CN113177614A - Image recognition system and method for power supply switch cabinet of urban rail transit - Google Patents
Image recognition system and method for power supply switch cabinet of urban rail transit Download PDFInfo
- Publication number
- CN113177614A CN113177614A CN202110584062.1A CN202110584062A CN113177614A CN 113177614 A CN113177614 A CN 113177614A CN 202110584062 A CN202110584062 A CN 202110584062A CN 113177614 A CN113177614 A CN 113177614A
- Authority
- CN
- China
- Prior art keywords
- module
- image
- switch cabinet
- state
- power supply
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- 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
- G08B21/18—Status alarms
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Multimedia (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Evolutionary Biology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Image Analysis (AREA)
Abstract
The invention provides an image recognition system for a power supply switch cabinet of urban rail transit, wherein the power supply switch cabinet is connected with an acquisition module, the acquisition module is connected with an image preprocessing module, the image preprocessing module is connected with a state recognition module, a model training module is also connected with the state recognition module, the state recognition module is also respectively connected with a man-machine display module, a report module and a communication interface module, an inspection report can be automatically generated according to inspection regulations, unmanned inspection work is realized, remote monitoring is realized, the data of PSCADA can be compared with the data of image recognition, double-system confirmation of signals is realized, the correctness of the signals is ensured, meanwhile, the system can transmit real-time video to the PSCADA system according to requirements, operation and maintenance personnel do not need to visit to the site, and the labor cost and the operation cost can be greatly reduced.
Description
Technical Field
The invention relates to the technical field of rail transit, in particular to an image recognition system and method for an urban rail transit power supply switch cabinet.
Background
At present, the inspection work of the power supply switch cabinet of urban rail transit still follows the traditional working mode, and operation and maintenance personnel need to go to the site to inspect equipment. If the switch tripping operation or other faults occur in the switch cabinet, the operation and maintenance personnel still need to attend the site to know the situation, and a large amount of manpower and material resource cost is consumed. The video identification system aiming at the power supply switch cabinet of the urban rail transit is urgently needed, and the image identification technology is used for replacing human eyes for judgment, so that the safety production level and the working efficiency of the power supply system are obviously improved, and the cost of manpower and material resources is reduced.
The existing power supply switch cabinet state identification algorithm only adopts a simple model matching method, and is simple in algorithm, low in automation degree and low in image identification accuracy. Therefore, in the state identification system for the urban rail transit power supply switch cabinet, an algorithm needs to be updated, feature learning is automatically performed layer by adopting a convolutional neural network method, the identification accuracy of the state of the power supply switch cabinet is improved, and the state identification system has great significance for guaranteeing normal operation of the urban rail transit power supply switch cabinet.
Disclosure of Invention
The invention provides a method and a system for identifying state images of an urban rail transit power supply switch cabinet, aiming at solving the problem that the work of the conventional urban rail transit power supply switch cabinet inspection, fault trip state checking and the like excessively depends on manpower, and the method and the system can identify the states of non-intelligent equipment such as a switch indicator lamp, a pressing plate, a handle, an ammeter, a voltmeter and the like of the switch cabinet, identify the appearance, an indicator lamp, display contents and the like of intelligent equipment such as a relay protection device in the switch cabinet and the like, and remotely transmit an identification result to a PSCADA system, thereby achieving unmanned and remote equipment inspection.
In order to achieve the purpose, the invention adopts the following technical scheme:
the utility model provides an urban rail transit power supply cubical switchboard image recognition system, includes image acquisition module, image preprocessing module, model training module, state identification module, man-machine display module, report form module, communication interface module, and the power supply cubical switchboard is connected acquisition module, acquisition module with image preprocessing module connects, image preprocessing module with state identification module connects, model training module also with state identification module connects, state identification module still connects man-machine display module, report form module, communication interface module respectively.
More specifically, the communication interface module is connected to the PSCADA system.
More specifically, the report module needs to predetermine and patrols and examines the template, reads the state information that image recognition accomplished and generates and corresponds and patrols and examines the report, it specifically includes the work regulation of patrolling and examining and patrols and examines the report template to patrol and examine the template.
