Integrated power distribution cabinet fault diagnosis system based on edge computing

Abstract

This invention relates to the field of power equipment fault diagnosis technology and discloses an integrated distribution cabinet fault diagnosis system based on edge computing, including a data acquisition unit, a fault modeling unit, a risk assessment unit, a fault diagnosis module, and a maintenance assessment unit. This invention uses a convolutional neural network to construct a fault identification model, trains and tests it based on historical fault data, and achieves intelligent identification and judgment of fault types. This significantly reduces misjudgments or missed diagnoses caused by human subjective factors, improving the objectivity and accuracy of diagnosis. By dynamically assessing the risk level of the distribution cabinet and adaptively adjusting the data acquisition frequency according to the risk level, it optimizes the allocation efficiency of edge computing resources while ensuring monitoring effectiveness. Furthermore, it has maintenance assessment and closed-loop handling functions, quantitatively evaluating maintenance effectiveness through a fault maintenance index, and initiating a re-inspection or secondary diagnosis process when maintenance fails to meet standards, thus improving the reliability of operation and maintenance work.

Description

Technical Field

[0001] This invention relates to the field of power equipment fault diagnosis technology, and in particular to an integrated distribution cabinet fault diagnosis system based on edge computing. Background Technology

[0002] Integrated switchgear, as a core hub device in modern power systems, integrates multiple functional modules such as switching equipment, protection devices, monitoring instruments, and control units. It can realize comprehensive functions including power distribution, circuit protection, status monitoring, and remote control. Its operational stability directly affects the reliability and security of the power supply system. With the deepening of smart grid construction, the application scenarios of integrated switchgear are becoming increasingly widespread, with large-scale deployments in fields ranging from industrial plants and commercial buildings to data centers and rail transit. The requirements for power quality are also constantly increasing. Therefore, how to effectively ensure the long-term stable operation of integrated switchgear has become an important issue in power operation and maintenance management. To this end, power companies have strengthened their research and application of switchgear status monitoring and fault diagnosis technologies to promptly identify potential equipment problems and reduce the occurrence of power outages.

[0003] However, traditional integrated distribution cabinet fault diagnosis methods mainly rely on regular manual inspections and experience-based judgment. Regular inspections cannot achieve real-time monitoring of equipment operating status and are difficult to detect sudden faults. Often, problems are only discovered after a fault occurs, resulting in serious delays in fault handling. Secondly, manual experience-based judgment depends on the professional level and subjective judgment of maintenance personnel. When faced with complex and ever-changing fault characteristics, it is easy to make misjudgments or omissions, resulting in low diagnostic accuracy.

[0004] To address the aforementioned technical deficiencies, a solution is proposed. Summary of the Invention

[0005] The purpose of this invention is to address the problem that traditional integrated power distribution cabinet fault diagnosis methods mainly rely on periodic manual inspections and experience-based judgment. Periodic inspections cannot achieve real-time monitoring of equipment operating status, making it difficult to detect sudden faults. Often, problems are only discovered after a fault occurs, leading to a serious delay in fault handling. Secondly, manual experience-based judgment depends on the professional level and subjective judgment of maintenance personnel, which is prone to misjudgment or omission when faced with complex and ever-changing fault characteristics, resulting in low diagnostic accuracy.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: an integrated power distribution cabinet fault diagnosis system based on edge computing, comprising a data acquisition unit, a fault modeling unit, a risk assessment unit, a fault diagnosis module, and a maintenance assessment unit; The data acquisition unit is used to acquire fault data, risk data and maintenance data of the integrated power distribution cabinet through the sensor array, and send the fault data to the fault modeling unit and fault diagnosis module, the risk data to the risk assessment unit, and the maintenance data to the maintenance assessment unit. The fault modeling unit is used to receive historical fault data of the distribution cabinets that have experienced historical faults, and to build a fault identification model for the integrated distribution cabinet based on the historical fault data. The risk assessment unit is used to receive risk data from integrated distribution cabinets, perform analysis and calculation, derive the fault risk index of integrated distribution cabinets, classify distribution cabinets into high-risk distribution cabinets, general-risk distribution cabinets and low-risk distribution cabinets, and adjust the data sampling frequency of distribution cabinets according to the risk level of distribution cabinets. The fault diagnosis module is used to identify faults in high-risk distribution cabinets, determine the first fault type of the distribution cabinet, and dispatch the first maintenance personnel to carry out maintenance. The maintenance assessment unit is used to acquire maintenance data of the integrated distribution cabinet after maintenance, analyze and calculate the fault maintenance index of the distribution cabinet, and carry out maintenance and disposal based on the fault maintenance results.

