Method, device, equipment, medium and product for predicting risk of SF6 high-voltage circuit breaker refusal

Abstract

The application discloses a SF6 high-voltage circuit breaker refusal risk prediction method, device, equipment, medium and product, and the method comprises the following steps: preprocessing historical record data of a SF6 high-voltage circuit breaker in a target area, obtaining a plurality of space-time characteristic factors, mapping the space-time characteristic factors to a unified matrix space, constructing a space-time characteristic matrix, constructing a key density function of each space-time characteristic factor based on the space-time characteristic matrix, constructing a key degree fuzzy reasoning model based on the key density function, and using the key degree fuzzy reasoning model to quantize fuzzy information of the space-time characteristic factors into a refusal risk degree; and predicting the refusal risk of the SF6 high-voltage circuit breaker in the target area based on the key degree fuzzy reasoning model, so as to realize high-precision prediction of the refusal risk distribution of the SF6 high-voltage circuit breaker from the space-time dimension, timely and effectively capture the potential risk of the SF6 high-voltage circuit breaker, and thus provide strong support for stable operation of a power system.

Description

Technical Field

[0001] This invention relates to the field of power systems, and in particular to a method, apparatus, equipment, medium, and product for predicting the risk of SF6 high-voltage circuit breaker failure to operate. Background Technology

[0002] As the scale of power systems continues to expand, their complexity is increasing daily. SF6 high-voltage circuit breakers, as key equipment for power transmission and distribution, are crucial for ensuring the stability of power supply. SF6 high-voltage circuit breakers are protective devices for high-voltage (typically 1kV and above) lines in power systems, utilizing sulfur hexafluoride (SF6) gas as insulation and arc-quenching medium. A failure of an SF6 high-voltage circuit breaker to operate can trigger a chain reaction, leading to widespread power outages and severely impacting the social economy and people's lives. Traditional methods for predicting the risk of SF6 high-voltage circuit breaker failure to operate primarily rely on substation ground monitoring data (monitoring electrical and mechanical parameters).

[0003] However, this prediction method, which relies solely on ground monitoring, has certain spatiotemporal limitations. In the temporal dimension, existing methods for predicting the risk of SF6 high-voltage circuit breaker failure to operate lack the ability to effectively integrate and deeply analyze long-term historical data. In the spatial dimension, on the one hand, ground sensors (voltage transformers, current transformers, pressure sensors, etc.) can only acquire local information within a limited range; on the other hand, they cannot effectively capture and analyze the potential impact of real-time external factors on the overall environmental changes affecting the circuit breaker. Summary of the Invention

[0004] The main objective of this invention is to provide a method, device, equipment, medium, and product for predicting the risk of SF6 high-voltage circuit breaker failure to operate. This invention aims to solve the technical problem that existing methods for predicting the risk of SF6 high-voltage circuit breaker failure to operate have spatiotemporal limitations, cannot effectively capture the potential risks of SF6 high-voltage circuit breakers, and result in low accuracy in predicting the risk of failure to operate.

[0005] To achieve the above objectives, the present invention provides a method for predicting the risk of SF6 high-voltage circuit breaker failure to operate, the method comprising the following steps:

[0006] The historical data of SF6 high-voltage circuit breakers in the target area are preprocessed to obtain multiple spatiotemporal characteristic factors. The historical data is collected by an air-ground integrated sensing system, which includes an air-based data acquisition module and a ground-based data acquisition module. The historical data includes time dimension data and spatial dimension data.

[0007] The spatiotemporal feature factors are mapped to a unified matrix space to construct a spatiotemporal feature matrix, which includes multiple historical records and the fault results and spatiotemporal feature factors corresponding to each historical record.

[0008] Construct key density functions for each spatiotemporal feature factor based on the aforementioned spatiotemporal feature matrix;

[0009] A key-degree fuzzy inference model is constructed based on the key density function. The key-degree fuzzy inference model is used to quantify the fuzzy information of spatiotemporal feature factors into a refusal risk degree.

