CN118278916A

CN118278916A - Fault processing method and device for power distribution equipment, electronic equipment and storage medium

Info

Publication number: CN118278916A
Application number: CN202410462457.8A
Authority: CN
Inventors: 孙友浩; 黄富; 王一风; 吴旦; 田政鳞; 林俊宏
Original assignee: China Southern Power Grid Digital Grid Technology Guangdong Co ltd
Current assignee: China Southern Power Grid Digital Grid Technology Guangdong Co ltd
Priority date: 2024-04-17
Filing date: 2024-04-17
Publication date: 2024-07-02

Abstract

The invention discloses a power distribution equipment fault processing method, a device, electronic equipment and a storage medium. Wherein the method comprises the following steps: under the condition that at least one device to be detected in the power distribution room meets the preset fault processing condition, processing the equipment operation data, the equipment maintenance log and the environment detection data corresponding to the pre-acquired device to be detected according to the pre-trained fault trend prediction model to obtain the equipment prediction health state corresponding to the device to be detected; and determining an equipment maintenance task list corresponding to the power distribution room according to the equipment prediction health state, the equipment maintenance log and the pre-acquired maintenance resource information corresponding to the at least one equipment to be detected, so as to carry out equipment maintenance on the corresponding equipment to be detected based on the equipment maintenance task list. According to the technical scheme, the effect of predicting the health state of the equipment based on the multidimensional data corresponding to the power distribution equipment is achieved under the condition that the defect of the power distribution equipment is determined, and the prediction accuracy is improved.

Description

Fault processing method and device for power distribution equipment, electronic equipment and storage medium

Technical Field

The present invention relates to the field of fault detection technologies, and in particular, to a method and an apparatus for processing a fault of a power distribution device, an electronic device, and a storage medium.

Background

The distribution room is used as a key link of a power system and bears important responsibilities of electric energy distribution and regulation. However, current techniques and methods present significant shortcomings and challenges in fault detection and maintenance of equipment status.

In the related art, fault detection of power distribution room equipment mainly depends on periodic manual inspection.

However, this method is not only inefficient, but is also susceptible to subjective judgment and skill in operation. Manual inspection often makes it difficult to find minor equipment damage or early failure in time, which may lead to the evolution of minor damage into severe failure.

Disclosure of Invention

The invention provides a power distribution equipment fault processing method, a device, electronic equipment and a storage medium, which are used for realizing the effect of predicting the health state of equipment based on multidimensional data corresponding to the power distribution equipment under the condition that the defect of the power distribution equipment is determined, improving the prediction accuracy, providing scientific basis for maintenance and replacement of the equipment, prolonging the service life of the equipment and reducing the maintenance cost.

According to an aspect of the present invention, there is provided a fault handling method for a power distribution apparatus, the method including:

Under the condition that at least one device to be detected in a power distribution room meets preset fault processing conditions, processing equipment operation data, equipment maintenance logs and environment detection data corresponding to the device to be detected, which are obtained in advance, according to a pre-trained fault trend prediction model to obtain equipment prediction health states corresponding to the device to be detected; the equipment prediction health state is used for indicating the health state change trend of the equipment to be detected within a preset time after the current moment;

Determining an equipment maintenance task list corresponding to the power distribution room according to the equipment prediction health state, the equipment maintenance log and the pre-acquired maintenance resource information corresponding to at least one piece of equipment to be detected, so as to perform equipment maintenance on the corresponding equipment to be detected based on the equipment maintenance task list; the maintenance resource information is used for indicating resources required for maintaining the equipment to be detected; the equipment maintenance task list comprises at least one equipment maintenance task arranged according to a preset task execution sequence.

According to another aspect of the present invention, there is provided a fault handling apparatus for a power distribution device, the apparatus comprising:

The data processing module is used for processing the equipment operation data, the equipment maintenance log and the environment detection data corresponding to the equipment to be detected, which are obtained in advance, according to the pre-trained fault trend prediction model under the condition that at least one piece of equipment to be detected in the power distribution room meets the preset fault processing condition, so as to obtain the equipment prediction health state corresponding to the equipment to be detected; the equipment prediction health state is used for indicating the health state change trend of the equipment to be detected within a preset time after the current moment;

The task list determining module is used for determining an equipment maintenance task list corresponding to the power distribution room according to the equipment prediction health state, the equipment maintenance log and the pre-acquired maintenance resource information corresponding to at least one piece of equipment to be detected, so that equipment maintenance is carried out on the corresponding equipment to be detected based on the equipment maintenance task list; the maintenance resource information is used for indicating resources required for maintaining the equipment to be detected; the equipment maintenance task list comprises at least one equipment maintenance task arranged according to a preset task execution sequence.

According to another aspect of the present invention, there is provided an electronic apparatus including:

At least one processor; and

A memory communicatively coupled to the at least one processor; wherein,

The memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the power distribution apparatus fault handling method of any of the embodiments of the present invention.

According to another aspect of the present invention, there is provided a computer readable storage medium storing computer instructions for causing a processor to execute the method for fault handling of power distribution equipment according to any of the embodiments of the present invention.