[0007] Furthermore, the system also includes an anomaly alarm unit, which is used to send an anomaly alarm message to the fault diagnosis terminal when an abnormal situation occurs in the integrated power distribution cabinet.

[0008] Furthermore, the process of constructing a fault identification model for integrated power distribution cabinets is as follows: S11. Collect historical fault data of multiple distribution cabinets with different fault types in history as a dataset, and randomly divide the dataset into a training set and a test set. Label the corresponding fault type on each morphological image of the training set as a label. The fault data includes the concentration of harmful gases in the internal environment of the distribution cabinet and the temperature, current and voltage data of the electrical equipment inside the distribution cabinet. S12. Construct a fault identification model for the integrated power distribution cabinet based on a convolutional neural network. Train the fault identification model for the integrated power distribution cabinet using a training set and test the fault identification model for the integrated power distribution cabinet using a test set to obtain a qualified fault identification model for the integrated power distribution cabinet.

[0009] Furthermore, the calculation process for the fault risk index of integrated power distribution cabinets is as follows: S21. Obtain risk data of the integrated power distribution cabinet and perform analysis and calculation. The risk data includes temperature, electromagnetic intensity and noise intensity data of the internal environment of the integrated power distribution cabinet. S22. Calculate the failure risk index of the integrated distribution cabinet according to the following formula. : in, The temperature of the internal environment of the integrated power distribution cabinet. The preset standard temperature for the internal environment of the distribution cabinet. The electromagnetic intensity of the internal environment of the integrated power distribution cabinet. The standard electromagnetic intensity is set for the internal environment of the pre-defined distribution cabinet. The noise level inside the integrated power distribution cabinet. The preset standard noise level inside the distribution cabinet. The preset electromagnetic weighting coefficient, The fault risk index of the integrated power distribution cabinet is used to reflect the degree of risk of the integrated power distribution cabinet failing, with a preset noise weighting coefficient. S23. Obtain the preset lower threshold value for fault risk. and failure risk upper limit threshold Failure risk index of integrated power distribution cabinet Comparative analysis, when In such cases, the distribution cabinets are classified as low-risk distribution cabinets; S24, when In such cases, the distribution cabinet is classified as a general risk distribution cabinet; S25, when In such cases, the distribution cabinet will be classified as a high-risk distribution cabinet.

[0010] Furthermore, the process of adjusting the data sampling frequency of the distribution cabinet according to its risk level is as follows: S31. For high-risk and low-risk distribution cabinets, maintain the preset standard data sampling frequency f. For general-risk distribution cabinets, analyze and calculate based on the preset standard data sampling frequency f and the fault risk index of general-risk distribution cabinets to obtain the adjusted sampling frequency of general-risk distribution cabinets. S32. Calculate the adjusted sampling frequency of the general risk distribution cabinet according to the following formula. : in, The preset standard data sampling frequency, This represents the failure risk index for a typical high-risk power distribution cabinet. The preset lower limit threshold for fault risk. This is the preset upper limit threshold for fault risk.

[0011] Furthermore, the process of fault identification for high-risk distribution cabinets is as follows: S41. Acquire real-time fault data of high-risk distribution cabinets through sensor arrays, and input the real-time fault data into the fault identification model of the tested and qualified integrated distribution cabinet to determine the fault type of the high-risk distribution cabinet. S42. Trigger the abnormal alarm unit to send abnormal alarm information to the fault diagnosis terminal, and obtain the first fault type of the high-risk power distribution cabinet through the fault diagnosis module, and dispatch the first maintenance personnel to carry out maintenance.

