Maintenance method and system for power equipment

Abstract

The invention discloses a maintenance method and system for power equipment, and the method comprises the steps: recognizing a maintenance image of the power equipment, determining the type data of the current power equipment, obtaining corresponding necessary pre-operation data according to the standard data of each maintenance behavior determined by the type data, and carrying out the maintenance of the power equipment. And performing behavior identification on the maintenance action of the maintenance personnel according to the maintenance personnel image, judging the maintenance action according to an identification result, the maintenance behavior standard data and the corresponding necessary pre-operation data, and generating an abnormal early warning signal when the maintenance action is judged not to meet a preset safety standard, according to the method, the feedback information of the maintainer obtained in the maintenance process of the current power equipment is recognized, the abnormal early warning signal is corrected according to the recognition result, deviation and omission in the operation process can be found and corrected in time, safety accidents caused by human negligence or misoperation are effectively avoided, and the safety of the power equipment is improved. And the safety and the reliability of the maintenance operation are obviously improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power maintenance, and in particular, to a maintenance method and system for power equipment. Background Art

[0002] With the continuous development of modern power maintenance technology, the maintenance and safety inspection of power equipment have received increasing attention and have become an indispensable part of ensuring the safe and stable operation of the power grid.

[0003] In the existing power equipment maintenance process, at the actual operation level, many deficiencies and limitations are exposed. For example, operators often rely on work experience or paper documents to perform a series of complex power equipment maintenance operations. Since the information presentation method of this maintenance method is relatively single, it is very easy to cause omission or misoperation of key steps. Once a necessary operation is skipped or executed improperly, it may not only affect the normal operation of the equipment, but also cause serious safety accidents and incalculable losses.

[0004] Therefore, how to optimize the power equipment maintenance process to improve the maintenance effect has become a technical problem that needs to be urgently solved by those skilled in the art. Summary of the Invention

[0005] The present invention provides a maintenance method and system for power equipment to improve the power equipment maintenance process.

[0006] To solve the above technical problems, an embodiment of the present invention provides a maintenance method for power equipment, including: Obtain a scene image during the power equipment maintenance process, where the scene image includes an image of a maintenance personnel and an image of a power equipment.

[0007] Identify the power equipment image to determine the type data of the current power equipment.

[0008] According to each maintenance behavior standard data determined by the type data, determine the necessary pre-operation data corresponding to each maintenance behavior standard data.

[0009] Perform behavior recognition on the maintenance actions of the maintenance personnel according to the image of the maintenance personnel, and judge the maintenance actions according to the recognition result, the maintenance behavior standard data, and the corresponding necessary pre-operation data. When it is judged that the maintenance action does not meet the preset safety standard, generate an abnormal warning signal.

[0010] Identify the feedback information of the maintenance personnel obtained during the current power equipment maintenance process, and correct the abnormal warning signal according to the recognition result.

[0011] Generate a matching maintenance log result based on the corrected abnormal warning signal, where the maintenance log result at least includes the monitoring log result during the maintenance process of the current power equipment.

[0012] Further, the recognition of the type data of the current power equipment by identifying the power equipment image includes: Obtain the first power equipment image collected by the image acquisition device.

[0013] Perform denoising and image enhancement processing on the first power equipment image to obtain a second power equipment image.

[0014] Use the histogram equalization algorithm to perform contrast equalization processing on the second power equipment image to obtain a third power equipment image.

[0015] Extract features from the third power equipment image based on the YOLO algorithm to obtain equipment feature information.

[0016] Identify the current power equipment in the third power equipment image based on the equipment feature information to obtain the equipment type of the current power equipment.

[0017] Further, the behavior recognition of the maintenance actions of the maintenance personnel according to the maintenance personnel image includes: Input the preprocessed maintenance personnel image into the OpenPose model for human body recognition to obtain the positions of the human body key points of the maintenance personnel.

[0018] Obtain the posture information of the maintenance personnel according to the positions of the human body key points.

[0019] Construct an operation action sequence according to the positions of the human body key points in the maintenance personnel images of adjacent frames.

[0020] Perform behavior recognition on the maintenance actions of the maintenance personnel according to the operation action sequence.

[0021] Further, the behavior recognition of the maintenance actions of the maintenance personnel according to the operation action sequence includes: Perform downsampling processing on the first operation action sequence to obtain a second operation action sequence.