[0010] Based on the criticality fuzzy inference model, the failure-to-operate risk prediction of SF6 high-voltage circuit breakers in the target area is performed to obtain the failure-to-operate risk degree of each spatiotemporal characteristic factor in the SF6 high-voltage circuit breaker.

[0011] Optionally, constructing the key density function for each spatiotemporal feature factor based on the spatiotemporal feature matrix includes:

[0012] Based on the spatiotemporal feature matrix, the probability density function of each spatiotemporal feature factor is generated, and the fault correlation information between each spatiotemporal feature factor and the failure to operate fault, as well as the severity information of the failure to operate fault, are determined.

[0013] The fault contribution weight and severity weight of each spatiotemporal characteristic factor are determined based on the fault association information and the fault severity information.

[0014] Based on the probability density function, the fault contribution weight, and the severity weight, a key density function for each spatiotemporal feature factor is constructed. The mathematical expression of the key density function is as follows:

[0015]

[0016] in, Represents spatiotemporal characteristic factors The key to the refusal to move. Represents spatiotemporal characteristic factors The probability density function value, which represents the frequency of occurrence of spatiotemporal characteristic factors under different states. Indicates the fault contribution weight. Indicates the severity weight.

[0017] Optionally, constructing a key-degree fuzzy inference model based on the key density function includes:

[0018] The criticality of each spatiotemporal characteristic factor is determined based on the critical density function.

[0019] Based on the aforementioned refusal criticality, an input membership function and an output refusal membership function are constructed. The input membership function and the output refusal membership function are constructed based on trapezoidal membership function form and triangular membership function form, respectively.

[0020] A multi-factor fuzzy reasoning framework is constructed based on the input membership function and the output rejection membership function;

[0021] The logical operation process in the multi-factor fuzzy reasoning framework is optimized by organizing it in a hierarchical structure to construct hierarchical fuzzy rules;

[0022] A key-degree fuzzy inference model is constructed based on the aforementioned hierarchical fuzzy rules.

[0023] Optionally, constructing the input membership function and the output membership function based on the refusal-to-move criticality includes:

[0024] Based on the data location type of each spatiotemporal feature factor, the refusal keyness of each spatiotemporal feature factor is fuzzified, and an input membership function is constructed based on the fuzzification result. The fuzzification process includes mapping the refusal keyness of each spatiotemporal feature factor to an input fuzzy set, and the input fuzzy set includes multiple different feature frequency sets.

[0025] Based on the aforementioned failure-to-operate criticality and the SF6 high-voltage circuit breaker failure-to-operate knowledge base, fuzzy operation logic rules are constructed.

[0026] Based on the fuzzy operation logic rules, the risk of refusal to act is fuzzy classified, and a fuzzy set of output refusal to act multi-level risk is constructed. The fuzzy set of output refusal to act multi-level risk includes multiple different sets of refusal risk levels.

[0027] Determine the fuzzy mapping relationship between each spatiotemporal feature factor and each risk level set in the output refusal multi-level risk fuzzy set;

[0028] The output rejection membership function is constructed based on the fuzzy mapping relationship.

[0029] Optionally, the keyness fuzzy inference model is configured to calculate the refusal keyness of the input spatiotemporal feature factors based on the key density function, and to perform fuzzification processing on the refusal keyness of the spatiotemporal feature factors to obtain fuzzy information of the spatiotemporal feature factors.

[0030] The key-degree fuzzy inference model is further configured to defuzzify the fuzzy information based on the centroid method, and output the refusal risk degree of the spatiotemporal feature factor, as shown in the following formula:

[0031]

[0032] in, Indicates the first The risk level of action of the spatiotemporal characteristic factors of the input group. Indicates the first Spatiotemporal feature factors of the input group This represents the total number of fuzzy sets that overlap after the input features are fuzzified. Indicates the first Membership function of a fuzzy set Representing fuzzy sets Elements in the domain of discourse.