[0012] Furthermore, the calculation process for the fault repair index of the distribution cabinet is as follows: S51. After maintenance, acquire and analyze the maintenance data of the integrated power distribution cabinet. The maintenance data includes the image evaluation feature value inside the power distribution cabinet, the power distribution efficiency of the power distribution cabinet, and the vibration intensity data of the power distribution cabinet. S52. Calculate the fault repair index for distribution cabinet fault repair according to the following formula. : in, Image assessment feature values ​​for the interior of high-risk distribution cabinets. To evaluate feature values ​​for a pre-defined standard image inside the distribution cabinet, To improve the power distribution efficiency of high-risk distribution cabinets. This is the preset standard power distribution efficiency of the distribution cabinet. For the vibration intensity of high-risk distribution cabinets, The preset standard vibration intensity of the distribution cabinet, These are preset image weighting coefficients. The fault repair index of the distribution cabinet is used to reflect the repair effect of the maintenance personnel on the distribution cabinet, with the preset efficiency weighting coefficient.

[0013] Furthermore, the maintenance and repair process is as follows: S61. Obtain the preset fault repair threshold. Fault repair index of power distribution cabinet fault repair Comparative analysis, when If the first inspection personnel achieve a good result in repairing the first type of fault in the power distribution cabinet, it indicates that the first inspection personnel have done a good job in repairing the first type of fault in the power distribution cabinet. S62, when If the first maintenance personnel perform poor maintenance on the first type of fault in the distribution cabinet, the distribution cabinet will still be in a faulty state after maintenance. It is necessary to re-analyze and derive the fault risk index of the distribution cabinet and classify the risks of the distribution cabinet. S63. When the power distribution cabinet under maintenance is classified as a general risk power distribution cabinet or a low risk power distribution cabinet, the first maintenance personnel shall be dispatched to re-inspect the power distribution cabinet according to the first fault type. S64. When the power distribution cabinet under maintenance is classified as a high-risk power distribution cabinet, it is necessary to re-collect the fault data of the power distribution cabinet and input it into the fault identification model for secondary fault identification to obtain the second fault type of the power distribution cabinet, and dispatch another second maintenance personnel to repair the faulty power distribution cabinet.

[0014] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are: This edge computing-based integrated power distribution cabinet fault diagnosis system uses a sensor array to collect multi-dimensional data from the power distribution cabinet in real time, enabling continuous monitoring of equipment operation status. It can promptly capture abnormal signals and sudden faults, significantly improving the timeliness of fault response and avoiding diagnostic delays caused by inspection cycles. Secondly, the system uses a convolutional neural network to build a fault recognition model, trained and tested based on historical fault data. This achieves intelligent identification and judgment of fault types, greatly reducing misjudgments or missed diagnoses caused by subjective human factors and improving the objectivity and accuracy of diagnosis. Furthermore, by introducing a fault risk index calculation and grading mechanism, the system can dynamically assess the risk level of the power distribution cabinet and adaptively adjust the data acquisition frequency according to the risk level, optimizing the allocation efficiency of edge computing resources while ensuring monitoring effectiveness. Simultaneously, the system also has maintenance assessment and closed-loop handling functions. It quantitatively evaluates maintenance effectiveness through a fault maintenance index and initiates re-inspection or secondary diagnosis processes when maintenance fails to meet standards, thereby ensuring that faults are completely eliminated and improving the quality and reliability of operation and maintenance work. Attached Figure Description

[0015] Figure 1 A schematic diagram of the system flow of the present invention is shown. Detailed Implementation

[0016] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0017] Example: like Figure 1 As shown, the edge computing-based integrated power distribution cabinet fault diagnosis system first uses a data acquisition unit to acquire fault data, risk data, and maintenance data of the integrated power distribution cabinet through a sensor array. The fault data is then sent to the fault modeling unit and the fault diagnosis module, the risk data is sent to the risk assessment unit, and the maintenance data is sent to the maintenance assessment unit.