[0022] Input the second operation action sequence into the pre-constructed LSTM model to obtain the probability distribution information of the behavior categories output by the LSTM model.

[0023] Perform recognition and judgment on the maintenance actions of the maintenance personnel according to the output result of the LSTM model.

[0024] Further, determining the necessary pre-operation data corresponding to each of the maintenance behavior standard data according to the determined maintenance behavior standard data of each type includes: Retrieving the corresponding maintenance behavior standard data from the database according to the type data.

[0025] Obtaining the necessary pre-operation data corresponding to each maintenance operation in the maintenance behavior standard data according to the directed dependency graph of power maintenance.

[0026] Further, judging the maintenance action according to the recognition result, the maintenance behavior standard data and the corresponding necessary pre-operation data includes: Constructing a maintenance safety standard graph according to the type data, the maintenance behavior standard data and the necessary pre-operation data, where the maintenance safety standard graph includes the standard behavior feature vectors and dependency relationships of each of the maintenance behavior standard data and each of the necessary pre-operation data.

[0027] Performing feature extraction on the maintenance action to obtain the maintenance action feature vector of the maintenance personnel.

[0028] Based on the graph attention mechanism, comparing the maintenance action feature vector with the standard behavior feature vector to obtain the behavior difference degree between the maintenance action and the safety standard.

[0029] Evaluating whether the maintenance action meets the preset safety standard according to the behavior difference degree.

[0030] Further, the feedback information of the maintenance personnel includes voice feedback information.

[0031] Further, identifying the feedback information of the maintenance personnel obtained during the current power equipment maintenance process and correcting the abnormal warning signal according to the recognition result includes: Performing noise reduction and volume adjustment on the voice feedback information obtained by the voiceprint acquisition device to obtain voice detection data.

[0032] Obtaining the corresponding skip keywords preset for the maintenance action.

[0033] Performing keyword matching operation on the voice detection data according to the skip keywords. If the matching is successful, it is determined that the voice feedback information contains the skip keywords of the maintenance action, and the abnormal warning signal is corrected.

[0034] Further, the maintenance log result also includes abnormal warning details, maintenance task assignment and progress, communication and collaboration records of maintenance personnel, and equipment historical maintenance records.

[0035] Another embodiment of the present invention provides an overhaul system for power equipment, including: An image acquisition module, configured to acquire a scene image during the overhaul of the power equipment, where the scene image includes an overhaul personnel image and a power equipment image.

[0036] An equipment identification module, configured to identify the power equipment image and determine the type data of the current power equipment.

[0037] A standard data acquisition module, configured to determine necessary pre-operation data corresponding to each overhaul behavior standard data according to each overhaul behavior standard data determined by the type data.

[0038] A signal warning module, configured to perform behavior recognition on the overhaul actions of the overhaul personnel according to the overhaul personnel image, judge the overhaul actions according to the recognition result, the overhaul behavior standard data, and the corresponding necessary pre-operation data, and generate an abnormal warning signal when it is judged that the overhaul action does not meet the preset safety standard.

[0039] A signal correction module, configured to identify the feedback information of the overhaul personnel obtained during the overhaul of the current power equipment, and correct the abnormal warning signal according to the recognition result.

[0040] A log generation module, configured to generate a matching overhaul log result with the corrected abnormal warning signal, where the overhaul log result at least includes a monitoring log result during the overhaul of the current power equipment.

[0041] Compared with the prior art, the beneficial effects of the embodiments of the present invention are at least one of the following: By real-time monitoring of the overhaul actions and voice information of the overhaul personnel and intelligent comparison with the preset safety standards and necessary operation steps, it is possible to timely discover and correct the deviations and omissions in the operation process, effectively avoid safety accidents caused by human negligence or improper operation, and significantly improve the safety and reliability of the overhaul operation; by integrating intelligent means such as image recognition, voiceprint recognition, and graph attention analysis, the overhaul process is standardized and automated, greatly reducing the burden on overhaul personnel and improving work efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 It is a step flow chart of the overhaul method for power equipment provided by the embodiment of the present invention; Figure 2 It is a structural block diagram of the overhaul system for power equipment provided by the embodiment of the present invention. DETAILED DESCRIPTION

[0043] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. The purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0044] In the description of the present application, the terms "first", "second", "third", etc. are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first", "second", "third", etc. may explicitly or implicitly include one or more of such features. In the description of the present application, unless otherwise specified, the meaning of "a plurality" is two or more.