[0033] Optionally, the historical data of SF6 high-voltage circuit breakers in the target area are preprocessed to obtain multiple spatiotemporal characteristic factors, including:

[0034] The historical data of SF6 high-voltage circuit breakers in the target area are cleaned using a linear interpolation strategy to obtain initial feature factors.

[0035] The initial feature factors are normalized to obtain multiple spatiotemporal feature factors.

[0036] Furthermore, to achieve the above objectives, the present invention also proposes an SF6 high-voltage circuit breaker failure-to-operate risk prediction device, the SF6 high-voltage circuit breaker failure-to-operate risk prediction device comprising:

[0037] The data processing module is used to preprocess the historical data of SF6 high-voltage circuit breakers in the target area to obtain multiple spatiotemporal characteristic factors. The historical data is collected through an air-ground integrated sensing system, which includes an air-based data acquisition module and a ground-based data acquisition module. The historical data includes time dimension data and spatial dimension data.

[0038] The feature mapping module is used to map the spatiotemporal feature factors to a unified matrix space to construct a spatiotemporal feature matrix. The spatiotemporal feature matrix includes multiple historical records and the fault results and spatiotemporal feature factors corresponding to each historical record.

[0039] The key density function module is used to construct key density functions for each spatiotemporal feature factor based on the spatiotemporal feature matrix.

[0040] The model building module is used to build a key degree fuzzy inference model based on the key density function. The key degree fuzzy inference model is used to quantify the fuzzy information of spatiotemporal feature factors into a refusal risk degree.

[0041] The risk prediction module is used to predict the failure to operate risk of SF6 high-voltage circuit breakers in the target area based on the criticality fuzzy inference model, and to obtain the failure to operate risk degree of each spatiotemporal characteristic factor in the SF6 high-voltage circuit breaker.

[0042] In addition, to achieve the above objectives, this application also proposes an SF6 high-voltage circuit breaker failure-to-operate risk prediction device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the SF6 high-voltage circuit breaker failure-to-operate risk prediction method described above.

[0043] In addition, to achieve the above objectives, this application also proposes a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the SF6 high-voltage circuit breaker failure-to-operate risk prediction method described above.

[0044] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the SF6 high-voltage circuit breaker failure-to-operate risk prediction method described above.

[0045] This invention preprocesses historical data of SF6 high-voltage circuit breakers in a target area to obtain multiple spatiotemporal characteristic factors. The historical data is collected through an integrated air-ground sensing system, which includes an airborne data acquisition module and a ground-based data acquisition module. The historical data includes time-dimensional and spatial-dimensional data. The spatiotemporal characteristic factors are mapped to a unified matrix space to construct a spatiotemporal characteristic matrix. This matrix includes multiple historical data samples and their corresponding fault results and spatiotemporal characteristic factors. Based on the spatiotemporal characteristic matrix, a key density function is constructed for each spatiotemporal characteristic factor. Based on the key density function, a key-degree fuzzy inference model is constructed. This key-degree fuzzy inference model quantifies the fuzzy information of the spatiotemporal characteristic factors into a failure-to-operate risk level. Based on this key-degree fuzzy inference model, the failure-to-operate risk of SF6 high-voltage circuit breakers in the target area is assessed. The invention predicts and obtains the failure-to-operate risk level of each spatiotemporal characteristic factor in the SF6 high-voltage circuit breaker. Because this invention collects historical spatiotemporal data of SF6 high-voltage circuit breakers in the target area through an integrated air-ground sensing system, and preprocesses this data to obtain multiple spatiotemporal characteristic factors, mapping these factors to a unified matrix space, it provides a comprehensive and multi-layered spatiotemporal information foundation for risk prediction. This effectively solves the problem of limited risk prediction due to spatiotemporal constraints. Based on the key density function, a key degree fuzzy inference model is constructed. Through fuzzy inference logic, a scientific and objective analysis of each spatiotemporal characteristic is achieved, accurately quantifying the impact of different spatiotemporal characteristics on the failure-to-operate risk. This is more in line with the complex and ever-changing operating characteristics of the power system, thus significantly improving the accuracy of risk assessment and timely and effectively capturing the potential risks of SF6 high-voltage circuit breakers, thereby providing strong support for ensuring the stable operation of the power system. Attached Figure Description