[0018] Then, the fault modeling unit receives historical fault data of the distribution cabinets that have experienced historical faults, and constructs a fault identification model for the integrated distribution cabinet based on the historical fault data. The process of constructing a fault identification model for an integrated power distribution cabinet is as follows: S11. Collect historical fault data of multiple distribution cabinets with different fault types in history as a dataset, and randomly divide the dataset into a training set and a test set. Label the corresponding fault type on each morphological image of the training set as a label. The fault data includes the concentration of harmful gases in the internal environment of the distribution cabinet and the temperature, current and voltage data of the electrical equipment inside the distribution cabinet. S12. Construct a fault identification model for the integrated power distribution cabinet based on a convolutional neural network. Train the fault identification model for the integrated power distribution cabinet using a training set and test the fault identification model for the integrated power distribution cabinet using a test set to obtain a qualified fault identification model for the integrated power distribution cabinet.

[0019] Then, the risk data of the integrated distribution cabinet is received through the risk assessment unit, analyzed and calculated to obtain the fault risk index of the integrated distribution cabinet, and the distribution cabinet is divided into high-risk distribution cabinet, general-risk distribution cabinet and low-risk distribution cabinet. The data sampling frequency of the distribution cabinet is adjusted according to the risk level of the distribution cabinet. The calculation process for the failure risk index of integrated power distribution cabinets is as follows: S21. Obtain risk data of the integrated power distribution cabinet and perform analysis and calculation. The risk data includes temperature, electromagnetic intensity and noise intensity data of the internal environment of the integrated power distribution cabinet. S22. Calculate the failure risk index of the integrated distribution cabinet according to the following formula. : in, The temperature of the internal environment of the integrated power distribution cabinet. The preset standard temperature for the internal environment of the distribution cabinet. The electromagnetic intensity of the internal environment of the integrated power distribution cabinet. The standard electromagnetic intensity is set for the internal environment of the pre-defined distribution cabinet. The noise level inside the integrated power distribution cabinet. The preset standard noise level inside the distribution cabinet. The preset electromagnetic weighting coefficient, The fault risk index of the integrated power distribution cabinet is used to reflect the degree of risk of the integrated power distribution cabinet failing, with a preset noise weighting coefficient. The higher the value of the fault risk index, the higher the risk of the integrated power distribution cabinet failing. S23. Obtain the preset lower threshold value for fault risk. and failure risk upper limit threshold Failure risk index of integrated power distribution cabinet Comparative analysis, when If the risk is low, the distribution cabinet is classified as a low-risk distribution cabinet, indicating that the risk of the distribution cabinet malfunctioning is low, no malfunction has occurred, and no fault diagnosis is required. S24, when If the situation is as described above, the distribution cabinet will be classified as a general risk distribution cabinet, indicating that the risk of the distribution cabinet malfunctioning is generally low, no malfunction has occurred, and no fault diagnosis is required. S25, when If the distribution cabinet is classified as a high-risk distribution cabinet, it indicates that the risk of failure is high and a failure is likely to occur. Fault diagnosis is required, and the abnormal alarm unit will be triggered to provide an alarm notification.

[0020] The process of adjusting the data sampling frequency of the distribution cabinet according to its risk level is as follows: S31. For high-risk and low-risk distribution cabinets, maintain the preset standard data sampling frequency f. For general-risk distribution cabinets, analyze and calculate based on the preset standard data sampling frequency f and the fault risk index of general-risk distribution cabinets to obtain the adjusted sampling frequency of general-risk distribution cabinets. S32. Calculate the adjusted sampling frequency of the general risk distribution cabinet according to the following formula. : in, The preset standard data sampling frequency, This represents the failure risk index for a typical high-risk power distribution cabinet. The preset lower limit threshold for fault risk. This is the preset upper limit threshold for fault risk.

[0021] Then, the fault diagnosis module is used to identify the faults in the high-risk distribution cabinet, determine the first fault type of the distribution cabinet, and dispatch the first maintenance personnel to carry out maintenance. The process of fault identification for high-risk distribution cabinets is as follows: S41. Acquire real-time fault data of high-risk distribution cabinets through sensor arrays, and input the real-time fault data into the fault identification model of the tested and qualified integrated distribution cabinet to determine the fault type of the high-risk distribution cabinet. S42. Trigger the abnormal alarm unit to send abnormal alarm information (including the location and fault type of the high-risk distribution cabinet) to the fault diagnosis terminal, and obtain the first fault type of the high-risk distribution cabinet through the fault diagnosis module, and dispatch the first maintenance personnel to carry out maintenance.