[0045] In the description of the present application, it should be noted that unless otherwise clearly defined and limited, the terms "installed", "connected", "connected" should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may be a mechanical connection or an electrical connection; it may be directly connected, or indirectly connected through an intermediate medium, and it may be the communication inside two elements. The terms "vertical", "horizontal", "left", "right", "up", "down" and similar expressions used herein are only for the purpose of illustration, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus cannot be understood as a limitation of the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific circumstances.

[0046] In the description of the present application, it should be noted that unless otherwise defined, all technical and scientific terms used in the present invention have the same meaning as commonly understood by those of ordinary skill in the technical field to which this technology belongs. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific circumstances.

[0047] An embodiment of the present invention provides a maintenance method for power equipment. Specifically, please refer to Figure 1 , Figure 1 which shows the step flow chart of the maintenance method for power equipment in one of the embodiments of the present invention, including steps S11 to S16: Step S11: Obtain the scene image during the maintenance of the power equipment. The scene image includes the image of the maintenance personnel and the image of the power equipment.

[0048] To monitor the maintenance process in real time, ensure the safety of the maintenance personnel and the correct operation of the equipment, it is necessary to obtain the scene image during the maintenance of the power equipment.

[0049] Specifically, in this embodiment, a high-definition camera is used as the image acquisition device to collect the scene image. During the maintenance process, it is necessary to identify the power equipment and the maintenance personnel. Therefore, the scene image includes the image of the maintenance personnel and the image of the power equipment.

[0050] The acquisition of the scene image provides visual data for the monitoring of the maintenance process, which is used for subsequent image recognition and behavior analysis, improving the visualization and traceability of the maintenance process and reducing human errors.

[0051] Step S12: Identify the image of the power equipment to determine the type data of the current power equipment.

[0052] Since different types of power equipment have different maintenance standards and safety requirements, it is necessary to identify the type of the current power equipment in the power equipment image to match the corresponding necessary maintenance operations.

[0053] The specific identification process is as follows: Obtain the first power equipment image collected by the image acquisition device. The first power equipment image is used as the original image, and it is necessary to preprocess and check the image. Specifically, check the integrity of the image, check the image quality, etc. The process of checking the integrity of the image is to confirm that the image has no damaged or missing parts, and checking the image quality is to evaluate the clarity, brightness, etc. of the image to ensure that it meets the requirements of subsequent processing.

[0054] The image may contain noise, which affects the recognition accuracy. Therefore, denoise the first power equipment image and apply image enhancement techniques, such as sharpening, contrast adjustment, etc., to improve the image quality and obtain the second power equipment image.

[0055] Adjust the second power equipment image to a unified size to meet the input requirements of the YOLO algorithm and ensure that all input images have a consistent size.

[0056] The second power equipment image is processed by the histogram equalization algorithm for contrast equalization to obtain the third power equipment image. Histogram Equalization is a commonly used image enhancement technique, mainly used to improve the contrast of images, making the details in the images more clearly visible. It redistributes the brightness values of the pixels in the image, making the grayscale histogram of the image more uniform. In some cases, the images taken during the power maintenance process may appear dull and lack contrast due to poor lighting conditions or limitations of the imaging equipment. Histogram equalization can stretch the dynamic range of the image, making the bright areas brighter and the dark areas darker, thus significantly improving the visual quality of the image.

[0057] Feature extraction is a key step in identifying the type of power equipment. The YOLO algorithm can simultaneously complete object detection and feature extraction in a single forward pass. When processing power equipment images, the YOLO algorithm can accurately detect the power equipment in the image and extract key features. This feature information will be used in the subsequent identification steps. In this embodiment, the YOLO algorithm is used to extract features from the third power equipment image to improve the recognition speed and accuracy, obtaining equipment feature information.

[0058] Based on the equipment feature information, the current power equipment in the third power equipment image is identified to obtain the equipment type of the current power equipment.

[0059] After extracting the equipment feature information, the next step is to identify these features to determine the type of power equipment. This step is usually achieved through classifiers such as Support Vector Machines (SVM), neural networks, etc. During the identification process, the extracted feature information needs to be matched with a known equipment feature library to find the most similar equipment type. Since there are a wide variety of power equipment and the features of each equipment are different, this step requires ensuring the accuracy and robustness of the classifier. Finally, the identification result will give the equipment type of the current power equipment, providing important information for subsequent equipment management and maintenance.