[0046] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0047] Figure 1 This is a schematic diagram of the structure of the SF6 high-voltage circuit breaker failure-to-operate risk prediction device in the hardware operating environment involved in the embodiments of the present invention;

[0048] Figure 2 This is a flowchart illustrating the first embodiment of the SF6 high-voltage circuit breaker failure-to-operate risk prediction method of the present invention;

[0049] Figure 3 This is a schematic diagram of the probability density function of spatiotemporal characteristic factors in one embodiment of the SF6 high-voltage circuit breaker failure-to-operate risk prediction method of the present invention;

[0050] Figure 4 This is a schematic diagram of the key density function of spatiotemporal characteristic factors in one embodiment of the SF6 high-voltage circuit breaker failure-to-operate risk prediction method of the present invention;

[0051] Figure 5 This is a schematic diagram illustrating the deployment effect of the failure-to-operate risk prediction framework in one embodiment of the SF6 high-voltage circuit breaker failure-to-operate risk prediction method of the present invention;

[0052] Figure 6 This is a flowchart illustrating the second embodiment of the SF6 high-voltage circuit breaker failure-to-operate risk prediction method of the present invention;

[0053] Figure 7 This is a schematic diagram of the input membership function in one embodiment of the SF6 high-voltage circuit breaker failure-to-operate risk prediction method of the present invention;

[0054] Figure 8 This is a schematic diagram of the output failure-to-operate membership function in one embodiment of the SF6 high-voltage circuit breaker failure-to-operate risk prediction method of the present invention;

[0055] Figure 9 This is a schematic diagram of the operation flow of the criticality fuzzy inference model in one embodiment of the SF6 high-voltage circuit breaker failure-to-operate risk prediction method of the present invention;

[0056] Figure 10 This is a flowchart of defuzzification and solution of the failure-to-operate risk degree in one embodiment of the SF6 high-voltage circuit breaker failure-to-operate risk prediction method of the present invention;

[0057] Figure 11This is a visualization of the failure-to-operate risk prediction results in one embodiment of the SF6 high-voltage circuit breaker failure-to-operate risk prediction method of the present invention;

[0058] Figure 12(a) and Figure 12(b) are comparison charts of ROC curve verification for SF6 failure to operate fault in one embodiment of the SF6 high-voltage circuit breaker failure to operate risk prediction method of the present invention;

[0059] Figures 13(a) and 13(b) are comparative graphs of PR curve verification for SF6 failure to operate fault in one embodiment of the SF6 high-voltage circuit breaker failure to operate risk prediction method of the present invention.

[0060] Figure 14 This is a comparison chart of SF6 failure-to-operate fault speed verification in one embodiment of the SF6 high-voltage circuit breaker failure-to-operate risk prediction method of the present invention;

[0061] Figure 15 This is a structural block diagram of the first embodiment of the SF6 high-voltage circuit breaker failure-to-operate risk prediction device of the present invention.

[0062] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0063] It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the invention.

[0064] Reference Figure 1 , Figure 1 This is a schematic diagram of the SF6 high-voltage circuit breaker failure-to-operate risk prediction device structure in the hardware operating environment involved in the embodiments of the present invention.

[0065] like Figure 1As shown, the SF6 high-voltage circuit breaker failure-to-operate risk prediction device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen or an input unit such as a keyboard; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wireless-Fidelity (Wi-Fi) interface). The memory 1005 may be high-speed random access memory (RAM) or stable non-volatile memory (NVM), such as a disk storage device. The memory 1005 may also optionally be a storage device independent of the aforementioned processor 1001.