[0022] Finally, the maintenance data of the integrated distribution cabinet after maintenance is obtained through the maintenance assessment unit, and the data is analyzed and calculated to obtain the fault maintenance index of the distribution cabinet. Based on the fault maintenance results, maintenance is carried out. The calculation process for the fault repair index of the power distribution cabinet is as follows: S51. After maintenance, obtain the maintenance data of the integrated power distribution cabinet and perform analysis and calculation. The maintenance data includes the image evaluation feature value inside the power distribution cabinet, the power distribution efficiency of the power distribution cabinet, and the vibration intensity data of the power distribution cabinet. It should be noted that the image evaluation feature value inside the power distribution cabinet and the power distribution efficiency of the power distribution cabinet are included. S52. Calculate the fault repair index for distribution cabinet fault repair according to the following formula. : in, Image assessment feature values ​​for the interior of high-risk distribution cabinets. To evaluate feature values ​​for a pre-defined standard image inside the distribution cabinet, To improve the power distribution efficiency of high-risk distribution cabinets. This is the preset standard power distribution efficiency of the distribution cabinet. For the vibration intensity of high-risk distribution cabinets, The preset standard vibration intensity of the distribution cabinet, These are preset image weighting coefficients. The fault repair index for distribution cabinet fault repair is a preset efficiency weighting coefficient, used to reflect the repair effect of the maintenance personnel on the distribution cabinet. The larger the value of the fault repair index, the better the repair effect of the maintenance personnel on the distribution cabinet. The smaller the value of the fault repair index, the worse the repair effect of the maintenance personnel on the distribution cabinet.

[0023] The maintenance and repair process is as follows: S61. Obtain the preset fault repair threshold. Fault repair index of power distribution cabinet fault repair Comparative analysis, when If the first maintenance personnel have done a good job in repairing the first type of fault in the power distribution cabinet, the power distribution cabinet can operate stably after the repair. S62, when If the first maintenance personnel perform poor maintenance on the first type of fault in the distribution cabinet, the distribution cabinet will still be in a faulty state after maintenance. It is necessary to re-analyze and derive the fault risk index of the distribution cabinet and classify the risks of the distribution cabinet. S63. When the power distribution cabinet under maintenance is classified as a general risk power distribution cabinet or a low risk power distribution cabinet, the first maintenance personnel shall be dispatched to re-inspect the power distribution cabinet according to the first fault type. S64. When the power distribution cabinet under maintenance is classified as a high-risk power distribution cabinet, it is necessary to re-collect the fault data of the power distribution cabinet and input it into the fault identification model for secondary fault identification to obtain the second fault type of the power distribution cabinet. At the same time, the abnormal alarm unit is triggered, and another second maintenance personnel are dispatched to repair the faulty power distribution cabinet.

[0024] This invention utilizes a sensor array to collect multi-dimensional data from the power distribution cabinet in real time, enabling continuous monitoring of equipment operation status. It can promptly capture abnormal signals and sudden faults, significantly improving the timeliness of fault response and avoiding diagnostic delays caused by inspection cycles. Secondly, the system employs a convolutional neural network to construct a fault identification model, trained and tested based on historical fault data. This achieves intelligent identification and judgment of fault types, greatly reducing misjudgments or missed diagnoses caused by subjective human factors and improving the objectivity and accuracy of diagnosis. Furthermore, by introducing a fault risk index calculation and grading mechanism, the system can dynamically assess the risk level of the power distribution cabinet and adaptively adjust the data acquisition frequency according to the risk level, optimizing the allocation efficiency of edge computing resources while ensuring monitoring effectiveness. Simultaneously, the system also features maintenance assessment and closed-loop handling functions. It quantitatively evaluates maintenance effectiveness through a fault maintenance index and initiates re-inspection or secondary diagnostic processes when maintenance fails to meet standards, ensuring that faults are completely eliminated and improving the quality and reliability of operation and maintenance work.

