending operation exists, whether the safety belt is worn is further judged, and if the safety belt is not worn, the safety risk is output.
And step three, the internal welding section, namely the welding work clothes, the protective gloves, the protective mask and the fan are detected in parallel, and a safety alarm is triggered as long as the detection is not the same.
The method for detecting the person standing under the suspended object in the third step comprises the steps of firstly identifying the hanging hook and the person, obtaining coordinate information of a human body detection frame [ X min-p,Ymin-p,Xmax-p,Ymax-p ], obtaining the coordinate information of the hanging hook detection frame [ X min-h,Ymin-h,Xmax-h,Ymaxh ], and secondly calculating the horizontal Euclidean distance between the center points of the hanging hook detection frame and the human body detection frameIf the horizontal Euclidean distance d is smaller than the specified threshold d th, the person under the suspended object is indicated, and if the horizontal Euclidean distance d is larger than the specified threshold d th, the person under the suspended object is indicated.
The step three, the ascending operation identification method comprises the steps of judging whether a person is in ascending operation according to the intersection ratio IOU of a human body detection frame and a reel detection frame and the height difference of a central point, wherein the coordinate information of the human body detection frame is [ X min-p,Ymin-p,Xmax-p,Ymax-p ], and the coordinate information of the reel detection frame is [ X min-r,Ymin-r,Xmax-r,Ymax-r ];
Height difference between human body and central point of winding drum:
;
The cross-mixing ratio of human body and winding drum:
;
Wherein:
And The areas of the human body detection frame and the reel detection frame are respectively.
The judgment conditions of the work of the person ascending on the winding drum are h > h th and 0< IOU th. The human body is shown above the winding drums, and the winding drums are overlapped to a certain extent, so that the human body is ensured to be in the vicinity of the winding drums, and meanwhile, the person at a distance is prevented from being misjudged to be a climbing operation.
In the embodiment of the present invention, d th＝200Px、hth＝160Px、IOUth =0.3, and the threshold d th、hth and the IOU th can be adjusted according to the actual engineering environment.
As shown in FIG. 3, the invention also discloses a safety monitoring system for the production process of the cylinder equipment, which comprises a video acquisition module, a safety monitoring module and an alarm module, wherein the safety monitoring module comprises a classification sub-module and a detection sub-module. The video acquisition module acquires the video stream of the production area in real time, the classification submodule in the safety monitoring module automatically identifies the flow sections (the hoisting section, the winding drum forming section, the external welding section and the internal welding section) of the current operation by adopting a video understanding algorithm, the detection submodule invokes a corresponding detection algorithm for each flow section to identify the safety risk of different flow sections, and the alarm module performs corresponding voice broadcasting according to the event type triggered by the safety risk and simultaneously sends a notification to workshop management personnel. Through classifying and identifying different scenes of the whole production process according to the existing risk characteristics, the occurrence of safety accidents can be effectively early warned and prevented, the false recognition rate is reduced, and the whole production safety level and the production efficiency are improved.
The above examples merely illustrate specific embodiments of the application, which are described in more detail and are not to be construed as limiting the scope of the application. It should be noted that it is possible for a person skilled in the art to make several variants and modifications without departing from the technical idea of the application, which fall within the scope of protection of the application.
Claims (8)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411664158.9A CN119169791B (en) | 2024-11-20 | 2024-11-20 | A method and system for monitoring safety during the production process of cylinder equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411664158.9A CN119169791B (en) | 2024-11-20 | 2024-11-20 | A method and system for monitoring safety during the production process of cylinder equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN119169791A CN119169791A (en) | 2024-12-20 |
| CN119169791B true CN119169791B (en) | 2025-08-29 |
Family
ID=93892935
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411664158.9A Active CN119169791B (en) | 2024-11-20 | 2024-11-20 | A method and system for monitoring safety during the production process of cylinder equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119169791B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110275912A (en) * | 2019-05-27 | 2019-09-24 | 千岳（西安）信息科技有限公司 | A kind of control system dynamically associated based on intelligently pushing and interface |
| CN114898513A (en) * | 2022-03-25 | 2022-08-12 | 中铁工程服务有限公司 | Gantry crane environment construction early warning system and method based on electroencephalogram and wireless direction finding |
| CN116935318A (en) * | 2023-07-26 | 2023-10-24 | 新疆信息产业有限责任公司 | Video analysis-based safety supervision service dynamic identification device and method |
Family Cites Families (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107645403B (en) * | 2016-07-22 | 2020-07-03 | 阿里巴巴集团控股有限公司 | Terminal rule engine device and terminal rule operation method |