[0066] Those skilled in the art will understand that Figure 1 The structure shown does not constitute a limitation on the SF6 high-voltage circuit breaker failure-to-operate risk prediction device, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0067] like Figure 1 As shown, the memory 1005, which is a computer-readable storage medium, may include an operating system, a network communication module, a user interface module, and an SF6 high-voltage circuit breaker failure-to-operate risk prediction program.

[0068] exist Figure 1 In the SF6 high-voltage circuit breaker failure-to-operate risk prediction device shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and memory 1005 in the SF6 high-voltage circuit breaker failure-to-operate risk prediction device of the present invention can be set in the SF6 high-voltage circuit breaker failure-to-operate risk prediction device. The SF6 high-voltage circuit breaker failure-to-operate risk prediction device calls the SF6 high-voltage circuit breaker failure-to-operate risk prediction program stored in the memory 1005 through the processor 1001 and executes the SF6 high-voltage circuit breaker failure-to-operate risk prediction method provided in the embodiment of the present invention.

[0069] This invention provides a method for predicting the risk of SF6 high-voltage circuit breaker failure to operate, referring to... Figure 2 , Figure 2 This is a flowchart illustrating the first embodiment of the SF6 high-voltage circuit breaker failure-to-operate risk prediction method of the present invention.

[0070] In this embodiment, the SF6 high-voltage circuit breaker failure-to-operate risk prediction method includes the following steps:

[0071] Step S10: Preprocess the historical data of SF6 high-voltage circuit breakers in the target area to obtain multiple spatiotemporal characteristic factors.

[0072] It should be noted that this embodiment is applied to the risk prediction and health management of SF6 high-voltage circuit breaker failure to operate. SF6 high-voltage circuit breaker is a protection device for high-voltage (usually 1kV and above) lines in power systems that uses sulfur hexafluoride (SF6) gas as insulation and arc extinguishing medium.

[0073] It should be understood that the executing entity of this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or a terminal electronic device capable of performing the above functions. The following description uses an SF6 high-voltage circuit breaker failure-to-operate risk prediction device (hereinafter referred to as the prediction device) as an example to illustrate this embodiment and the following embodiments.

[0074] It should be noted that the historical data is collected through an integrated air-ground sensing system, which includes an air-based data acquisition module and a ground-based data acquisition module. The historical data includes time-dimensional data and spatial-dimensional data.

[0075] It should be noted that the target area can be a substation area, such as including 110kV substations, as well as wind power plants, photovoltaic power plants, thermal power plants, etc. Historical data can be real-time fault records of SF6 circuit breaker failure to operate within the target area over a historical period (e.g., 3 years).

[0076] It should be noted that the air-ground integrated sensing system can be an air-ground integrated sensing platform built based on airborne data acquisition modules and ground-based data acquisition modules. The airborne data acquisition module can be an aerial surveillance platform (such as a drone); the ground-based data acquisition module can be a ground vision platform (such as a ground camera) and various ground sensors (such as voltage transformers (TV), current transformers, spring sensors, temperature and humidity sensors, SF6 gas sensors, etc.).

[0077] In some embodiments, the predictive device can be combined with an aerial surveillance platform (professional UAV infrared and visual inspection), a ground-based visual platform (camera inspection), and various ground sensors (voltage transformers, current transformers, spring sensors, temperature and humidity sensors, SF6 gas sensors, etc.) to form an integrated air-ground sensing platform. This platform comprehensively collects information on the operating environment and status of the SF6 high-voltage circuit breaker from both a spatial dimension (covering key components of the circuit breaker and surrounding environmental characteristics such as terrain, wind speed, and humidity) and a temporal dimension (including operating dates and seasonal climate factors). The collected data types cover electrical parameters, mechanical parameters, temporal parameters, and external environmental parameters, providing multi-dimensional support for the health monitoring and fault diagnosis of the circuit breaker.