According to the technical scheme, under the condition that at least one device to be detected in the power distribution room meets the preset fault processing condition, the device operation data, the device maintenance logs and the environment detection data corresponding to the device to be detected, which are obtained in advance, are processed according to the pre-trained fault trend prediction model to obtain the device prediction health state corresponding to the device to be detected, and further, according to the device prediction health state, the device maintenance logs and the pre-obtained maintenance resource information corresponding to the device to be detected, the device maintenance task list corresponding to the power distribution room is determined, so that the device maintenance is carried out on the corresponding device to be detected based on the device maintenance task list, the problems that the efficiency is low, the influence of subjective judgment and operation skills is easy, and the damage of the small device cannot be found in time are solved, the effect of predicting the device health state based on the multidimensional data corresponding to the power distribution device is achieved under the condition that the defect exists is determined, the prediction accuracy is improved, and scientific basis is provided for the maintenance and replacement of the device, and the service life of the device is prolonged, and the maintenance cost is lowered.

It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

Fig. 1 is a flowchart of a fault handling method for a power distribution device according to a first embodiment of the present invention;

Fig. 2 is a flowchart of a fault handling method for a power distribution device according to a second embodiment of the present invention;

Fig. 3 is a schematic structural diagram of a fault handling device for power distribution equipment according to a third embodiment of the present invention;

Fig. 4 is a schematic structural diagram of an electronic device implementing a fault handling method of a power distribution device according to an embodiment of the present invention.

Detailed Description

In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.

It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

Example 1

Fig. 1 is a flowchart of a fault handling method for a power distribution device according to a first embodiment of the present invention, where the present embodiment is applicable to fault detection of the power distribution device and prediction of a device health status of the power distribution device when it is determined that the power distribution device meets a preset fault handling condition, the method may be performed by a fault handling device for the power distribution device, where the fault handling device for the power distribution device may be implemented in a form of hardware and/or software, and the fault handling device for the power distribution device may be configured in a terminal and/or a server. As shown in fig. 1, the method includes:

And S110, under the condition that at least one device to be detected in the power distribution room meets the preset fault processing condition, processing the equipment operation data, the equipment maintenance log and the environment detection data corresponding to the pre-acquired device to be detected according to the pre-trained fault trend prediction model to obtain the equipment prediction health state corresponding to the device to be detected.

Among them, a power distribution room, also called a power distribution substation, is an important component in an electric power system, and is mainly used for receiving, converting, distributing and transmitting electric energy. The device to be detected may be a power distribution device provided in a power distribution room. By way of example, the equipment to be tested may include high and low voltage distribution equipment, transformers, control equipment, protection devices, and the like. The method comprises the steps that a preset fault processing condition comprises the condition that abnormal vibration exists in equipment to be detected and risks exist in an area where the equipment to be detected is located; abnormal vibration can be understood as an abnormal vibration frequency of the device when it is in operation. The area where the device to be detected is located may be understood as the surrounding environment where the device to be detected is located, i.e. the environment around the device to be detected. The risk of the area is understood as that the environment detection data of the area where the device is located exceeds a preset environment risk threshold, i.e. the area where the device is located is not secure. The device vibration data is used for indicating whether the device to be detected has abnormal vibration. The environment detection data are used for determining whether the area where the equipment to be detected is located is at risk. The environmental detection data may be used to indicate environmental conditions of the area in which the device is located. The environmental detection data may be used to indicate whether there is a risk in the area where the device to be detected is located. Alternatively, the environmental detection data may include at least smoke concentration, carbon monoxide concentration, and the like. The failure trend prediction model may be used to predict the health of the device in the event of a failure of the device. The failure trend prediction model may be understood as a neural network model that takes device operation data, device maintenance logs, and environment detection data as input objects to predict a device health state of a device to be detected. The failure trend prediction model may be a neural network model of any structure. Alternatively, the failure trend prediction model may include, but is not limited to, convolutional neural networks (Convolutional Neural Network, CNN) and Long-term memory networks (Long Short-Term Memory network, LSTM). Device operational data may be understood as data characterizing the operation of the device. Alternatively, the device operation data may include at least device vibration data, electrical status data, and the like. The device vibration data may be understood as data characterizing the vibration state of the device when it is in operation. The device vibration data may be used to indicate whether an abnormality exists in the device to be detected. The electrical status data may include data of current, voltage, power factor, and load, among others. The device maintenance log may be understood as a log recording the historical maintenance of the device. The device maintenance log may include a device history maintenance record. The equipment history maintenance records may include maintenance times, maintenance types, replacement part records, and the like. The device predicted health state can be understood as a device health index change trend of the device to be detected within a period of time after the current moment, which is obtained based on model prediction. The predicted health state of the device can be used for indicating the change trend of the health state of the device to be detected within a preset time period after the current moment. The preset duration may be any duration, and may alternatively be 30 minutes, 1 hour, 2 hours, or the like. The device predicted health state may be represented by an index value variation trend of at least one device performance index within a preset time period. Alternatively, the device performance indicators may include insulation resistance, ground resistance, protection response time, and harmonic distortion conditions, among others.

In this embodiment, for a plurality of devices to be detected in the power distribution room, fault detection may be performed on each device to be detected periodically or continuously, so as to determine the device health status of each device to be detected. In order to perform comprehensive equipment state evaluation on equipment to be detected, equipment operation data and environment detection data of the equipment to be detected can be obtained when the equipment to be detected performs fault detection. Furthermore, the vibration state of the equipment to be detected during operation can be detected based on the equipment operation data, and the environment safety state of the area where the equipment to be detected is located can be detected based on the environment detection data. Further, in the case that it is determined that abnormal vibration exists in the to-be-detected device and the risk exists in the area where the to-be-detected device is located, it may be indicated that the to-be-detected device currently has a defect, and further fault detection is required. In order to determine the change trend of the health state of the equipment to be detected within the preset time after the current moment, aiming at least one equipment to be detected, which has abnormal vibration in the power distribution room and risk in the area, equipment operation data, environment detection data and equipment maintenance logs which are obtained in advance and correspond to the equipment to be detected, can be input into a pre-trained fault trend prediction model. Furthermore, the equipment operation data, the environment detection data and the equipment maintenance log can be processed based on the fault trend prediction model, so that the equipment prediction health state corresponding to the equipment to be detected is obtained. Therefore, the performance degradation condition of the equipment to be detected can be analyzed according to the equipment prediction health state, and the equipment maintenance strategy corresponding to the equipment to be detected can be determined according to the analysis result.