[0025] The size of the interval and threshold is set to facilitate comparison. The size of the threshold depends on the amount of sample data and the number of bases set by those skilled in the art for each set of sample data; as long as it does not affect the ratio between the parameter and the quantized value.

[0026] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation. The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. An integrated power distribution cabinet fault diagnosis system based on edge computing, characterized in that, It includes a data acquisition unit, a fault modeling unit, a risk assessment unit, a fault diagnosis module, and a maintenance assessment unit; The data acquisition unit is used to acquire fault data, risk data and maintenance data of the integrated power distribution cabinet through the sensor array, and send the fault data to the fault modeling unit and fault diagnosis module, the risk data to the risk assessment unit, and the maintenance data to the maintenance assessment unit. The fault modeling unit is used to receive historical fault data of the distribution cabinets that have experienced historical faults, and to build a fault identification model for the integrated distribution cabinet based on the historical fault data. The risk assessment unit is used to receive risk data from integrated distribution cabinets, perform analysis and calculation, derive the fault risk index of integrated distribution cabinets, classify distribution cabinets into high-risk distribution cabinets, general-risk distribution cabinets and low-risk distribution cabinets, and adjust the data sampling frequency of distribution cabinets according to the risk level of distribution cabinets. The fault diagnosis module is used to identify faults in high-risk distribution cabinets, determine the first fault type of the distribution cabinet, and dispatch the first maintenance personnel to carry out maintenance. The maintenance assessment unit is used to acquire maintenance data of the integrated distribution cabinet after maintenance, analyze and calculate the fault maintenance index of the distribution cabinet, and carry out maintenance and disposal based on the fault maintenance results.

2. The integrated power distribution cabinet fault diagnosis system based on edge computing according to claim 1, characterized in that, The system also includes an abnormal alarm unit, which is used to send abnormal alarm information to the fault diagnosis terminal when an abnormal situation occurs in the integrated power distribution cabinet.

3. The integrated power distribution cabinet fault diagnosis system based on edge computing according to claim 1, characterized in that, The process of constructing a fault identification model for an integrated power distribution cabinet is as follows: S11. Collect historical fault data of multiple distribution cabinets with different fault types in history as a dataset, and randomly divide the dataset into a training set and a test set. Label the corresponding fault type on each morphological image of the training set as a label. The fault data includes the concentration of harmful gases in the internal environment of the distribution cabinet and the temperature, current and voltage data of the electrical equipment inside the distribution cabinet. S12. Construct a fault identification model for the integrated power distribution cabinet based on a convolutional neural network. Train the fault identification model for the integrated power distribution cabinet using a training set and test the fault identification model for the integrated power distribution cabinet using a test set to obtain a qualified fault identification model for the integrated power distribution cabinet.

4. The integrated power distribution cabinet fault diagnosis system based on edge computing according to claim 1, characterized in that, The calculation process for the failure risk index of integrated power distribution cabinets is as follows: S21. Obtain risk data of the integrated power distribution cabinet and perform analysis and calculation. The risk data includes temperature, electromagnetic intensity and noise intensity data of the internal environment of the integrated power distribution cabinet. S22. Calculate the failure risk index of the integrated distribution cabinet according to the following formula. : in, The temperature of the internal environment of the integrated power distribution cabinet. The preset standard temperature for the internal environment of the distribution cabinet. The electromagnetic intensity of the internal environment of the integrated power distribution cabinet. The standard electromagnetic intensity is set for the internal environment of the pre-defined distribution cabinet. The noise level inside the integrated power distribution cabinet. The preset standard noise level inside the distribution cabinet. The preset electromagnetic weighting coefficient, The fault risk index of the integrated power distribution cabinet is used to reflect the degree of risk of the integrated power distribution cabinet failing, with a preset noise weighting coefficient. S23. Obtain the preset lower threshold value for fault risk. and failure risk upper limit threshold Failure risk index of integrated power distribution cabinet Comparative analysis, when In such cases, the distribution cabinets are classified as low-risk distribution cabinets; S24, when In such cases, the distribution cabinet is classified as a general risk distribution cabinet; S25, when In such cases, the distribution cabinet will be classified as a high-risk distribution cabinet.