[0078] Furthermore, in order to improve data quality and reduce the impact of outlier data on prediction results, step S10 above may include:

[0079] Step S101: Based on the linear interpolation strategy, perform data cleaning on the historical data of SF6 high-voltage circuit breakers in the target area to obtain initial feature factors;

[0080] Step S102: Normalize the initial feature factors to obtain multiple spatiotemporal feature factors.

[0081] It should be noted that the prediction equipment performs data cleaning on the extracted complex spatiotemporal features from multiple sources, eliminating the impact of outliers on the prediction results and employing linear interpolation. Subsequently, normalization is performed to map the data to a standard interval, effectively eliminating inconsistencies in data size and distribution caused by differences in data sources and types. Then, the extracted features are mapped to a unified matrix space to construct a comprehensive database, providing robust support for subsequent analysis and decision-making. Preprocessing of historical data may include:

[0082] (1) Data cleaning (outlier removal and linear interpolation): Outliers are extracted using a method combining standard deviation and box plots, specifically:

[0083] First, calculate the mean of the data. and standard deviation At the same time, determine the quartiles. and as well as For each data point, if or or If the value is not found, the point will be marked as an outlier and removed.

[0084] Linear interpolation is based on the assumption that adjacent data points have a linear relationship. It interpolates by taking the median value between two adjacent normal data points. Specifically:

[0085]

[0086] in, The specific value being replaced; and These are the numerical values ​​of the normal characteristic factors arranged in order for this spatiotemporal feature.

[0087] Normalization: Mapping spatiotemporal feature data of different magnitudes and ranges to a unified standard interval. Specifically, it includes:

[0088]

[0089] in, These are the normalized spatiotemporal characteristic factors. For each spatiotemporal feature data sequence, the first... One factor, This is the maximum value in the spatiotemporal characteristic data sequence; It is the minimum value in this spatiotemporal feature data sequence.

[0090] Step S20: Map the spatiotemporal feature factors to a unified matrix space to construct a spatiotemporal feature matrix.

[0091] It should be noted that the spatiotemporal feature matrix includes multiple historical records and the corresponding fault results and spatiotemporal feature factors for each historical record.

[0092] It is understandable that this embodiment maps spatiotemporal feature factors to a unified matrix space. Specifically, let the database contain a set of sample rules from the historical operation records of circuit breakers. ;in The total number of fault regulations to be entered. This refers to the serial number of a specific sample regulation. Indicates a certain All of them Multidimensional spatiotemporal feature types of space-time. For any element in It is by Specific numerical composition of dimensional features .in, In order to be in A certain spatiotemporal characteristic under the regulations. Furthermore, for any fault outcome in the sample regulations. Where 1 indicates that the circuit breaker has failed to operate, and 0 indicates that the circuit breaker has not failed to operate.

[0093] Therefore, the final comprehensive database is constructed. for:

[0094]

[0095] In some embodiments, the prediction device collects multi-dimensional spatiotemporal features from both air and ground, performs data cleaning, and eliminates the impact of outliers on the prediction results. Subsequently, normalization processing and organic fusion of various spatiotemporal environmental features are performed, mapping these features to a unified matrix space to construct a comprehensive database.

[0096] Step S30: Construct the key density function of each spatiotemporal feature factor based on the spatiotemporal feature matrix.

[0097] It should be noted that the key density function (KDF) is a function used to describe the weights that influence the occurrence of faults in a continuous random variable across its various value intervals.

[0098] In some embodiments, the prediction device can obtain the probability density function (PDF) of each spatiotemporal characteristic factor, and construct a key density function that can accurately reflect the actual fault contribution of each characteristic based on the probability density function.