A method of an image recognition system for an urban rail transit power supply switch cabinet comprises the following steps:
s1, training the relevant recognition model of the urban rail transit switch cabinet, and performing model training under a model training module by adopting a convolutional neural network;
s2, recognizing the image by using the trained CNN convolutional neural network model;
and S3, identifying the relevant state information data of the switch cabinet by the image identification system.
More specifically, the specific steps of S1 are as follows:
s11: collecting a large amount of image data of multiple angles such as front view, side view, oblique view and the like of the power variable switch cabinet to form sample image data, and putting the sample data into a sample data set after marking;
s12: preprocessing sample image data acquired in the S11, performing image segmentation according to recognizable types, segmenting key image areas such as an in-cabinet switch state, a three-station switch position, a protective pressing plate position, a voltmeter, an ammeter, a local remote handle position, a heating indicator lamp, a switch energy storage state, an SF6 gas pressure indicator lamp, a charged display, a relay protection device fault alarm indicator lamp and the like, removing noise points of the images, and enhancing details of the image data;
s13: customizing a CNN convolutional neural network model of the power transformer switch cabinet, and establishing a convolutional neural network with 2 convolutional layers, a maximum pooling layer and two full-connection layers, wherein the last full-connection layer has the same dimensionality as input switch cabinet image data;
s14, performing feature extraction on the preprocessed image data in the S12 by using a convolutional neural network, extracting feature points of sample image data, and establishing feature vectors of a switch state, a three-position switch position, a protection pressure plate position, a voltmeter, an ammeter, a local remote handle position, a heating indicator lamp, a switch energy storage state, an SF6 gas pressure indicator lamp, a charged display and a relay protection device fault alarm indicator lamp in the power transformation switch cabinet for the output of 2 full connection layers;
s15: training the characteristics acquired in S14 by using a classifier model, acquiring different training data subsets from the sample data set by using a tensortflow algorithm, and training the model;
s16: circularly executing the step of S15 until the data which are not marked in the sample plate data set are 0, and finishing the model training;
and S17, after model training is finished, integrating the classifiers by adopting majority voting to obtain a final CNN convolutional neural network model, and detecting information such as a switch state, a three-position switch position, a protection pressing plate position, a voltmeter reading, an ammeter reading, a local remote handle position, a heating indicator light, a switch energy storage state, an SF6 gas pressure indicator light, a charged display state, a relay protection device fault alarm indicator light state and the like.
More specifically, the specific steps of S2 are as follows:
s21: a camera is arranged in front of the medium-voltage switch cabinet, the angle and the focal length are adjusted, the camera is aligned to the related equipment to be identified of the medium-voltage switch cabinet, and the related video stream information is collected;
s22, the image recognition module is in network communication with the camera, and an OpenCV library is adopted to capture the video stream with Rtps of the camera;
s23, loading a CNN convolutional neural network model in an image recognition module, configuring a relevant recognition area, detecting a target to obtain all roi, signals and the model, and correcting the recognition area by using the target detection;
s24: the method comprises the steps of processing collected video stream image information in real time, denoising the image, identifying an identification program conveniently, executing a neural network model, detecting the image information and obtaining state information contained in a current image.
More specifically, the specific steps of S3 are as follows:
s31: displaying state information including a signal name, a signal state, a displacement time, and the like in the image recognition system;
s32: and generating an inspection report in the image identification system, wherein the report contains the state information of the power supply switch cabinet which is daily inspected by the operation and maintenance personnel, the identified state information is compared with the related state in the inspection working procedure, whether the inspection item is normal or not is automatically judged, the inspection report is automatically filed when the inspection item is normal, and an alarm is given when the inspection item is abnormal to remind the operation and maintenance personnel to inspect the abnormal item.
S33: preferably, the image recognition system can transmit the recognized state information to the PSCADA system, and double-system signal confirmation of safety interlock related information is carried out, so that automatic alarm of signal double-system confirmation is realized.
S34: preferably, the PSCADA system can call a real-time monitoring picture according to requirements, so that remote video monitoring is realized. The video monitoring function can realize the active uploading of the video when the equipment is abnormal in state and passively receive the video calling according to the requirement.