[0060] Step S13: According to the standard data of each maintenance behavior determined from the type data, determine the necessary pre-operation data corresponding to each standard data of the maintenance behavior.

[0061] Retrieve the corresponding maintenance behavior standard data from the database according to the type data. The key to this step is to ensure the accuracy of the type data and the integrity of the database. The database used in this embodiment is the database within the power system that records the maintenance operation information of power equipment. The type data represents information such as the type of the current power equipment, possible fault types, or maintenance requirements. These information serve as the basis for retrieving the maintenance behavior standard data, and the maintenance behavior standard data required for the current power equipment is obtained according to the type data.

[0062] The directed dependency graph of power maintenance is a graphical tool that represents the dependency relationships between maintenance operations, and at least includes each maintenance operation, the necessary pre-operations corresponding to each maintenance operation, etc., as well as the dependency relationships, sequence, and logical relationships between them.

[0063] Use the directed dependency graph to analyze each maintenance operation in the maintenance behavior standard data, determine the dependency relationships between them, and extract the necessary pre-operation data corresponding to each maintenance operation accordingly.

[0064] Step S14, perform behavior recognition on the maintenance actions of the maintenance personnel according to the image of the maintenance personnel, and judge the maintenance actions according to the recognition result, the maintenance behavior standard data, and the corresponding necessary pre-operation data. When it is judged that the maintenance action does not meet the preset safety standard, an abnormal warning signal is generated.

[0065] As an advanced human pose estimation algorithm, the OpenPose model can accurately identify the positions of key points of the human body in the image, such as joints, head, hands, etc. These key point positions provide key data for subsequent acquisition of pose information and construction of operation action sequences.

[0066] Input the preprocessed image of the maintenance personnel into the OpenPose model for human body recognition to obtain the positions of the key points of the human body of the maintenance personnel. Through accurate detection of the key points of the human body, it provides a reliable data basis for subsequent steps and helps to accurately analyze the posture and actions of the maintenance personnel.

[0067] After obtaining the positions of the key points of the human body, it is necessary to use this key point information to extract the pose information of the maintenance personnel. This includes analyzing the relative positions, angles, and dynamic changes of the key points to reflect the overall movement trend and local details of the maintenance personnel, and obtaining the pose information of the maintenance personnel according to the positions of the key points of the human body.

[0068] In order to analyze the continuous actions of maintenance personnel, it is necessary to connect the positions of human key points in adjacent frame images to construct an operation action sequence. This step needs to ensure the coherence and accuracy of the action sequence so that the subsequent behavior recognition model can correctly identify the actions of maintenance personnel. The construction of the operation action sequence provides dynamic data support for subsequent behavior recognition and helps to achieve precise analysis of the continuous actions of maintenance personnel.

[0069] When processing continuous action sequences, due to the large amount of data and possible redundant information, it is necessary to perform downsampling on the first operation action sequence. Downsampling can reduce the amount of data, improve processing efficiency, and retain key action information to obtain the second operation action sequence. Through downsampling, a more concise and efficient action sequence can be obtained.

[0070] Input the downsampled second operation action sequence into a pre-constructed LSTM model. The model will output the probability distribution information of behavior categories. The LSTM model can capture long-term dependencies in sequence data and is suitable for processing data of the continuous actions of maintenance personnel. Through the application of the LSTM model, accurate identification of the action categories of maintenance personnel can be achieved.

[0071] The last step is to identify and judge the maintenance actions of maintenance personnel based on the output results of the LSTM model. It is necessary to match the probability distribution information output by the model with preset behavior categories to determine the specific action categories of maintenance personnel.

[0072] Integrate type data, maintenance behavior standard data, and necessary pre-operation data to construct a maintenance safety standard diagram. The maintenance safety standard diagram not only includes the standard behavior feature vectors of each of the maintenance behavior standard data and each of the necessary pre-operation data, but also includes the dependency relationships between these behaviors. Constructing the maintenance safety standard diagram provides a clear standard and framework for subsequent comparison of maintenance actions, helps to standardize the maintenance process, and can also ensure objectivity and consistency in the evaluation process.

[0073] In addition, the visualization feature of the maintenance safety standard diagram helps maintenance personnel better understand the maintenance safety standards, thereby improving the overall safety awareness.