5. The integrated power distribution cabinet fault diagnosis system based on edge computing according to claim 1, characterized in that, The process of adjusting the data sampling frequency of the distribution cabinet according to its risk level is as follows: S31. For high-risk and low-risk distribution cabinets, maintain the preset standard data sampling frequency f. For general-risk distribution cabinets, analyze and calculate based on the preset standard data sampling frequency f and the fault risk index of general-risk distribution cabinets to obtain the adjusted sampling frequency of general-risk distribution cabinets. S32. Calculate the adjusted sampling frequency of the general risk distribution cabinet according to the following formula. : in, The preset standard data sampling frequency, This represents the failure risk index for a typical high-risk power distribution cabinet. The preset lower limit threshold for fault risk. This is the preset upper limit threshold for fault risk.

6. The integrated power distribution cabinet fault diagnosis system based on edge computing according to claim 1, characterized in that, The process of fault identification for high-risk distribution cabinets is as follows: S41. Acquire real-time fault data of high-risk distribution cabinets through sensor arrays, and input the real-time fault data into the fault identification model of the tested and qualified integrated distribution cabinet to determine the fault type of the high-risk distribution cabinet. S42. Trigger the abnormal alarm unit to send abnormal alarm information to the fault diagnosis terminal, and obtain the first fault type of the high-risk power distribution cabinet through the fault diagnosis module, and dispatch the first maintenance personnel to carry out maintenance.

7. The integrated power distribution cabinet fault diagnosis system based on edge computing according to claim 1, characterized in that, The calculation process for the fault repair index of the power distribution cabinet is as follows: S51. After maintenance, acquire and analyze the maintenance data of the integrated power distribution cabinet. The maintenance data includes the image evaluation feature value inside the power distribution cabinet, the power distribution efficiency of the power distribution cabinet, and the vibration intensity data of the power distribution cabinet. S52. Calculate the fault repair index for distribution cabinet fault repair according to the following formula. : in, Image assessment feature values ​​for the interior of high-risk distribution cabinets. To evaluate feature values ​​for a pre-defined standard image inside the distribution cabinet, To improve the power distribution efficiency of high-risk distribution cabinets. This is the preset standard power distribution efficiency of the distribution cabinet. For the vibration intensity of high-risk distribution cabinets, The preset standard vibration intensity of the distribution cabinet, These are preset image weighting coefficients. The fault repair index of the distribution cabinet is used to reflect the repair effect of the maintenance personnel on the distribution cabinet, with the preset efficiency weighting coefficient.

8. The integrated power distribution cabinet fault diagnosis system based on edge computing according to claim 1, characterized in that, The maintenance and repair process is as follows: S61. Obtain the preset fault repair threshold. Fault repair index of power distribution cabinet fault repair Comparative analysis, when If the first inspection personnel achieve a good result in repairing the first type of fault in the power distribution cabinet, it indicates that the first inspection personnel have done a good job in repairing the first type of fault in the power distribution cabinet. S62, when If the first maintenance personnel perform poor maintenance on the first type of fault in the distribution cabinet, the distribution cabinet will still be in a faulty state after maintenance. It is necessary to re-analyze and derive the fault risk index of the distribution cabinet and classify the risks of the distribution cabinet. S63. When the power distribution cabinet under maintenance is classified as a general risk power distribution cabinet or a low risk power distribution cabinet, the first maintenance personnel shall be dispatched to re-inspect the power distribution cabinet according to the first fault type. S64. When the power distribution cabinet under maintenance is classified as a high-risk power distribution cabinet, it is necessary to re-collect the fault data of the power distribution cabinet and input it into the fault identification model for secondary fault identification to obtain the second fault type of the power distribution cabinet, and dispatch another second maintenance personnel to repair the faulty power distribution cabinet.

Images