It should be noted that, before the failure trend prediction model provided in this embodiment is applied, the failure trend prediction model needs to be trained first. Before training the model, a plurality of training samples may be constructed to train the model based on the training samples. In order to improve the accuracy of the fault trend prediction model, training samples can be constructed as much and as abundant as possible.

Alternatively, the training process of the failure trend prediction model may be: acquiring a plurality of training samples, wherein the training samples can comprise equipment operation data, equipment maintenance logs, environment detection data and actual equipment health states corresponding to sample equipment at a prediction moment, wherein the equipment operation data, the equipment maintenance logs and the environment detection data correspond to the sample equipment at a historical moment; for each training sample, inputting the equipment operation data, the equipment maintenance log and the environment detection data in the training sample into a fault trend prediction model to be trained to obtain a predicted health state; determining a loss value based on the predicted health state and the actual device health state in the training sample; and correcting model parameters in the fault trend prediction model to be trained based on the loss values, and converging a loss function in the fault trend prediction model to be used as a training target to obtain the fault trend prediction model.

It should be noted that, the prediction of the device predicted health state corresponding to the device to be detected based on the device operation data, the environment detection data and the device maintenance log has the advantages that the multidimensional data corresponding to the device to be detected can be synthesized under the condition that the defect exists in the device to be detected, the prediction capability of the device health state is enhanced, and the prediction accuracy is improved. Furthermore, the safety and reliability of the power system are remarkably improved.

It should be noted that, the device operation data, the environment detection data, and the device maintenance log are data with different dimensions, so, in order to unify dimensions, before the data are input into the fault trend prediction model, data normalization processing may be performed on the device operation data, the environment detection data, and the device maintenance log, and then the processed device operation data, the environment detection data, and the device maintenance log may be input into the fault trend prediction model.

S120, determining an equipment maintenance task list corresponding to the power distribution room according to the equipment prediction health state, the equipment maintenance log and the pre-acquired maintenance resource information corresponding to at least one piece of equipment to be detected, so as to perform equipment maintenance on the corresponding equipment to be detected based on the equipment maintenance task list.

Wherein the maintenance resource information may be used to indicate resources required for maintaining the device to be detected. Maintaining resource information may be understood as maintaining resources needed for the device to be detected. Optionally, the maintenance resource information may include maintenance personnel, maintenance tools, maintenance duration, maintenance budget, and the like. The equipment maintenance task list comprises at least one equipment maintenance task arranged according to a preset task execution sequence. The preset task execution sequence may be an execution sequence according to which the equipment maintenance tasks are executed, that is, the equipment maintenance tasks arranged in the front of the equipment maintenance task list are executed first, and the equipment maintenance tasks arranged in the rear of the equipment maintenance task list are executed later. The preset task execution order may be determined according to a task priority score corresponding to the equipment maintenance task. The equipment maintenance tasks may be used to maintain equipment that is defective or faulty. The equipment maintenance tasks can be generated through equipment operation data, environment detection data, equipment maintenance logs and equipment prediction health state analysis corresponding to equipment to be detected.

In this embodiment, for at least one device to be detected in the power distribution room that satisfies a preset fault processing condition, after obtaining a device predicted health state corresponding to the device to be detected, device operation data, a device maintenance log, and environment detection data of the device to be detected may be analyzed according to the device predicted health state. Further, an equipment maintenance task may be generated from the analysis result. Further, task scores corresponding to at least one equipment maintenance task can be determined, and then the equipment maintenance tasks can be arranged according to a preset task execution sequence according to the task scores, so that an equipment maintenance task list is obtained.

Optionally, determining the equipment maintenance task list corresponding to the power distribution room according to the equipment prediction health state and the equipment maintenance log corresponding to the at least one to-be-detected equipment and the pre-acquired maintenance resource information includes: generating equipment maintenance tasks according to equipment operation data, environment detection data, equipment maintenance logs and equipment prediction health states corresponding to at least one piece of equipment to be detected; acquiring a device weight value corresponding to a device to be detected; processing the equipment prediction health state, the equipment maintenance log and the equipment weight value corresponding to the equipment to be detected according to the pre-trained risk assessment model to obtain a risk score corresponding to the equipment to be detected; processing risk scores and maintenance resource information corresponding to all equipment to be detected according to optimization functions corresponding to a plurality of preset optimization targets to obtain task scores corresponding to maintenance tasks of each equipment; and arranging at least one equipment maintenance task according to the order of the task scores from high to low so as to obtain an equipment maintenance task list.

The device weight value is understood as a parameter value that characterizes the importance of the device. The device weight value may be a predetermined device parameter value. The higher the equipment weight value is, the higher the importance degree of the equipment to be detected in the power distribution room can be shown; the lower the device weight value, the lower the importance of the device to be detected in the power distribution room. By way of example, if the motor is responsible for a critical production line, it may be given a high equipment weight value, such as 8/10, while less critical equipment weight values may be below 5.