[0074] After obtaining the actual actions of maintenance personnel, it is necessary to convert them into feature vectors through feature extraction technology. The accuracy of feature extraction directly affects the results of subsequent comparison and evaluation, providing the necessary data basis for subsequent comparison and evaluation. Through precise feature extraction, quantitative analysis of maintenance actions can be achieved, so as to more objectively evaluate whether they meet safety standards.

[0075] The maintenance action feature vector is compared with the standard behavior feature vector using the graph attention mechanism to obtain the behavior difference degree between the maintenance action and the safety standard. The graph attention mechanism is a deep learning technology that can automatically learn the correlation weights between nodes and aggregate information based on these weights. During the comparison process, this mechanism can dynamically adjust the attention focus to more accurately capture the differences between the maintenance action and the standard behavior, enabling fine-grained analysis of the maintenance action, thereby more accurately evaluating its differences from the safety standard, not only improving the accuracy and efficiency of the evaluation, but also helping to discover potential safety hazards and improper operations.

[0076] After the comparison is completed, it is necessary to evaluate whether the maintenance action meets the preset safety standard based on the behavior difference degree. The behavior difference degree evaluation and safety standard judgment are the core links of the solution, which are directly related to the safety and efficiency of the maintenance work. Through accurate evaluation, improper operations can be discovered and corrected in a timely manner, thereby avoiding potential safety risks.

[0077] Step S15: Identify the feedback information from the maintenance personnel obtained during the current power equipment maintenance process, and correct the abnormal warning signal according to the identification result.

[0078] Specifically, the feedback information from the maintenance personnel used in this embodiment is voice feedback information.

[0079] During the power equipment maintenance process, the maintenance personnel may provide key information through voice feedback, which is crucial for identifying the maintenance progress, abnormal situations, and operation suggestions. However, the on-site environment often has various noise interferences, such as equipment operation sounds, personnel conversation sounds, etc., which will affect the clarity of the voice feedback information. Therefore, it is necessary to perform noise reduction processing on the voice feedback information obtained by the voiceprint acquisition device to reduce the interference of background noise.

[0080] In addition, it is also necessary to perform appropriate volume adjustment according to the original volume size of the voice to ensure the accuracy and reliability of subsequent processing. By performing noise reduction and volume adjustment to obtain voice detection data, the clarity of the voice feedback information can be significantly improved, providing an accurate data basis for subsequent keyword matching and abnormal warning signal correction, and helping to reduce false alarms and missed alarms.

[0081] In the power equipment maintenance process, sometimes the monitoring results may be inaccurate. For example, if a necessary maintenance action and its necessary pre-operation have been completed but not detected, false alarms may occur and incorrect warnings may be issued. At this time, the operator can trigger keyword detection by talking to the voiceprint acquisition device in the monitoring equipment, such as "I have completed the power verification work", so as to skip this process.

[0082] In addition, there are some routine or known-safe operations in power maintenance, which do not require real-time monitoring or warning by the system. To improve the flexibility of the system and the user experience, a series of skip keywords can be preset, which are associated with specific maintenance actions. When the maintenance personnel complete these operations, if the image recognition system fails to accurately capture or identify them, the maintenance personnel can convey the information that the operation has been completed and is safe to the system by saying the corresponding skip keywords. By presetting skip keywords, the system can intelligently identify and skip those known-safe operations, reducing unnecessary warnings and interference, and improving the continuity and efficiency of the maintenance work.

[0083] After obtaining the preprocessed voice detection data and the preset skip keywords, the system needs to perform a keyword matching operation to match the skip keywords with the voice detection data. If the match is successful, it is determined that the voice feedback information contains the skip keyword of the maintenance action, and the abnormal warning signal is corrected, that is, the abnormal warning signal is cancelled.

[0084] Through the keyword matching operation, the system can respond to the voice commands of the maintenance personnel in real time and accurately, and intelligently correct the abnormal warning signal. This not only reduces false alarms and missed alarms caused by misjudgment, improves the accuracy and reliability of maintenance, but also gives the maintenance personnel greater initiative and control, enabling them to respond more flexibly and efficiently to various situations during the maintenance process, thereby improving the quality and efficiency of the overall maintenance work.

[0085] Step S16, generate a matching maintenance log result based on the corrected abnormal warning signal, where the maintenance log result at least includes the monitoring log result during the maintenance process of the current power equipment.

[0086] The maintenance log result also includes details of abnormal warnings, maintenance task allocation and progress, records of communication and collaboration among maintenance personnel, and historical maintenance records of equipment.