By adopting the invention, the state of the power supply switch cabinet is monitored by means of video monitoring and image recognition, and the inspection report can be automatically generated according to the inspection regulation, thereby realizing unmanned inspection work. Furthermore, the state information of the image recognition system after recognition is transmitted to the PSCADA system in real time through a network, so that not only is remote monitoring realized, but also the data of the PSCADA system and the data of the image recognition can be compared, double-system confirmation of signals is realized, and the correctness of the signals is ensured. Meanwhile, the system can also transmit real-time videos to the PSCADA system according to requirements, operation and maintenance personnel do not need to visit the site for inspection, and labor cost and operation cost can be greatly reduced.
FIG. 1 is a diagram of an image recognition system of an urban rail transit power supply switch cabinet;
FIG. 2 is an image recognition flowchart of an urban rail transit power supply switch cabinet;
FIG. 3 is a flow chart of algorithm model training of the present invention;
FIG. 4 is a custom model of the present invention.
The specific implementation mode is as follows:
the following description will be made of a specific embodiment of the present invention, taking an urban rail transit 33kV power-to-power switch cabinet as an example: (one type of switch cabinet is taken as an example), fig. 4 is a self-defined model of the invention, and the specific self-defined parameter model refers to the attached drawings. Referring to the attached figure 1, the image recognition system for the power supply switch cabinet of the urban rail transit comprises an image acquisition module, an image preprocessing module, a model training module, a state recognition module, a human-computer display module, a report module and a communication interface module, wherein the power supply switch cabinet is connected with the acquisition module, the acquisition module is connected with the image preprocessing module, the image preprocessing module is connected with the state recognition module, a sample is connected with the state recognition module through a special configuration file of the model training module, and the state recognition module is further respectively connected with the human-computer display module, the report module and the communication interface module. The communication interface module is connected with the PSCADA system and is transmitted to the PSCADA system through signal flow and video flow.
The report module needs to preset an inspection template, reads state information of image recognition completion and generates a corresponding inspection report, and the inspection template specifically comprises inspection working rules and an inspection report template.
Referring to the attached figure 2, an image identification flow chart of a power supply switch cabinet of urban rail transit is shown, the system controls an engine to adjust a camera holder and zoom through a preset configuration file, the camera holder and the zoom provide a standardized network open interface for the camera through an onvif, the camera transmits through a rtsp real-time stream transmission protocol, transmitted video information obtains rtsp video streams through opencv, all roi, signals and models are obtained through target detection of the obtained rtsp video streams and control engine information, a neural network model is further executed, and finally corresponding states are identified and are in signal association with corresponding feature points of the power supply switch cabinet. Meanwhile, the control engine signal can directly carry out the work of event reporting, alarm uploading, polling report generation and the like.
Referring to fig. 3, which is a flow chart of algorithm model training of the present invention, the customized CNN convolutional neural network model and labeled data are programmed and output based on tensoflow data flow to be a trained CNN convolutional neural network model.
A method of an image recognition system for an urban rail transit power supply switch cabinet comprises the following steps:
s1, training the relevant recognition model of the urban rail transit switch cabinet, and performing model training under a model training module by adopting a convolutional neural network;
s2, recognizing the image by using the trained CNN convolutional neural network model;
and S3, identifying the relevant state information data of the switch cabinet by the image identification system.