The risk assessment model may be used to assess the risk of failure of the device to be detected. The risk assessment model may be a neural network model of any structure. Alternatively, the risk assessment model may be a decision tree model or a random forest model. The risk score may be understood as a parameter value that characterizes the severity of the risk of failure of the device to be detected. The higher the risk score, the higher the degree of risk of failure of the device to be detected may be indicated. The lower the risk score, the lower the degree of risk of failure of the device to be detected may be indicated. The preset optimization objective may be an optimization objective according to which all equipment maintenance tasks are ordered. Alternatively, the preset optimization objectives may include maintaining minimum resources and highest risk scores, etc. Accordingly, the optimization function may be understood as an objective function corresponding to a preset optimization objective. The task score may be a parameter value that characterizes the priority of device maintenance task execution. The higher the task score, the more preferentially the equipment maintenance task is executed; the lower the task score, the more late the device maintenance task is performed.

In this embodiment, for at least one device to be detected, device operation data, device maintenance logs, and environment detection data may be analyzed according to a device predicted health state corresponding to the device to be detected, and a device maintenance task corresponding to the device to be detected may be generated according to an analysis result. And then, acquiring a device weight value corresponding to the device to be detected. Further, the device weight value, the device predicted health state and the device maintenance log may be input to a pre-trained risk assessment model, so as to perform risk assessment on the device to be detected according to the device weight value, the device predicted health state and the device maintenance log based on the risk assessment model, and obtain a risk score corresponding to the device to be detected. Furthermore, the risk scores and the maintenance resource information corresponding to all the devices to be detected can be input into the optimization functions corresponding to the preset optimization targets, so that the equipment maintenance tasks corresponding to all the devices to be detected are scored on the basis of meeting the preset optimization targets, and the task scores corresponding to each equipment maintenance task are obtained. Further, at least one equipment maintenance task can be arranged according to the order of the task scores from high to low, and an equipment maintenance task list is constructed according to the arranged at least one equipment maintenance task.

Further, after the equipment maintenance task list is obtained, the corresponding equipment to be detected can be maintained according to the equipment maintenance tasks included in the equipment maintenance task list.

Example two

Fig. 2 is a flowchart of a fault handling method for a power distribution device according to a second embodiment of the present invention, where, based on the foregoing embodiment, before determining that a device to be detected meets a preset fault handling condition, for a plurality of devices to be detected in a power distribution room, an image to be processed corresponding to the device to be detected is obtained, and in case that it is determined that a surface defect exists in the device to be detected included in the image to be processed, an electrical performance influence parameter corresponding to the surface defect of the device to be detected is determined according to the image to be processed; under the condition that the electrical performance influence parameter exceeds a preset influence threshold, acquiring equipment vibration data of equipment to be detected, and carrying out frequency domain analysis on the equipment vibration data according to a fast Fourier transform algorithm to obtain vibration frequency characteristics; under the condition that abnormal vibration exists in the equipment to be detected based on the vibration frequency characteristics, environment detection data of an area where the equipment to be detected is located are obtained; and under the condition that the risk exists in the area where the equipment to be detected is located based on the environment detection data, determining that the equipment to be detected meets the preset fault processing condition. The specific implementation manner can be seen in the technical scheme of the embodiment. Wherein, the technical terms identical or similar to those of the above embodiments are not repeated herein.

As shown in fig. 2, the method includes:

S210, aiming at a plurality of to-be-detected devices in the power distribution room, acquiring to-be-processed images corresponding to the to-be-detected devices, and determining electrical performance influence parameters corresponding to the surface defects of the to-be-detected devices according to the to-be-processed images under the condition that the surface defects of the to-be-detected devices included in the to-be-processed images are determined.

The image to be processed can be an image obtained after the equipment to be detected is photographed. The image to be processed may represent image data of the surface of the device to be inspected. In this embodiment, a photographing device may be set in advance around each device to be detected, and the corresponding device to be detected may be periodically photographed by the photographing device, so as to obtain a to-be-processed image corresponding to the device to be detected. Surface defects can be understood as the presence of localized non-uniformities in the surface of the device to be inspected. Alternatively, the surface defects may include crack defects, dent defects, oxidation defects, paint-fall off defects, or the like. The electrical performance influence parameter is used for indicating the influence degree of the surface defect of the equipment to be detected on the electrical performance of the equipment to be detected.

In this embodiment, for a plurality of devices to be detected in a power distribution room, images to be processed corresponding to the devices to be detected may be acquired. The image to be processed may then be analyzed to determine whether the device to be inspected included in the image to be processed has a surface defect.

Optionally, after obtaining the image to be processed corresponding to the device to be detected, the method further includes: preprocessing an image to be processed according to a preset image preprocessing mode to obtain an image to be detected corresponding to the image to be processed; processing the image to be detected according to an edge detection algorithm to obtain an equipment edge image corresponding to equipment to be detected; and determining the curvature of the edge of the equipment according to the image of the edge of the equipment, and determining whether the surface defect exists in the equipment to be detected according to the curvature of the edge of the equipment.

The preset image preprocessing method comprises graying and/or Gaussian blur. The image to be detected is the image obtained after the image to be processed is preprocessed. The edge detection algorithm may be a Canny edge detection algorithm. The device edge image may be an image obtained by extracting edge pixels of an image to be detected. The curvature of the edge of the device may be a parameter of the degree of curvature of the edge of the surface device. The device edge curvature may be determined from coordinate information of the device edge pixels.

