Method and device for evaluating fault risk of isolator, equipment and storage medium

Abstract

The embodiment of the application discloses a fault risk assessment method and device for isolating switches, equipment and a storage medium, and the method comprises the following steps: obtaining historical operation data of the isolating switch; determining a prior distribution obeyed by the isolating switch in an initial state of operation data based on the historical operation data; collecting actual operation data of the isolating switch in real time; performing fault prediction according to the prior distribution and the actual operation data by using a sequence Monte Carlo method to obtain a fault prediction result of the isolating switch; and comparing the fault prediction result with a preset fault threshold to determine whether the isolating switch is currently faulty. The sequence Monte Carlo method is adopted to effectively process the nonlinear and non-Gaussian distribution of the mechanical system of the isolating switch based on the particle filtering technology, so as to improve the accuracy of the fault prediction result. In addition, the state of the system is updated based on the time sequence, and the fault risk assessment result obtained by analyzing the updated system state is more reliable.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of fault detection, and in particular to a fault risk assessment method and device for disconnectors, equipment and a storage medium. BACKGROUND

[0002] Disconnectors play an important role in power systems for protection and isolation, and their failure can lead to serious power system accidents. With the increasing scale and complexity of power systems, the reliability and safety of disconnectors become particularly important. Therefore, risk assessment methods can be used to monitor disconnectors to ensure their normal operation.

[0003] Traditional risk assessment methods include qualitative assessment and quantitative assessment. Qualitative assessment relies on expert subjective judgment and is easily influenced by human factors, lacking scientific basis; quantitative assessment is usually based on statistical analysis and fault tree analysis methods, but these methods often fall short when dealing with high-dimensional, multi-variable and nonlinear systems. Therefore, existing risk assessment methods are usually based on historical data and expert experience, making it difficult to handle uncertainty and randomness, resulting in inaccurate and unreliable assessment results. SUMMARY

[0004] Therefore, it is necessary to propose a fault risk assessment method and device for disconnectors, equipment and a storage medium to improve the accuracy of fault risk assessment results.

[0005] To achieve the above-mentioned purpose, the first aspect of the present application provides a fault risk assessment method for disconnectors, which comprises:

[0006] obtaining historical operation data of the disconnector;

[0007] determining a prior distribution that the initial state of the operation data of the disconnector is subject to based on the historical operation data;

[0008] real-time collection of actual operation data of the disconnector;

[0009] using a sequential Monte Carlo method to perform fault prediction according to the prior distribution and the actual operation data, and obtaining a fault prediction result of the disconnector;

[0010] comparing the fault prediction result with a preset fault threshold to determine whether the disconnector is currently failing.

[0011] Further, the sequential Monte Carlo method is used to perform fault prediction according to the prior distribution and the actual operation data, and the fault prediction result of the disconnector is obtained, specifically including:

[0012] randomly sampling N particle samples from the prior distribution;

[0013] updating all particle samples by using a state transition model to generate predicted operation data corresponding to each particle sample;

[0014] performing fault analysis according to differences between all predicted operation data and actual operation data to obtain a fault prediction result.

[0015] Further, the state transition model is represented by the following formula:

[0016]

[0017] In the formula, is predicted operation data corresponding to the particle sample at time t, f(x t-1 ) is a preset system function of the disconnecting switch, is a preset process noise.

[0018] Further, the fault analysis according to differences between all predicted operation data and actual operation data to obtain a fault prediction result specifically includes:

[0019] calculating each particle sample's target weight according to each predicted operation data and actual operation data by using a preset likelihood function;

[0020] calculating a sum of target weights of all particle samples to obtain a total weight; the total weight is the fault prediction result.

[0021] Further, the weight calculation formula of the particle sample is as follows:

[0022]

[0023] In the formula, is the target weight of the i th particle sample, y t is the actual operation data, is the i th particle sample, is predicted operation data corresponding to the i th particle sample, is a preset dispersion degree of an observation noise distribution.

[0024] Further, the calculation of each particle sample's target weight according to each predicted operation data and actual operation data by using a preset likelihood function specifically includes:

[0025] calculating each particle sample's initial weight according to the predicted operation data and actual operation data based on a preset likelihood function;

[0026] The effective particle number is calculated according to initial weights of all particle samples;

[0027] When the effective particle number is less than a preset particle number threshold, resampling is performed on the particle samples to generate new particle samples, and the operation of updating all particle samples by using the state transition model to generate predicted running data corresponding to each particle sample is continued until the effective particle number is not less than the preset particle number threshold;

[0028] When the effective particle number is not less than the preset particle number threshold, the initial weights are taken as target weights, and the step of calculating the sum of the target weights of all particle samples to obtain a total weight is continued.