More specifically, the specific steps of S1 are as follows:
s11: collecting a large amount of image data of multiple angles such as front view, side view, oblique view and the like of the power variable switch cabinet to form sample image data, and putting the sample data into a sample data set after marking;
s12: preprocessing sample image data acquired in the S11, performing image segmentation according to recognizable types, segmenting key image areas such as an in-cabinet switch state, a three-station switch position, a protective pressing plate position, a voltmeter, an ammeter, a local remote handle position, a heating indicator lamp, a switch energy storage state, an SF6 gas pressure indicator lamp, a charged display, a relay protection device fault alarm indicator lamp and the like, removing noise points of the images, and enhancing details of the image data;
s13: customizing a CNN convolutional neural network model of the power transformer switch cabinet, and establishing a convolutional neural network with 2 convolutional layers, a maximum pooling layer and two full-connection layers, wherein the last full-connection layer has the same dimensionality as input switch cabinet image data;
s14, performing feature extraction on the preprocessed image data in the S12 by using a convolutional neural network, extracting feature points of sample image data, and establishing feature vectors of a switch state, a three-position switch position, a protection pressure plate position, a voltmeter, an ammeter, a local remote handle position, a heating indicator lamp, a switch energy storage state, an SF6 gas pressure indicator lamp, a charged display and a relay protection device fault alarm indicator lamp in the power transformation switch cabinet for the output of 2 full connection layers;
s15: training the characteristics acquired in S14 by using a classifier model, acquiring different training data subsets from the sample data set by using a tensortflow algorithm, and training the model;
s16: circularly executing the step of S15 until the data which are not marked in the sample plate data set are 0, and finishing the model training;
and S17, after model training is finished, integrating the classifiers by adopting majority voting to obtain a final CNN convolutional neural network model, and detecting information such as a switch state, a three-position switch position, a protection pressing plate position, a voltmeter reading, an ammeter reading, a local remote handle position, a heating indicator light, a switch energy storage state, an SF6 gas pressure indicator light, a charged display state, a relay protection device fault alarm indicator light state and the like.
More specifically, the specific steps of S2 are as follows:
s21: a camera is arranged in front of the medium-voltage switch cabinet, the angle and the focal length are adjusted, the camera is aligned to the related equipment to be identified of the medium-voltage switch cabinet, and the related video stream information is collected;
s22, the image recognition module is in network communication with the camera, and an OpenCV library is adopted to capture the video stream with Rtps of the camera;
s23, loading a CNN convolutional neural network model in an image recognition module, configuring a relevant recognition area, detecting a target to obtain all roi, signals and the model, and correcting the recognition area by using the target detection;
s24: the method comprises the steps of processing collected video stream image information in real time, denoising the image, identifying an identification program conveniently, executing a neural network model, detecting the image information and obtaining state information contained in a current image.
More specifically, the specific steps of S3 are as follows:
s31: displaying state information including a signal name, a signal state, a displacement time, and the like in the image recognition system;
s32: and generating an inspection report in the image identification system, wherein the report contains the state information of the power supply switch cabinet which is daily inspected by the operation and maintenance personnel, the identified state information is compared with the related state in the inspection working procedure, whether the inspection item is normal or not is automatically judged, the inspection report is automatically filed when the inspection item is normal, and an alarm is given when the inspection item is abnormal to remind the operation and maintenance personnel to inspect the abnormal item.
S33: preferably, the image recognition system can transmit the recognized state information to the PSCADA system, and double-system signal confirmation of safety interlock related information is carried out, so that automatic alarm of signal double-system confirmation is realized.
S34: preferably, the PSCADA system can call a real-time monitoring picture according to requirements, so that remote video monitoring is realized. The video monitoring function can realize the active uploading of the video when the equipment is abnormal in state and passively receive the video calling according to the requirement.
Claims (7)
1. The image recognition system is characterized by comprising an image acquisition module, an image preprocessing module, a model training module, a state recognition module, a man-machine display module, a report module and a communication interface module, wherein the power supply switch cabinet is connected with the acquisition module, the acquisition module is connected with the image preprocessing module, the image preprocessing module is connected with the state recognition module, the model training module is also connected with the state recognition module, and the state recognition module is further respectively connected with the man-machine display module, the report module and the communication interface module.
2. The image recognition system for the urban rail transit power supply switch cabinet according to claim 1, wherein the communication interface module is connected with the PSCADA system.
3. The image identification system for the urban rail transit power supply switch cabinet according to claim 1, wherein the report module is required to preset an inspection template, read state information of image identification completion and generate a corresponding inspection report, and the inspection template specifically comprises an inspection work rule and an inspection report template.
4. Method for using the image recognition system of the urban rail transit power supply switch cabinet according to any one of claims 1 to 3, characterized by comprising the following steps:
s1, training the relevant recognition model of the urban rail transit switch cabinet, and performing model training under a model training module by adopting a convolutional neural network;
s2, recognizing the image by using the trained CNN convolutional neural network model;
and S3, identifying the relevant state information data of the switch cabinet by the image identification system.