In this embodiment, the image to be processed may be preprocessed according to a preset image preprocessing manner, so as to obtain an image to be detected corresponding to the image to be processed. And then, extracting edge pixels of the image to be detected according to an edge detection algorithm to obtain an equipment edge image. Then, the curvature of the equipment edge can be determined according to the pixel points of the equipment edge in the equipment edge image, and the determined curvature of the equipment edge is compared with a preset curvature threshold value. Further, under the condition that the curvature of the edge of the equipment is larger than a preset curvature threshold value, the existence of surface defects of the equipment to be detected is determined, and the surface defect areas are marked in the image to be processed. For example, assuming that the preset curvature threshold is 8, the determined curvature of the edge of the device is 10, and the curvature of the edge of the device is greater than the preset curvature threshold, it may be indicated that the surface defect exists in the device to be detected.

It should be noted that, the advantage of identifying the surface defects based on the above manner is that the micro defects on the surface of the device are effectively identified, so that not only the accuracy and efficiency of defect detection are improved, but also the subjective errors and operation risks of manual inspection are reduced.

Optionally, determining, according to the image to be processed, an electrical performance influence parameter corresponding to the surface defect of the device to be detected, including: extracting features of a surface defect area in the image to be processed to obtain features of the surface defect area; processing the surface defect area characteristics according to a pre-trained decision tree model to obtain surface defect associated information corresponding to equipment to be detected; and acquiring electrical state data corresponding to the equipment to be detected, and determining electrical performance influence parameters corresponding to the surface defects of the equipment to be detected according to the electrical state data and the surface defect association information.

The surface defect area features are understood to be, among other things, information characterizing the image features of the surface defect area of the device. Alternatively, the surface defect area features may include texture density, color, area, and the like. Decision tree models can be understood as neural network models that perform defect type classification based on surface defect region features. The decision tree model can be trained based on the surface defect region characteristics corresponding to the sample device and corresponding real defect association information. The surface defect-related information includes at least surface defect type and defect severity information. Alternatively, the surface defect type may include a crack defect, a dent defect, an oxidation defect, or a paint peeling defect, etc. The defect severity information may be information characterizing the severity of the defect determined by means of quantitative scoring. Illustratively, the defect severity information may include: the mild degree is 1 minute, the moderate degree is 2 minutes, and the severe degree is 3 minutes.

In this embodiment, after the surface defect area is marked in the image to be processed, in order to perform type classification and severity judgment on the existing surface defect to determine a maintenance policy corresponding to the device to be detected based on the classification result, feature extraction may be performed on the surface defect area in the image to be processed according to a preset feature extraction algorithm, and the extracted feature may be used as a surface defect area feature. The surface defect region features may then be input into a pre-trained decision tree model to determine surface defect type and severity information from the surface defect region features based on the decision tree model. Further, surface defect related information corresponding to the device to be detected can be obtained. Further, electrical state data corresponding to the equipment to be detected can be obtained, and electrical performance influence parameters corresponding to the surface defects of the equipment to be detected can be determined according to the electrical state data and the surface defect association information.

It should be noted that, through the fusion analysis with the electrical state data of the equipment, the influence of the defects on the performance of the equipment can be accurately estimated, and finer equipment detection and fault early warning are realized.

Optionally, determining, according to the electrical state data and the surface defect related information, an electrical performance influence parameter corresponding to the surface defect of the device to be detected, including: respectively preprocessing the surface defect associated information and the electrical state data according to a preset data preprocessing mode to obtain the associated information to be processed and the state data to be processed; and processing the associated information to be processed and the state data to be processed according to the pre-trained logistic regression model to obtain the electrical performance influence parameters corresponding to the surface defects of the equipment to be detected.

The preset data preprocessing mode comprises data cleaning and/or data format conversion. A logistic regression model may be understood as a neural network model that determines the extent of impact of surface defects on electrical performance based on surface defect correlation information and electrical state data. The logistic regression model may be trained based on the defect-related sample information, the electrical state sample data, and the actual electrical performance impact parameters.

In this embodiment, data cleaning and/or data format conversion processing may be performed on the electrical status data and the surface defect related information, and the processed electrical status data is used as the status data to be processed, and the processed surface defect related information is used as the related information to be processed. Furthermore, the state data to be processed and the associated information to be processed can be integrated to obtain a data set, the data set is input into a pre-trained logistic regression model, the state data to be processed and the associated information to be processed are processed based on the logistic regression model, and the electrical performance influence parameters corresponding to the surface defects of the equipment to be detected are obtained.

S220, under the condition that the electrical performance influence parameter exceeds a preset influence threshold, equipment vibration data of equipment to be detected are obtained, and frequency domain analysis is conducted on the equipment vibration data according to a fast Fourier transform algorithm so as to obtain vibration frequency characteristics.

The preset influence threshold may be a predetermined parameter value for evaluating whether further fault detection of the device is required in case of a surface defect of the device. It should be understood by those skilled in the art that the fast fourier transform (Fast Fourier Transform, FFT) is a fast algorithm of the discrete fourier transform, and is obtained by modifying the algorithm of the discrete fourier transform according to the characteristics of the discrete fourier transform, such as odd, even, imaginary, real, etc. The vibration frequency characteristic may be a characteristic that characterizes the vibration frequency of the device in the device vibration data. By way of example, assuming the device vibration data is [1,2,3,4,5], the vibration frequency characteristics may be [10 hertz, 20 hertz, 30 hertz, 40 hertz, 50 hertz ].

In this embodiment, the device vibration data may be acquired based on a vibration sensor preset on the device to be detected.

In this embodiment, after the electrical performance influence parameter is obtained, the electrical performance influence parameter may be compared with a preset influence threshold. Furthermore, under the condition that the electrical performance influence parameter exceeds a preset influence threshold value, equipment vibration data corresponding to equipment to be detected can be obtained. Further, a fast fourier transform algorithm may be used to perform frequency domain analysis on the device vibration data to obtain a frequency characteristic of the device vibration, and the obtained frequency characteristic is used as a vibration frequency characteristic.