[0029] Further, the effective particle number is calculated by the following formula:

[0030]

[0031] In the formula, is a target weight of the i th particle sample, and N is a total number of particle samples.

[0032] To achieve the above object, the second aspect of the present application provides a fault risk assessment device of a disconnecting switch, which comprises a data acquisition module, a data analysis module and a fault prediction module;

[0033] The data acquisition module is configured to acquire historical running data of the disconnecting switch.

[0034] The data analysis module is configured to determine an initial state of the running data of the disconnecting switch according to the historical running data.

[0035] The data analysis module is configured to determine an initial state of the running data of the disconnecting switch according to the historical running data.

[0036] The data analysis module is configured to perform fault prediction according to the prior distribution and the actual running data by using a sequential Monte Carlo method to obtain a fault prediction result of the disconnecting switch.

[0037] The fault prediction module is configured to compare the fault prediction result with a preset fault threshold to determine whether the disconnecting switch is currently in fault.

[0038] To achieve the above object, the third aspect of the present application provides a computer readable storage medium storing a computer program, wherein the computer program is executed by a processor to make the processor execute the steps of the method according to the first aspect.

[0039] To achieve the above object, the fourth aspect of the present application provides a computer device, comprising a memory and a processor, characterized in that the memory stores a computer program, and the computer program is executed by the processor to make the processor execute the steps of the method according to the first aspect.

[0040] By adopting the embodiment of the present application, the following beneficial effects are achieved:

[0041] The embodiment of the present application provides a fault risk assessment method for the isolator, and the method comprises the following steps: obtaining historical operation data of the isolator; determining a prior distribution obeyed by the isolator in an initial state of operation data based on the historical operation data; collecting actual operation data of the isolator in real time; performing fault prediction according to the prior distribution and the actual operation data by using a sequence Monte Carlo method, to obtain a fault prediction result of the isolator; and comparing the fault prediction result with a preset fault threshold, to determine whether the isolator is currently in fault. The sequence Monte Carlo method is adopted in the present application, and a particle filtering technology is used to effectively process non-linear and non-Gaussian distribution of a mechanical system of the isolator, so as to improve the accuracy of the fault prediction result. In addition, the state of the system is updated based on a time sequence, and then the fault risk assessment result obtained by analyzing the updated system state is more reliable. BRIEF DESCRIPTION OF DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative labor.

[0043] Among them:

[0044] Figure 1 The flowchart of the fault risk assessment method for the isolator in the embodiment of the present application is shown in the figure.

[0045] Figure 2 The structural block diagram of the fault risk assessment device for the isolator in the embodiment of the present application is shown in the figure.

[0046] Figure 3 The internal structure diagram of the computer device in the embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0047] With reference to the accompanying drawings, the technical solutions in the embodiments of the present application will be clearly and completely described below, obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the protection scope of the present application.

[0048] The mechanical system failure of the isolating switch usually involves multiple physical processes, such as increased friction, wear, poor lubrication, etc., and the mechanical resistance change caused by these failure factors is not linearly increased. The traditional fault evaluation method is difficult to find the nonlinear change generated when the mechanical system fails, and then it is difficult to accurately analyze the fault from it.

[0049] Based on this, the embodiment of the present application proposes an isolating switch fault risk evaluation method based on sequence Monte Carlo method, which can be referred to as Figure 1 , Figure 1 The flowchart of the isolating switch fault risk evaluation method in the embodiment of the present application, the method comprises:

[0050] Step 110, obtaining the historical operation data of the isolating switch.

[0051] In the embodiment of the present application, before the fault diagnosis of the mechanical system of the isolating switch, the initial state of the mechanical system needs to be evaluated. Specifically, the historical operation data of the mechanical system of the isolating switch is obtained, and the initial state thereof is evaluated based on the historical operation data.

[0052] The mechanical system of the isolating switch involves complex dynamics, especially the interaction with the driving motor, and the driving motor power will change greatly with the change of the mechanical state. Therefore, in the embodiment of the present application, the operation data can be the driving motor power of the isolating switch, so as to evaluate the fault risk of the mechanical system of the isolating switch based on the driving motor power of the isolating switch.

[0053] Step 120, determining the prior distribution obeyed by the operation data of the isolating switch in the initial state based on the historical operation data.