| CN110110650A (en) * | 2019-05-02 | 2019-08-09 | 西安电子科技大学 | Face identification method in pedestrian |
| CN110647818A (en) * | 2019-08-27 | 2020-01-03 | 北京易华录信息技术股份有限公司 | Identification method and device for shielding target object |
| CN110826514A (en) * | 2019-11-13 | 2020-02-21 | 国网青海省电力公司海东供电公司 | Construction site violation intelligent identification method based on deep learning |
| CN110990873B (en) * | 2019-12-03 | 2023-06-02 | 浙江大华技术股份有限公司 | Monitoring method for illegal operation, computer equipment and storage medium |
| KR102488007B1 (en) * | 2020-07-10 | 2023-01-11 | 주식회사 포스코 | Method for determining whether to wear personal protective equipment and server for performing the same |
| CN113420601B (en) * | 2021-05-27 | 2023-07-18 | 南方电网调峰调频发电有限公司 | Abnormal scene monitoring method and device, computer equipment and storage medium |
| CN113903081B (en) * | 2021-09-29 | 2024-10-18 | 北京许继电气有限公司 | Hydropower plant image visual identification artificial intelligence alarm method and device |
| CN114219283A (en) * | 2021-12-14 | 2022-03-22 | 江苏紫喻智能科技有限公司 | Standard construction process detection method |
| CN117993701A (en) * | 2022-11-04 | 2024-05-07 | 中国石油化工股份有限公司 | Chemical device safety control system and method based on risk hidden danger combined quantification |
| CN116091506B (en) * | 2023-04-12 | 2023-06-16 | 湖北工业大学 | Machine vision defect quality inspection method based on YOLOV5 |
| CN117197724B (en) * | 2023-10-23 | 2025-08-15 | 北京计算机技术及应用研究所 | Dangerous behavior detection method in hoisting operation scene |
| CN117523503B (en) * | 2024-01-08 | 2024-05-03 | 威科电子模块（深圳）有限公司 | Preparation equipment safety monitoring method and system based on thick film circuit board |
| CN117854211B (en) * | 2024-03-07 | 2024-05-28 | 南京奥看信息科技有限公司 | Target object identification method and device based on intelligent vision |
| CN117952479B (en) * | 2024-03-26 | 2024-07-05 | 广州珠江装修工程有限公司 | BIM-based interior decoration engineering supervision method and system |
| CN118609121B (en) * | 2024-05-27 | 2025-03-18 | 烟台大学 | A cell detection method and electronic device based on YOLOv8 |
| CN118764585A (en) * | 2024-06-24 | 2024-10-11 | 深圳市中孚能电气设备有限公司 | Production system inspection method, device, computer equipment and storage medium |
| CN118840785B (en) * | 2024-09-20 | 2025-01-14 | 朗坤智慧科技股份有限公司 | Intelligent identification method and system for ascending operation risk based on industrial scene |
-
2024
- 2024-11-20 CN CN202411664158.9A patent/CN119169791B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110275912A (en) * | 2019-05-27 | 2019-09-24 | 千岳（西安）信息科技有限公司 | A kind of control system dynamically associated based on intelligently pushing and interface |
| CN114898513A (en) * | 2022-03-25 | 2022-08-12 | 中铁工程服务有限公司 | Gantry crane environment construction early warning system and method based on electroencephalogram and wireless direction finding |
| CN116935318A (en) * | 2023-07-26 | 2023-10-24 | 新疆信息产业有限责任公司 | Video analysis-based safety supervision service dynamic identification device and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN119169791A (en) | 2024-12-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110745704B (en) | Tower crane early warning method and device | |
| CN110738135B (en) | Method and system for judging and guiding worker operation step standard visual recognition | |
| CN118840785B (en) | Intelligent identification method and system for ascending operation risk based on industrial scene | |
| CN105976365A (en) | Nocturnal fire disaster video detection method | |
| CN113206978A (en) | Security intelligent monitoring early warning system and method for oil and gas pipeline station | |
| CN112613449A (en) | Safety helmet wearing detection and identification method and system based on video face image | |
| CN114662208B (en) | A construction visualization system and method based on Bim technology | |
| CN111506011A (en) | A construction safety monitoring method and device | |
| CN113111771A (en) | Method for identifying unsafe behaviors of power plant workers | |
| CN114092875B (en) | Machine learning-based operation site safety supervision method and device | |
| CN115620192A (en) | Method and device for detecting wearing of safety rope in aerial work | |
| CN115797856A (en) | A smart security monitoring method for construction scenes based on machine vision | |
| CN112906441A (en) | Image recognition system and method for communication industry survey and maintenance | |
| CN116682034A (en) | Dangerous behavior detection method under complex production operation scene | |
| CN114565886A (en) | Method for detecting dangerous behavior of personnel crossing station tracks in railway industry | |
| CN108388873A (en) | A kind of supervisory systems of machine vision, method and client computer, storage medium | |
| CN107290349A (en) | Detection means, the system and method for cableway steel wire rope based on machine vision | |
| CN113505744A (en) | User behavior detection method and device | |
| CN119169791B (en) | A method and system for monitoring safety during the production process of cylinder equipment | |
| CN115439697A (en) | Method and system for identifying wearing of safety helmet | |
| CN114565887A (en) | A detection method for forklift safety operation based on safety helmet wearing recognition | |
| CN115171037A (en) | Wearing identification device and method for safety operation of hazardous chemical storage chamber based on visual identification | |
| CN112217994A (en) | Early warning method for safety operation around electric power high-voltage line | |
| CN114724348B (en) | Rescue alarm method based on deep learning | |
| CN117115999A (en) | Mobile safety inspection method and terminal equipment |
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 |