S230, acquiring environment detection data of an area where the equipment to be detected is located under the condition that abnormal vibration exists in the equipment to be detected based on the vibration frequency characteristics.

Among them, abnormal vibration can be understood as abnormal vibration frequency of the apparatus at the time of operation. The environmental detection data may be acquired based on smoke detectors and/or gas detectors pre-arranged in the vicinity of the device to be detected.

Optionally, determining that the device to be detected has abnormal vibration based on the vibration frequency characteristic includes: and matching the vibration frequency characteristic with a preset normal frequency characteristic, and determining that abnormal vibration exists in the equipment to be detected under the condition that the vibration frequency characteristic is not matched with the preset normal frequency characteristic.

In this embodiment, the preset normal frequency characteristic may be a vibration frequency characteristic determined in the case of normal vibration of the apparatus.

As an alternative implementation manner in this embodiment, after the vibration frequency characteristic is obtained, the vibration frequency characteristic may be matched with a preset normal frequency characteristic. Further, in the case where it is determined that the vibration frequency characteristic and the preset normal frequency characteristic do not match, it may be determined that there is abnormal vibration of the device to be detected. Further, in the case where it is determined that the device to be detected has abnormal vibration, environmental detection data of an area where the device to be detected is located may be obtained. Furthermore, the environmental condition of the area where the device to be detected is located can be detected based on the environmental detection data.

And S240, under the condition that the risk exists in the area where the equipment to be detected is located based on the environment detection data, determining that the equipment to be detected meets the preset fault processing condition.

In this embodiment, determining, based on the environmental detection data, that there is a risk in an area where the device to be detected is located includes: comparing the environment detection data with a preset environment risk threshold value, and determining that the area where the equipment to be detected is located has risk under the condition that the environment detection data exceeds the preset environment risk threshold value.

The preset environmental risk threshold may include a smoke risk threshold and/or a gas risk threshold.

As an alternative implementation of this embodiment, after obtaining the environmental detection data, the environmental detection data may be compared with a preset environmental risk threshold. And further, under the condition that the environment detection data exceeds the preset risk threshold, the risk of the environment where the equipment to be detected is located can be determined. Further, it can be determined that the device to be detected satisfies the preset fault handling condition.

It should be noted that, in the case that the environmental detection data includes the smoke concentration and the carbon monoxide concentration, the risk of the area where the device to be detected is located can be determined under the condition that any one of the data exceeds the corresponding preset environmental risk threshold. That is, in the case where the smoke concentration exceeds the smoke risk threshold, or in the case where the carbon monoxide concentration exceeds the gas risk threshold, it is possible to determine that there is a risk in the area where the device to be detected is located. And under the condition that the smoke concentration exceeds the smoke risk threshold value and under the condition that the carbon monoxide concentration exceeds the gas risk threshold value, determining that the area where the equipment to be detected is located is at risk.

Exemplary, the smoke risk threshold of the preset environmental risk thresholds is 60 parts per million (ppm); the gas risk threshold is 30 parts per million (ppm). The smoke concentration in the environmental test data was assumed to be 75ppm and the carbon monoxide concentration in the gas was assumed to be 40ppm. At this time, the smoke concentration in the environmental detection data of the area where the device to be detected a is located exceeds the smoke risk threshold, and the carbon monoxide concentration in the gas exceeds the gas risk threshold, which may indicate that the area where the device to be detected a is located is at risk.

S250, under the condition that at least one device to be detected in the power distribution room meets the preset fault processing condition, processing the equipment operation data, the equipment maintenance log and the environment detection data corresponding to the pre-acquired device to be detected according to the pre-trained fault trend prediction model to obtain the equipment prediction health state corresponding to the device to be detected.

And S260, determining an equipment maintenance task list corresponding to the power distribution room according to the equipment prediction health state, the equipment maintenance log and the pre-acquired maintenance resource information corresponding to at least one piece of equipment to be detected, so as to perform equipment maintenance on the corresponding equipment to be detected based on the equipment maintenance task list.

According to the technical scheme, the to-be-detected images corresponding to the to-be-detected equipment are obtained for the plurality of to-be-detected equipment in the power distribution room, under the condition that the to-be-detected equipment included in the to-be-detected images is determined to have surface defects, the electrical performance influence parameters corresponding to the surface defects of the to-be-detected equipment are determined according to the to-be-detected images, then, under the condition that the electrical performance influence parameters exceed the preset influence threshold, equipment vibration data of the to-be-detected equipment are obtained, frequency domain analysis is conducted on the equipment vibration data according to a fast Fourier transform algorithm to obtain vibration frequency characteristics, then, under the condition that abnormal vibration exists in the to-be-detected equipment, environment detection data of the area where the to-be-detected equipment is located are obtained, and then, under the condition that the area where the to-be-detected equipment is located is determined to have risks based on the environment detection data, the to-be-detected equipment is determined to meet preset fault processing conditions, the effect of effectively identifying the micro defects on the surface of the equipment is achieved, accuracy and efficiency of defect detection are improved, multi-dimensional data are provided for equipment vibration analysis is introduced, in addition, the judgment capability of abnormal operation states of the equipment is enhanced, in addition, the environment detection is conducted, the overall risk detection is improved, and the safety level is achieved is analyzed.

Example III

Fig. 3 is a schematic structural diagram of a fault handling device for power distribution equipment according to a third embodiment of the present invention. As shown in fig. 3, the apparatus includes: a data processing module 310 and a task list determination module 320.