[0087] During the power equipment maintenance process, the accuracy and timeliness of the abnormal warning signal are crucial for ensuring equipment safety and reducing fault downtime.

[0088] After the recognition of the feedback information of the maintenance personnel and the correction of the abnormal warning signal in the foregoing steps, the maintenance system obtains more accurate abnormal warning information. Next, starting from these corrected abnormal warning signals, maintenance log entries can be generated. The detailed information of the warning signal, including warning time, warning type, warning level, associated equipment, etc., is accurately recorded in the maintenance log to provide data support for subsequent analysis and decision-making.

[0089] The maintenance method of the power equipment of the present invention can timely detect and correct the deviations and omissions in the operation process by real-time monitoring the maintenance actions and voice information of the maintenance personnel and intelligently comparing them with the preset safety standards and necessary operation steps, effectively avoiding safety accidents caused by human negligence or improper operation, and significantly improving the safety and reliability of the maintenance operation; by integrating intelligent means such as image recognition, voiceprint recognition, and graph attention analysis, the maintenance process is standardized and automated, greatly reducing the burden on maintenance personnel and improving work efficiency.

[0090] The embodiment of the present invention also provides a maintenance device for power equipment, which is used to execute the maintenance method of the power equipment as described above. Figure 2 It is a structural block diagram of the maintenance device for power equipment according to the embodiment of the present invention. The device includes: An image acquisition module 21, which is used to acquire the scene image during the maintenance of the power equipment. The scene image includes the image of the maintenance personnel and the image of the power equipment.

[0091] An equipment identification module 22, which is used to identify the power equipment image and determine the type data of the current power equipment.

[0092] A standard data acquisition module 23, which is used to determine the necessary pre-operation data corresponding to each maintenance behavior standard data according to each maintenance behavior standard data determined by the type data.

[0093] A signal warning module 24, which is used to perform behavior recognition on the maintenance actions of the maintenance personnel according to the image of the maintenance personnel, and judge the maintenance actions according to the recognition result, the maintenance behavior standard data, and the corresponding necessary pre-operation data. When it is judged that the maintenance action does not meet the preset safety standard, an abnormal warning signal is generated.

[0094] A signal correction module 25, which is used to identify the feedback information of the maintenance personnel obtained during the maintenance of the current power equipment, and correct the abnormal warning signal according to the recognition result.

[0095] A log generation module 26, which is used to generate a matching maintenance log result with the corrected abnormal warning signal. Among them, the maintenance log result at least includes the monitoring log result during the maintenance of the current power equipment.

[0096] The technical features and technical effects of the system proposed in the embodiments of the present invention are the same as those of the method proposed in the embodiments of the present invention, and will not be elaborated herein. Each module in the above system can be implemented in whole or in part by software, hardware, and their combination. Each of the above modules can be embedded in the processor in the computer device in the form of hardware or be independent of it, or can be stored in the memory in the computer device in the form of software, so as to facilitate the processor to call and execute the operations corresponding to the above modules.

[0097] The above embodiments only represent several implementation manners of the present invention. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the scope of the patent of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the appended claims.

Claims

1. A method for repairing electric power equipment, characterized in that: include: Acquire a scene image during the maintenance process of the electric power equipment, wherein the scene image includes an image of a maintenance person and an image of the electric power equipment; Identify the electric power equipment image and determine the type data of the current electric power equipment; According to each inspection behavior standard data determined by the type data, determining necessary pre-operation data corresponding to each inspection behavior standard data; Performing behavioral recognition on the maintenance action of the maintenance personnel according to the maintenance personnel image, judging the maintenance action according to the recognition result, the maintenance behavior standard data and the corresponding necessary pre-operation data, and generating an abnormal warning signal when it is judged that the maintenance action does not meet the preset safety standard; Identify the maintenance personnel feedback information obtained during the current power equipment maintenance process, and modify the abnormal warning signal according to the identification result; A matching maintenance log result is generated using the corrected abnormal warning signal, wherein the maintenance log result at least includes a monitoring log result during the maintenance process of the current power equipment.

2. The method for repairing electric power equipment according to claim 1, characterized in that: The identifying the electric power equipment image and determining the type data of the current electric power equipment includes: Acquire a first electric power equipment image acquired by an image acquisition device; Performing denoising and image enhancement processing on the first electric power equipment image to obtain a second electric power equipment image; Performing contrast equalization processing on the second electric power equipment image using a histogram equalization algorithm to obtain a third electric power equipment image; Performing feature extraction on the third power equipment image based on the YOLO algorithm to obtain equipment feature information; The current power device in the third power device image is identified based on the device characteristic information to obtain a device type of the current power device.