[0054] In the embodiment of the present application, the initial state of the operation data of the isolating switch obeys a certain prior distribution, therefore, the prior distribution obeyed by the initial state of the operation data of the isolating switch can be obtained by analyzing the historical operation data of the initial state of the isolating switch. The prior distribution obeyed by the initial state of the operation data of the isolating switch can be represented by the following formula:

[0055]

[0056] In the formula, is the particle sample in the initial state, an initial state.

[0057] Step 130, collecting actual operation data of the disconnecting switch in real time.

[0058] Specifically, through a real-time or online monitoring application, the operation data of the disconnecting switch, such as the real-time power of the driving motor, is collected in real time. By continuously tracking and updating the system state, the system state of the disconnecting switch is updated in time for fault prediction.

[0059] Step 140, using a sequential Monte Carlo method to perform fault prediction according to the prior distribution and the actual operation data to obtain a fault prediction result of the disconnecting switch.

[0060] Considering the influence of adverse factors such as increased friction and mechanical resistance on the disconnecting switch, the operation data of the disconnecting switch will change abnormally, for example, when the lack of lubricant causes an increase in friction, the power of the driving motor of the disconnecting switch may show a nonlinear increase instead of a linear increase; when the mechanical parts are stuck, the power output of the driving motor of the disconnecting switch may show a sharp fluctuation, and this fluctuation is not necessarily a linear relationship. It can be seen that the complex dynamic behavior of the mechanical system makes the relationship between the power characteristics and the fault state nonlinear. Therefore, the embodiment of the present application adopts the sequential Monte Carlo method to process the nonlinear, non-Gaussian distribution of the operation data (i.e. the power of the driving motor) of the disconnecting switch due to the fault state, enhances the ability to process the nonlinear and dynamic system of the disconnecting switch, and further improves the accuracy of the fault prediction result.

[0061] Step 150, comparing the fault prediction result with a preset fault threshold to determine whether the disconnecting switch is currently malfunctioning.

[0062] In the embodiment of the present application, a fault threshold is preset, which represents the minimum fault prediction result of the fault occurrence. When the fault prediction result is less than the fault threshold, it is considered that the disconnecting switch does not malfunction; when the fault prediction result is not less than the fault threshold, it is considered that the disconnecting switch malfunctions, at which time a fault warning is triggered so as to timely handle the fault.

[0063] The present application utilizes the sequential Monte Carlo method to effectively process the nonlinear, non-Gaussian distribution of the mechanical system of the disconnecting switch based on the particle filtering technology to improve the accuracy of the fault prediction result. In addition, the state of the system is updated based on the time series, and the fault risk assessment result obtained through the analysis of the updated system state is more reliable.

[0064] In an embodiment of the present application, step 140, using a sequential Monte Carlo method to perform fault prediction according to the prior distribution and the actual operation data to obtain a fault prediction result of the disconnecting switch, specifically comprising:

[0065] Step 410, randomly sampling N particle samples from the prior distribution.

[0066] In the embodiment of the present application, each particle in the prior distribution represents a possible initial state of the mechanical system of the disconnecting switch, and N particle samples are randomly sampled from the prior distribution to update and evaluate the state of the mechanical system based on parallel simulation of multiple particle samples.

[0067] The sampling process of the particle samples is represented by the following formula:

[0068]

[0069] In the formula, is the i-th particle sample in the initial state, and t=0 is the initial state.

[0070] Step 420, updating all particle samples using a state transition model to generate predicted operation data corresponding to each particle sample.

[0071] In the embodiment of the present application, a nonlinear state transition model is introduced considering the influence of time series on the change of particle state, and the current state of the particle sample is updated based on the state transition model to obtain predicted operation data corresponding to each particle sample at different times. By processing the correlation in time series, the system states at different time points can influence and update each other, so as to improve the fault prediction accuracy of the mechanical system of the disconnecting switch.

[0072] Specifically, the change of the particle sample with time t can be described by the state transition model, and the state transition model reflects the change of the mechanical system from time t−1 to t. In an embodiment of the present application, the state transition model can be represented by the following state transition equation:

[0073]

[0074] In the formula, is the particle state at time t, f(x t-1 ) is a preset system function of the disconnecting switch, is a preset process noise, and the process noise is subject to a normal distribution, , which is used to simulate the uncertainty of the mechanical system.