The data processing module 310 is configured to, when it is determined that at least one device to be detected in the power distribution room meets a preset fault processing condition, process, according to a pre-trained fault trend prediction model, the pre-acquired device operation data, device maintenance log and environment detection data corresponding to the device to be detected, to obtain a device predicted health state corresponding to the device to be detected; the equipment prediction health state is used for indicating the health state change trend of the equipment to be detected within a preset time after the current moment; the task list determining module 320 is configured to determine, according to a predicted health state of a device corresponding to at least one device to be detected, a device maintenance log, and maintenance resource information acquired in advance, a device maintenance task list corresponding to the power distribution room, so as to perform device maintenance on a corresponding device to be detected based on the device maintenance task list; the maintenance resource information is used for indicating resources required for maintaining the equipment to be detected; the equipment maintenance task list comprises at least one equipment maintenance task arranged according to a preset task execution sequence.

Optionally, the preset fault processing condition includes that the equipment to be detected has abnormal vibration and the area where the equipment to be detected is located has risk; the equipment vibration data are used for indicating whether abnormal vibration exists in the equipment to be detected or not; the environment detection data are used for determining whether the area where the equipment to be detected is located is at risk.

Optionally, the apparatus further includes: the system comprises an image acquisition module, a vibration data acquisition module, an environment detection data acquisition module and a regional risk determination module.

The image acquisition module is used for acquiring to-be-processed images corresponding to a plurality of to-be-detected devices in the power distribution room, and determining electrical performance influence parameters corresponding to the surface defects of the to-be-detected devices according to the to-be-processed images under the condition that the surface defects of the to-be-detected devices included in the to-be-processed images are determined; the electrical performance influence parameter is used for indicating the influence degree of the surface defect of the equipment to be detected on the electrical performance of the equipment to be detected;

The vibration data acquisition module is used for acquiring equipment vibration data of the equipment to be detected under the condition that the electrical performance influence parameter exceeds a preset influence threshold value, and carrying out frequency domain analysis on the equipment vibration data according to a fast Fourier transform algorithm so as to obtain vibration frequency characteristics;

The environment detection data acquisition module is used for acquiring environment detection data of an area where the equipment to be detected is located under the condition that abnormal vibration exists in the equipment to be detected based on the vibration frequency characteristics;

And the regional risk determining module is used for determining that the equipment to be detected meets the preset fault processing condition under the condition that the risk exists in the region where the equipment to be detected is located based on the environment detection data.

Optionally, the apparatus further includes: an image processing module, an edge image determining module and a defect area determining module.

The image processing module is used for preprocessing the image to be processed according to a preset image preprocessing mode to obtain an image to be detected corresponding to the image to be processed; the preset image preprocessing method comprises graying and/or Gaussian blur;

the edge image determining module is used for processing the image to be detected according to an edge detection algorithm to obtain an equipment edge image corresponding to the equipment to be detected;

The defect area determining module is used for determining the curvature of the equipment edge according to the equipment edge image, determining that the equipment to be detected has surface defects under the condition that the curvature of the equipment edge exceeds a preset curvature threshold value, and marking the surface defect area in the processing image.

Optionally, the image acquisition module includes: a feature extraction unit, a defect association information determination unit, and a performance impact parameter determination unit.

The feature extraction unit is used for extracting features of the surface defect area in the image to be processed to obtain the features of the surface defect area;

The defect association information determining unit is used for processing the surface defect area characteristics according to a pre-trained decision tree model to obtain surface defect association information corresponding to the equipment to be detected; wherein the surface defect related information at least comprises surface defect type and defect severity information;

and the performance influence parameter determining unit is used for acquiring the electrical state data corresponding to the equipment to be detected and determining the electrical performance influence parameter corresponding to the surface defect of the equipment to be detected according to the electrical state data and the surface defect related information.

Optionally, the performance influence parameter determining unit includes: the data preprocessing subunit and the performance influencing parameter determining subunit.

The data preprocessing subunit is used for respectively preprocessing the surface defect associated information and the electrical state data according to a preset data preprocessing mode to obtain to-be-processed associated information and to-be-processed state data; the preset data preprocessing mode comprises data cleaning and/or data format conversion;

And the performance influence parameter determination subunit is used for processing the to-be-processed associated information and the to-be-processed state data according to a pre-trained logistic regression model to obtain the electrical performance influence parameters corresponding to the surface defects of the to-be-detected equipment.

Optionally, the task list determination module 320 includes: the system comprises a task generating unit, a weight value obtaining unit, a risk score determining unit, a task score determining unit and a task list determining unit.

The task generating unit is used for generating equipment maintenance tasks according to equipment operation data, environment detection data, equipment maintenance logs and equipment prediction health states corresponding to at least one piece of equipment to be detected;

The weight value acquisition unit is used for acquiring the equipment weight value corresponding to the equipment to be detected;

the risk score determining unit is used for processing the equipment prediction health state, the equipment maintenance log and the equipment weight value corresponding to the equipment to be detected according to a pre-trained risk assessment model to obtain a risk score corresponding to the equipment to be detected;

The task score determining unit is used for processing the risk scores and the maintenance resource information corresponding to all the equipment to be detected according to the optimization functions corresponding to the preset optimization targets to obtain task scores corresponding to each equipment maintenance task;

and the task list determining unit is used for arranging at least one equipment maintenance task according to the order of the task scores from high to low so as to obtain an equipment maintenance task list.

The power distribution equipment fault processing device provided by the embodiment of the invention can execute the power distribution equipment fault processing method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.