3. The method for repairing electric power equipment according to claim 1, characterized in that: The performing behavior recognition on the maintenance action of the maintenance personnel according to the maintenance personnel image includes: Input the preprocessed image of the maintenance personnel into the OpenPose model for human body recognition to obtain the key point positions of the maintenance personnel; Acquiring posture information of the maintenance personnel according to the positions of the key points of the human body; Constructing an operation action sequence according to the positions of the key points of the human body in the maintenance personnel images of adjacent frames; Behavior recognition is performed on the maintenance actions of the maintenance personnel according to the operation action sequence.

4. The method for repairing electric power equipment according to claim 3, characterized in that: The performing behavior recognition on the maintenance action of the maintenance personnel according to the operation action sequence includes: Downsampling the first operation action sequence to obtain a second operation action sequence; Inputting the second operation action sequence into a pre-built LSTM model to obtain probability distribution information of the behavior category output by the LSTM model; The maintenance actions of the maintenance personnel are identified and judged according to the output results of the LSTM model.

5. The method for repairing electric power equipment according to claim 1, characterized in that: The determining of necessary pre-operation data corresponding to each of the inspection behavior standard data determined by the type data includes: Retrieving corresponding inspection behavior standard data from a database according to the type data; According to the directed dependency graph of power maintenance, necessary pre-operation data corresponding to each maintenance operation in the maintenance behavior standard data is obtained.

6. The method for repairing electric power equipment according to claim 1, characterized in that: The judging of the maintenance action according to the recognition result, the maintenance behavior standard data and the corresponding necessary pre-operation data includes: Constructing a maintenance safety standard diagram according to the type data, the maintenance behavior standard data and the necessary pre-operation data, wherein the maintenance safety standard diagram includes standard behavior feature vectors and dependency relationships of each of the maintenance behavior standard data and each of the necessary pre-operation data; Extracting features of the maintenance action to obtain a maintenance action feature vector of the maintenance personnel; Based on the graph attention mechanism, the maintenance action feature vector is compared with the standard behavior feature vector to obtain the behavior difference between the maintenance action and the safety standard; Whether the maintenance action meets the preset safety standard is evaluated based on the behavior difference.

7. The method for repairing electric power equipment according to claim 1, characterized in that: The maintenance personnel feedback information includes voice feedback information.

8. The method for repairing electric power equipment according to claim 7, characterized in that: The identifying of the maintenance personnel feedback information obtained during the current power equipment maintenance process, and correcting the abnormal warning signal according to the identification result, includes: Performing noise reduction and volume adjustment on the voice feedback information obtained by the voiceprint collection device to obtain voice detection data; Obtaining a corresponding skip keyword preset for the maintenance action; A keyword matching operation is performed on the voice detection data according to the skip keyword. If the match is successful, it is determined that the voice feedback information contains the skip keyword of the maintenance action, and the abnormal warning signal is corrected.

9. The method for repairing electric power equipment according to claim 1, characterized in that: The maintenance log results also include abnormal warning details, maintenance task allocation and progress, maintenance personnel communication and collaboration records, and equipment historical maintenance records.

10. A maintenance system for electric power equipment, characterized in that: include: An image acquisition module is used to obtain scene images during the maintenance of power equipment, wherein the scene images include images of maintenance personnel and images of power equipment; An equipment identification module, used to identify the electric equipment image and determine the type data of the current electric equipment; A standard data acquisition module, used to determine necessary pre-operation data corresponding to each of the inspection behavior standard data determined by the type data; A signal warning module is used to identify the maintenance action of the maintenance personnel according to the maintenance personnel image, judge the maintenance action according to the identification result, the maintenance behavior standard data and the corresponding necessary pre-operation data, and generate an abnormal warning signal when it is judged that the maintenance action does not meet the preset safety standard; A signal correction module, used to identify the feedback information of the maintenance personnel obtained during the current power equipment maintenance process, and to correct the abnormal warning signal according to the identification result; A log generation module is used to generate a matching maintenance log result based on the corrected abnormal warning signal, wherein the maintenance log result at least includes a monitoring log result during the maintenance process of the current power equipment.

Images