[0075] The particle prediction is realized by updating the particle sample by the state transition model. Each particle sample generates a new predicted state according to the state transition equation, thereby simulating the possible state of the system at time t. The predicted operation data corresponding to each particle sample at different times is generated according to the updated system state.

[0076] The formula for predicting the particle state can be expressed as:

[0077]

[0078] In the formula, is the particle state of the i th particle at time t, is a preset system function of the disconnecting switch, is a preset process noise, and the process noise is subject to a normal distribution.

[0079] The embodiment of the present application reflects the change rule of the mechanical system state over time through the state transition equation, and considers the factor of random disturbance, so that more accurate prediction running data under the current state can be obtained.

[0080] Step 430, fault analysis is performed according to the difference between all the prediction running data and the actual running data, and a fault prediction result is obtained.

[0081] In an ideal state, the prediction running data and the observed actual running data should be the same or similar, but if the disconnecting switch has a mechanical fault, the observed actual running data and the prediction running data will have a difference, therefore, by analyzing the difference between the prediction running data and the actual running data, it is determined whether the disconnecting switch has a fault.

[0082] In an embodiment of the present application, Step 430, fault analysis is performed according to the difference between all the prediction running data and the actual running data, and a fault prediction result is obtained, specifically including:

[0083] Step 431, a preset likelihood function is used to calculate each particle sample target weight according to each prediction running data and actual running data.

[0084] In the embodiment of the present application, the observation model is introduced to map the particle sample from the current state to the observation space for observation, and the observation model describes the relationship between the system state and the actual running state under the normal state, that is, the relationship between the prediction running data and the actual running data.

[0085] When constructing the observation model, the error of the sensor collecting the running data and the external noise are considered, and the observation equation can be expressed as:

[0086]

[0087] In the formula, is the actual running data, is the prediction running data, is the observation noise, and the observation noise is subject to a normal distribution, .

[0088] The observation equation is used to compare the predicted running data with the actual running data to determine the reasonability of the particles. It can be understood that when the system fails, the relationship between the predicted running data and the actual running data cannot satisfy the observation equation, and thus the error between the actual running data and the predicted running data is analyzed to determine whether the mechanical system fails.

[0089] Specifically, the state of the particle sample is corrected according to the actually collected actual running data, and first, a target weight is allocated to each particle sample. The target weight is calculated according to a likelihood function of the actual running data and the predicted running data. The weight of the particle sample represents the matching degree of the predicted running data and the actual running data, and the higher the weight is, the closer the predicted running data corresponding to the particle sample is to the actual running data.

[0090] In an embodiment of the present application, the weight calculation formula of the particle sample is as follows:

[0091]

[0092] In the formula, is the target weight of the i th particle sample, y t is the actual running data, is the i th particle sample, is the predicted running data corresponding to the i th particle sample, is the preset discrete degree of the observation noise distribution.

[0093] In another embodiment of the present application, to prevent the target weight of the particle sample from excessively concentrating on a small number of particles and causing particle degradation, an adaptive resampling strategy can be introduced. When the particle sample does not satisfy a preset condition, the particle sample is resampled to improve the quality of the particle sample. Based on this, Step 431 calculates the target weight of each particle sample according to each predicted running data and actual running data by using a preset likelihood function, and specifically includes:

[0094] Step 4311 calculates the initial weight of each particle sample according to the predicted running data and the actual running data based on the preset likelihood function.

[0095] In the embodiment of the present application, the initial weight of each particle sample is calculated according to the predicted running data and the actual running data. The initial weight can be calculated by the following formula:

[0096]

[0097] In the formula, is the initial weight of the i th particle sample, y t is the actual running data, the target weight of the i th particle sample, N is the total number of particle samples. the predicted running data corresponding to the i th particle sample, the dispersion degree of the preset observation noise distribution.

[0098] Step 4312, the effective particle number is calculated according to the initial weight of all particle samples.

[0099] Specifically, the effective particle number (Effective Sample Size, ESS) reflects the diversity of the particle sample set. The larger the effective particle number is, the more uniform the particle sample weight is, the higher the particle quality is, and the more accurate the result obtained based on the particle sample set is; the smaller the effective particle number is, the more weight is concentrated on a small number of particles, and the lower the particle quality is, and the lower the robustness of the result obtained based on the particle sample set is.

[0100] In an embodiment of the present application, the effective particle number is calculated by the following formula:

[0101]

[0102] In the formula, the target weight of the i th particle sample, N is the total number of particle samples.