Example IV

Fig. 4 shows a schematic diagram of the structure of an electronic device 10 that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic equipment may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.

As shown in fig. 4, the electronic device 10 includes at least one processor 11, and a memory, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, etc., communicatively connected to the at least one processor 11, in which the memory stores a computer program executable by the at least one processor, and the processor 11 may perform various appropriate actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from the storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 may also be stored. The processor 11, the ROM 12 and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.

Various components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, etc.; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.

The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 11 performs the various methods and processes described above, such as the distribution equipment fault handling method.

In some embodiments, the power distribution device fault handling method may be implemented as a computer program tangibly embodied on a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the power distribution apparatus fault handling method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the power distribution device fault handling method in any other suitable manner (e.g., by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.

A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.

The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.

It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.

The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.

Claims

1. A method of fault handling for a power distribution device, comprising:

2. The power distribution equipment fault handling method according to claim 1, wherein the preset fault handling conditions include that abnormal vibration exists in the equipment to be detected and that risks exist in an area where the equipment to be detected is located; the equipment operation data at least comprises equipment vibration data and electrical state data; the equipment vibration data are used for indicating whether abnormal vibration exists in the equipment to be detected or not; the environment detection data are used for determining whether the area where the equipment to be detected is located is at risk.

3. The power distribution equipment fault handling method of claim 2, further comprising:

Aiming at a plurality of to-be-detected devices in a power distribution room, acquiring to-be-processed images corresponding to the to-be-detected devices, and determining electrical performance influence parameters corresponding to the surface defects of the to-be-detected devices according to the to-be-processed images under the condition that the surface defects of the to-be-detected devices included in the to-be-processed images are determined; the electrical performance influence parameter is used for indicating the influence degree of the surface defect of the equipment to be detected on the electrical performance of the equipment to be detected;

under the condition that the electrical performance influence parameter exceeds a preset influence threshold, acquiring equipment vibration data of the equipment to be detected, and carrying out frequency domain analysis on the equipment vibration data according to a fast Fourier transform algorithm to obtain vibration frequency characteristics;

acquiring environment detection data of an area where the equipment to be detected is located under the condition that abnormal vibration exists in the equipment to be detected based on the vibration frequency characteristics;

And under the condition that the risk exists in the area where the equipment to be detected is located based on the environment detection data, determining that the equipment to be detected meets the preset fault processing condition.

4. The power distribution equipment fault handling method of claim 3, further comprising:

Preprocessing the image to be processed according to a preset image preprocessing mode to obtain an image to be detected corresponding to the image to be processed; the preset image preprocessing method comprises graying and/or Gaussian blur;

processing the image to be detected according to an edge detection algorithm to obtain an equipment edge image corresponding to the equipment to be detected;

And determining the curvature of the equipment edge according to the equipment edge image, determining that the equipment to be detected has surface defects under the condition that the curvature of the equipment edge exceeds a preset curvature threshold value, and marking a surface defect area in the processing image.

5. The power distribution equipment fault handling method according to claim 4, wherein the determining, according to the image to be processed, an electrical performance impact parameter corresponding to a surface defect of the equipment to be detected includes:

Extracting features of the surface defect areas in the image to be processed to obtain surface defect area features;

Processing the surface defect area characteristics according to a pre-trained decision tree model to obtain surface defect associated information corresponding to the equipment to be detected; wherein the surface defect related information at least comprises surface defect type and defect severity information;

And acquiring electrical state data corresponding to the equipment to be detected, and determining electrical performance influence parameters corresponding to the surface defects of the equipment to be detected according to the electrical state data and the surface defect association information.

6. The power distribution equipment fault handling method according to claim 5, wherein the determining an electrical performance impact parameter corresponding to a surface defect of the equipment to be detected according to the electrical status data and the surface defect association information includes:

Respectively preprocessing the surface defect associated information and the electrical state data according to a preset data preprocessing mode to obtain to-be-processed associated information and to-be-processed state data; the preset data preprocessing mode comprises data cleaning and/or data format conversion;

And processing the to-be-processed associated information and the to-be-processed state data according to a pre-trained logistic regression model to obtain the electrical performance influence parameters corresponding to the surface defects of the to-be-detected equipment.

7. The power distribution equipment fault handling method according to claim 1, wherein the determining an equipment maintenance task list corresponding to the power distribution room according to the equipment prediction health state and the equipment maintenance log corresponding to the at least one to-be-detected equipment and the pre-acquired maintenance resource information comprises:

Generating equipment maintenance tasks according to equipment operation data, environment detection data, equipment maintenance logs and equipment prediction health states corresponding to at least one piece of equipment to be detected;

Acquiring a device weight value corresponding to the device to be detected;

Processing the equipment prediction health state, the equipment maintenance log and the equipment weight value corresponding to the equipment to be detected according to a pre-trained risk assessment model to obtain a risk score corresponding to the equipment to be detected;

processing risk scores and maintenance resource information corresponding to all the equipment to be detected according to optimization functions corresponding to a plurality of preset optimization targets to obtain task scores corresponding to each equipment maintenance task;

and arranging at least one equipment maintenance task according to the order of the task scores from high to low so as to obtain an equipment maintenance task list.

8. A power distribution equipment fault detection apparatus, comprising:

9. An electronic device, the electronic device comprising:

At least one processor; and

A memory communicatively coupled to the at least one processor; wherein,

The memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the power distribution apparatus fault handling method of any of claims 1-7.

10. A computer readable storage medium storing computer instructions for causing a processor to perform the method of fault handling of a power distribution apparatus according to any one of claims 1 to 7.