5. The method for the image recognition system of the urban rail transit power supply switch cabinet according to claim 4, wherein the specific steps of S1 are as follows:
s11: collecting a large amount of image data of multiple angles such as front view, side view, oblique view and the like of the power variable switch cabinet to form sample image data, and putting the sample data into a sample data set after marking;
s12: preprocessing sample image data acquired in the S11, performing image segmentation according to recognizable types, segmenting key image areas such as an in-cabinet switch state, a three-station switch position, a protective pressing plate position, a voltmeter, an ammeter, a local remote handle position, a heating indicator lamp, a switch energy storage state, an SF6 gas pressure indicator lamp, a charged display, a relay protection device fault alarm indicator lamp and the like, removing noise points of the images, and enhancing details of the image data;
s13: customizing a CNN convolutional neural network model of the power transformer switch cabinet, and establishing a convolutional neural network with 2 convolutional layers, a maximum pooling layer and two full-connection layers, wherein the last full-connection layer has the same dimensionality as input switch cabinet image data;
s14, performing feature extraction on the preprocessed image data in the S12 by using a convolutional neural network, extracting feature points of sample image data, and establishing feature vectors of a switch state, a three-position switch position, a protection pressure plate position, a voltmeter, an ammeter, a local remote handle position, a heating indicator lamp, a switch energy storage state, an SF6 gas pressure indicator lamp, a charged display and a relay protection device fault alarm indicator lamp in the power transformation switch cabinet for the output of 2 full connection layers;
s15: training the characteristics acquired in S14 by using a classifier model, acquiring different training data subsets from the sample data set by using a tensortflow algorithm, and training the model;
s16: circularly executing the step of S15 until the data which are not marked in the sample plate data set are 0, and finishing the model training;
and S17, after model training is finished, integrating the classifiers by adopting majority voting to obtain a final CNN convolutional neural network model, and detecting information such as a switch state, a three-position switch position, a protection pressing plate position, a voltmeter reading, an ammeter reading, a local remote handle position, a heating indicator light, a switch energy storage state, an SF6 gas pressure indicator light, a charged display state, a relay protection device fault alarm indicator light state and the like.
6. The method for the image recognition system of the urban rail transit power supply switch cabinet according to claim 4, wherein the specific steps of S2 are as follows:
s21: a camera is arranged in front of the medium-voltage switch cabinet, the angle and the focal length are adjusted, the camera is aligned to the related equipment to be identified of the medium-voltage switch cabinet, and the related video stream information is collected;
s22, the image recognition module is in network communication with the camera, and an OpenCV library is adopted to capture the video stream with Rtps of the camera;
s23, loading a CNN convolutional neural network model in an image recognition module, configuring a relevant recognition area, detecting a target to obtain all roi, signals and the model, and correcting the recognition area by using the target detection;
s24: the method comprises the steps of processing collected video stream image information in real time, denoising the image, identifying an identification program conveniently, executing a neural network model, detecting the image information and obtaining state information contained in a current image.
7. The method for the image recognition system of the urban rail transit power supply switch cabinet according to claim 4, wherein the specific steps of S3 are as follows:
s31: displaying state information including a signal name, a signal state, a displacement time, and the like in the image recognition system;
s32: and generating an inspection report in the image identification system, wherein the report contains the state information of the power supply switch cabinet which is daily inspected by the operation and maintenance personnel, the identified state information is compared with the related state in the inspection working procedure, whether the inspection item is normal or not is automatically judged, the inspection report is automatically filed when the inspection item is normal, and an alarm is given when the inspection item is abnormal to remind the operation and maintenance personnel to inspect the abnormal item.
S33: preferably, the image recognition system can transmit the recognized state information to the PSCADA system, and double-system signal confirmation of safety interlock related information is carried out, so that automatic alarm of signal double-system confirmation is realized.