[0103] Step 4313, when the effective particle number is less than the preset particle number threshold, the particle sample is resampled to generate a new particle sample, and the operation of updating all particle samples by using the state transition model to generate the predicted running data corresponding to each particle sample is continued until the effective particle number is not less than the preset particle number threshold; when the effective particle number is not less than the preset particle number threshold, the initial weight is taken as the target weight, and the step of calculating the sum of the target weights of all particle samples to obtain the total weight is continued.

[0104] Specifically, when the effective particle number is lower than the preset particle number threshold, the resampling operation needs to be performed. The new particle sample is generated by resampling from the particle sample with high weight. By introducing an adaptive resampling strategy, whether to perform resampling is determined according to the dynamic change of the effective particle number, which prevents particle degradation while avoiding unnecessary calculation, so that the calculation resources can be more concentrated on the particle with high weight, thereby effectively reducing the number of invalid particles, greatly improving the calculation efficiency, and improving the real-time performance of the fault risk assessment.

[0105] The extraction process of the new particle sample can refer to the following formula:

[0106]

[0107] In the formula, , respectively the i-th and j-th particle sample, is the Dirac function.

[0108] After generating a new particle sample by re-sampling, the steps of Step 420-Step 430 are repeatedly executed until the effective particle number is not less than the particle number threshold. The initial weight of all particle samples at this time is taken as the target weight, so that subsequent failure risk assessment is carried out based on the target weight.

[0109] By evaluating the effectiveness of the particle sample, the particle is updated step by step, which can dynamically adjust the prediction of the failure rate, ensure the diversity of the particle sample set, and enable the subsequent analysis to continue to accurately capture the system state. Because the occurrence of the disconnector system failure can be gradual, the system state will change over time and operating conditions, so the ability to update the particle in real time is particularly important for mechanical failure prediction.

[0110] Step 432, the sum of the target weights of all particle samples is calculated to obtain the total weight; the total weight is the failure prediction result.

[0111] In the embodiment of the present application, whether the disconnector has a mechanical failure can be determined according to the sum of the target weights of all particle samples. First, the total weight of all particle samples is obtained according to the sum of the target weights of all particle samples; second, the total weight is compared with the preset failure threshold, when the total weight is less than the preset failure threshold, it indicates that the disconnector has not occurred mechanical failure; when the total weight is not less than the preset failure threshold, it indicates that the disconnector has occurred mechanical failure, at this time the system should initiate a failure warning, so as to timely adjust the failure of the disconnector.

[0112] The adaptive resampling strategy introduced in the embodiment of the present application can effectively avoid the problem of particle degradation by adjusting the weight distribution of the particle, improve the accuracy of the failure diagnosis process, and if the particle meets the condition, it can also reduce unnecessary resampling operation, improve the calculation efficiency, so as to realize more real-time failure evaluation.

[0113] The embodiment of the present application also proposes a disconnector failure risk assessment device, which can be referred to Figure 2 , Figure 2 is the structure block diagram of the disconnector failure risk assessment device in the embodiment of the present application, and the device comprises a data acquisition module 201, a data analysis module 202 and a failure prediction module 203.

[0114] The data acquisition module 201 is used to acquire the historical operation data of the disconnector.

[0115] The prior distribution followed by the initial state of the disconnector operation data is determined based on the historical operation data.

[0116] Real-time acquisition of actual operating data of disconnect switches.

[0117] The data analysis module 202 is used to perform fault prediction based on prior distribution and actual operating data using the sequential Monte Carlo method, and obtain the fault prediction results of the disconnecting switch.

[0118] The fault prediction module 203 is used to compare the fault prediction result with the preset fault threshold to determine whether the disconnecting switch is currently faulty.

[0119] The fault risk assessment device for disconnecting switches in this embodiment of the invention adopts the sequential Monte Carlo method and uses particle filtering technology to effectively handle the nonlinear and non-Gaussian distribution of the disconnecting switch mechanical system, thereby improving the accuracy of fault prediction results. In addition, the system state is updated based on time series, and the fault risk assessment results obtained by analyzing the updated system state are more reliable.

[0120] Figure 3 An internal structural diagram of a computer device according to one embodiment of the present invention is shown. This computer device can specifically be a terminal or a system. Figure 3 As shown, the computer device includes a processor, memory, and network interface connected via a system bus. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and may also store a computer program. When executed by the processor, this computer program causes the processor to perform the steps in the above-described method embodiments. The internal memory may also store a computer program, which, when executed by the processor, causes the processor to perform the steps in the above-described method embodiments. Those skilled in the art will understand that... Figure 3 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0121] In one embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the steps in the above method embodiments.

[0122] In one embodiment, a computer readable storage medium is provided, which stores a computer program. The computer program is executed by a processor to make the processor perform the steps of the above method embodiments. A person of ordinary skill in the art can understand that all or part of the processes in the above method embodiments can be completed by a computer program instructing relevant hardware. The program can be stored in a non-volatile computer readable storage medium. When the program is executed, it can include the processes of the above method embodiments. Any reference to memory, storage, database, or other medium used in the embodiments provided in the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0123] The technical features of the above embodiments can be combined in any manner. To make the description concise, not all possible combinations of the technical features in the above embodiments are described, but as long as the combinations of the technical features do not exist contradictions, they should be considered as the scope of the present disclosure.

[0124] The above embodiments only express several implementation manners of the present application, and the description is specific and detailed, but it should not be understood as a limitation on the scope of the patent of the present application. It should be pointed out that for those of ordinary skill in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are all within the scope of protection of the present application. Therefore, the scope of protection of the patent of the present application should be subject to the appended claims.

Claims

1. A method for failure risk assessment of a disconnector, characterized in that The method comprises: acquiring historical operation data of the disconnecting switch; determining a prior distribution to which operation data of the disconnecting switch in an initial state is subject based on the historical operation data; real-time collection of actual operation data of the disconnecting switch; fault prediction based on the prior distribution and the actual operation data by using a sequential Monte Carlo method to obtain a fault prediction result of the disconnecting switch; comparison of the fault prediction result with a preset fault threshold to determine whether the disconnecting switch is currently faulty; wherein the fault prediction based on the prior distribution and the actual operation data by using the sequential Monte Carlo method to obtain the fault prediction result of the disconnecting switch specifically comprises: random extraction of N particle samples from the prior distribution; updating of all particle samples by using a state transition model to generate predicted operation data corresponding to each particle sample; fault analysis based on a gap between all the predicted operation data and the actual operation data to obtain a fault prediction result; the state transition model is represented by the following formula: In the formula, is the predicted running data corresponding to the particle sample at time t, f(x t-1 ) is a preset system function of the disconnecting switch, is a preset process noise; wherein the fault analysis based on the gap between all the predicted operation data and the actual operation data to obtain a fault prediction result specifically comprises: calculation based on each of the predicted operation data and the actual operation data by using a preset likelihood function to obtain a target weight of each particle sample; calculation of a sum of the target weights of all particle samples to obtain a total weight; the total weight is the fault prediction result; wherein the calculation based on each of the predicted operation data and the actual operation data by using the preset likelihood function to obtain the target weight of each particle sample specifically comprises: calculation based on the predicted operation data and the actual operation data by using a preset likelihood function to obtain an initial weight of each particle sample; calculation of an effective particle number based on the initial weights of all particle samples; when the effective particle number is less than a preset particle number threshold, resampling of particle samples to generate new particle samples, and continuous execution of the updating of all particle samples by using the state transition model to generate predicted operation data corresponding to each particle sample until the effective particle number is not less than the preset particle number threshold; when the effective particle number is not less than the preset particle number threshold, the initial weight is taken as a target weight, and the step of calculating a sum of the target weights of all particle samples to obtain a total weight is continuously executed.

2. The method of claim 1, wherein, the effective particle number is calculated by the following formula: In the formula, Wi is the target weight of the i-th particle sample, and N is the total number of particle samples.

3. A fault risk assessment device for a disconnector, characterized in that The device refers to the method as claimed in any one of claims 1-2, and the device comprises a data collection module, a data analysis module, and a fault prediction module; the data collection module is configured to acquire historical operation data of the disconnecting switch; determining a prior distribution to which operation data of the disconnecting switch in an initial state is subject based on the historical operation data; real-time collection of actual operation data of the disconnecting switch; the data analysis module is configured to perform fault prediction based on the prior distribution and the actual operation data by using a sequential Monte Carlo method to obtain a fault prediction result of the disconnecting switch; The fault prediction module is configured to compare the fault prediction result with a preset fault threshold to determine whether the disconnector is currently faulty.

4. A computer readable storage medium storing a computer program, characterized in that, The computer program, when executed by a processor, causes the processor to perform the steps of the method of any one of claims 1 to 2. 5.A computer device, comprising a memory and a processor, and characterized in that, The memory stores a computer program, which, when executed by the processor, causes the processor to perform the steps of the method of any one of claims 1 to 2.

Images