S34: preferably, the PSCADA system can call a real-time monitoring picture according to requirements, so that remote video monitoring is realized. The video monitoring function can realize the active uploading of the video when the equipment is abnormal in state and passively receive the video calling according to the requirement.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110584062.1A CN113177614A (en) | 2021-05-27 | 2021-05-27 | Image recognition system and method for power supply switch cabinet of urban rail transit |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110584062.1A CN113177614A (en) | 2021-05-27 | 2021-05-27 | Image recognition system and method for power supply switch cabinet of urban rail transit |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113177614A true CN113177614A (en) | 2021-07-27 |
Family
ID=76927089
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110584062.1A Pending CN113177614A (en) | 2021-05-27 | 2021-05-27 | Image recognition system and method for power supply switch cabinet of urban rail transit |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113177614A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113741596A (en) * | 2021-08-25 | 2021-12-03 | 中国铁路设计集团有限公司 | Operation and maintenance method and system for railway power supply and distribution |
| CN114039279A (en) * | 2021-09-29 | 2022-02-11 | 交控科技股份有限公司 | Control cabinet monitoring method and system in rail transit station |
| CN114359844A (en) * | 2022-03-21 | 2022-04-15 | 广州银狐科技股份有限公司 | AED equipment state monitoring method and system based on color recognition |
| CN117412151A (en) * | 2023-09-14 | 2024-01-16 | 国电银河海兴新能源有限公司 | Track camera monitoring method and cleaning device replacement structure |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104199454A (en) * | 2014-09-27 | 2014-12-10 | 江苏华宏实业集团有限公司 | Control system of inspection robot for high voltage line |
| CN104242454A (en) * | 2014-09-24 | 2014-12-24 | 刘瑞 | Power monitoring system of rail transit power supply system |
| CN205759288U (en) * | 2016-05-18 | 2016-12-07 | 江苏泽昌环保科技发展有限公司 | One remotely monitors automatic fire protection system |
| CN106709511A (en) * | 2016-12-08 | 2017-05-24 | 华中师范大学 | Urban rail transit panoramic monitoring video fault detection method based on depth learning |
| CN108573283A (en) * | 2018-04-12 | 2018-09-25 | 大连理工大学 | A kind of anti-design method failed to report of notch of switch machine monitoring |
| CN108616715A (en) * | 2016-12-09 | 2018-10-02 | 青岛璐琪信息科技有限公司 | A kind of remote video monitoring alarm system and method |
| CN109359697A (en) * | 2018-10-30 | 2019-02-19 | 国网四川省电力公司广元供电公司 | Graph image recognition methods and inspection system used in a kind of power equipment inspection |
| CN109389180A (en) * | 2018-10-30 | 2019-02-26 | 国网四川省电力公司广元供电公司 | A power equipment image-recognizing method and inspection robot based on deep learning |
| CN110415220A (en) * | 2019-07-09 | 2019-11-05 | 国电大渡河瀑布沟发电有限公司 | A kind of device intelligence method for inspecting of large hydropower station |
| CN111707906A (en) * | 2020-07-14 | 2020-09-25 | 广州白云电器设备股份有限公司 | Method for realizing fault location of subway direct-current traction power supply system |
| CN112131924A (en) * | 2020-07-10 | 2020-12-25 | 国网河北省电力有限公司雄安新区供电公司 | Transformer substation equipment image identification method based on density cluster analysis |
-
2021
- 2021-05-27 CN CN202110584062.1A patent/CN113177614A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104242454A (en) * | 2014-09-24 | 2014-12-24 | 刘瑞 | Power monitoring system of rail transit power supply system |
| CN104199454A (en) * | 2014-09-27 | 2014-12-10 | 江苏华宏实业集团有限公司 | Control system of inspection robot for high voltage line |
| CN205759288U (en) * | 2016-05-18 | 2016-12-07 | 江苏泽昌环保科技发展有限公司 | One remotely monitors automatic fire protection system |
| CN106709511A (en) * | 2016-12-08 | 2017-05-24 | 华中师范大学 | Urban rail transit panoramic monitoring video fault detection method based on depth learning |
| CN108616715A (en) * | 2016-12-09 | 2018-10-02 | 青岛璐琪信息科技有限公司 | A kind of remote video monitoring alarm system and method |
| CN108573283A (en) * | 2018-04-12 | 2018-09-25 | 大连理工大学 | A kind of anti-design method failed to report of notch of switch machine monitoring |
| CN109359697A (en) * | 2018-10-30 | 2019-02-19 | 国网四川省电力公司广元供电公司 | Graph image recognition methods and inspection system used in a kind of power equipment inspection |
| CN109389180A (en) * | 2018-10-30 | 2019-02-26 | 国网四川省电力公司广元供电公司 | A power equipment image-recognizing method and inspection robot based on deep learning |
| CN110415220A (en) * | 2019-07-09 | 2019-11-05 | 国电大渡河瀑布沟发电有限公司 | A kind of device intelligence method for inspecting of large hydropower station |
| CN112131924A (en) * | 2020-07-10 | 2020-12-25 | 国网河北省电力有限公司雄安新区供电公司 | Transformer substation equipment image identification method based on density cluster analysis |
| CN111707906A (en) * | 2020-07-14 | 2020-09-25 | 广州白云电器设备股份有限公司 | Method for realizing fault location of subway direct-current traction power supply system |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113741596A (en) * | 2021-08-25 | 2021-12-03 | 中国铁路设计集团有限公司 | Operation and maintenance method and system for railway power supply and distribution |
| CN113741596B (en) * | 2021-08-25 | 2022-10-04 | 中国铁路设计集团有限公司 | Operation and maintenance method and system for railway power supply and distribution |
| CN114039279A (en) * | 2021-09-29 | 2022-02-11 | 交控科技股份有限公司 | Control cabinet monitoring method and system in rail transit station |
| CN114359844A (en) * | 2022-03-21 | 2022-04-15 | 广州银狐科技股份有限公司 | AED equipment state monitoring method and system based on color recognition |
| CN117412151A (en) * | 2023-09-14 | 2024-01-16 | 国电银河海兴新能源有限公司 | Track camera monitoring method and cleaning device replacement structure |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113177614A (en) | Image recognition system and method for power supply switch cabinet of urban rail transit | |
| CN111507308B (en) | Transformer substation safety monitoring system and method based on video identification technology | |
| CN110826538B (en) | Abnormal off-duty identification system for electric power business hall | |
| CN104678963B (en) | A kind of system and method for the acquisition instrument facility information based on computer vision | |
| CN108764668A (en) | A kind of facilities management system and method based on BIM technology | |
| CN104597903B (en) | Transformer substation routing inspection robot for automatic meter reading | |
| CN109271881B (en) | Safety management and control method and device for personnel in transformer substation and server | |
| CN112018892A (en) | Electric power operation and maintenance remote guidance system | |
| CN111722714A (en) | Digital substation metering operation inspection auxiliary method based on AR technology | |
| CN109325605A (en) | Electric power based on augmented reality AR technology believes logical computer room inspection platform and method for inspecting | |
| CN111526330A (en) | Transformer substation equipment state intelligent recognition system based on machine vision | |
| CN109784138B (en) | Image datamation inspection method for unmanned transformer substation | |
| CN107133592B (en) | Human body target feature detection algorithm for power substation by fusing infrared thermal imaging and visible light imaging technologies | |
| CN112290546B (en) | Transformer substation primary equipment fault discrimination method based on man-machine co-fusion | |
| CN110069975A (en) | A kind of conducting wire neural network based opens burst recognition methods and system | |
| CN110807460A (en) | Transformer substation intelligent patrol system based on image recognition and application method thereof | |
| CN113988633A (en) | Anti-misoperation system of digital twin transformer substation | |
| CN112651516A (en) | Intelligent inspection system and method for transformer substation machine room based on AR technology | |
| CN114665608B (en) | Intelligent sensing inspection system and method for transformer substation | |
| CN115393566A (en) | Fault identification and early warning method and device for power equipment, storage medium and equipment | |
| CN212255543U (en) | Intelligent inspection equipment for high-voltage cable | |
| CN113361686A (en) | Multilayer heterogeneous multi-mode convolutional neural network integrated robot inspection method | |
| CN115939996A (en) | Automatic inspection system of power inspection robot | |
| CN115131505A (en) | Multi-system fusion's of transformer substation panorama perception system | |
| CN111431284A (en) | BIM technology-based intelligent transformer substation management and control system |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210727 |
|
| RJ01 | Rejection of invention patent application after publication |