[0099] Furthermore, in order to more accurately measure the actual fault contribution of each feature, step S30 above may include:

[0100] Step S301: Generate the probability density function of each spatiotemporal feature factor based on the spatiotemporal feature matrix, and determine the fault association information between each spatiotemporal feature factor and the failure to operate fault, as well as the severity information of the failure to operate fault;

[0101] Step S302: Determine the fault contribution weight and severity weight of each spatiotemporal characteristic factor based on the fault association information and the fault severity information.

[0102] Step S303: Construct the key density function of each spatiotemporal feature factor based on the probability density function, the fault contribution weight, and the severity weight.

[0103] It should be noted that predictive equipment can construct probability density functions for each spatiotemporal characteristic factor by analyzing the spatiotemporal feature matrix. Based on this, a key density function that accurately reflects the actual fault contribution of each feature can be constructed. Taking the characteristic factor of average temperature as an example, refer to... Figure 3 and Figure 4 , Figure 3 This is a schematic diagram of the probability density function of spatiotemporal feature factors in one embodiment. Figure 4 This is a schematic diagram of the key density function of spatiotemporal feature factors in one embodiment.

[0104] Understandably, predictive equipment can rely on observation data within its statistical period based on various spatiotemporal characteristics. Calculate and plot its probability density function, where the probability density function satisfies ,and , It is a certain feature The first of the observation data Each characteristic factor.

[0105] However, relying solely on frequency of occurrence to represent the importance of a circuit breaker in the event of a failure to operate is not rigorous. Many rare but high-risk factors exist (such as earthquakes and extremely high load currents), which, despite their low frequency of occurrence, can immediately lead to a circuit breaker failure to operate once they occur. Therefore, to more accurately measure the actual fault contribution of each feature, this embodiment constructs a more comprehensive evaluation index, the Keyness Density Function (KDF), based on the probability density function. The KDF not only considers the probability of occurrence of factors but also assigns higher weights to feature factors with higher risk contributions, thus reflecting their actual "criticality." The mathematical expression of the Keyness Density Function is as follows:

[0106]

[0107] in, Represents spatiotemporal characteristic factors The key to refusal to act; Represents spatiotemporal characteristic factors The probability density function value, which represents the frequency of occurrence of spatiotemporal feature factors under different states; This represents the fault contribution weight, which indicates the magnitude of the contribution of this factor to the circuit breaker's failure to operate fault when it occurs. This indicates the severity weight, which reflects the extent to which the occurrence of this factor may lead to a failure to operate.

[0108] Step S40: Construct a keyness fuzzy inference model based on the key density function.

[0109] It should be noted that the Critical Decomposed Fuzzy Inference (CDFI) model is used to quantify the fuzzy information of spatiotemporal feature factors into a refusal risk degree.

[0110] Understandably, this implementation establishes fuzzy operation rules based on the multi-factor holistic reasoning (MHR) method in traditional multi-factor fuzzy reasoning, designs an output failure-to-operate membership function in conjunction with the key density function, and establishes a CDFI model based on a hierarchical reasoning architecture to obtain the output failure-to-operate risk degree, and finally obtains the failure-to-operate risk level. This allows for a precise measurement of the real-time prediction of multi-level risks of SF6 high-voltage circuit breaker failure-to-operate faults based on various sample regulations in the comprehensive database.

[0111] Step S50: Based on the criticality fuzzy inference model, predict the failure-to-operate risk of the SF6 high-voltage circuit breaker in the target area, and obtain the failure-to-operate risk degree of each spatiotemporal characteristic factor in the SF6 high-voltage circuit breaker.

[0112] It should be noted that the characteristic factors reflecting the failure of SF6 high-voltage circuit breakers to operate in real-world scenarios are not limited to the localized important information collected by ground sensors, but also include the potential influence of many spatiotemporal environmental factors. Traditional prediction methods, which rely solely on this information to predict the risk of SF6 circuit breaker failure to operate, have low accuracy and cannot meet the high standards of power system stability required in real-world scenarios. Furthermore, existing prediction methods often employ explicit set algorithms, subjectively classifying continuous data for prediction, which is inconsistent with actual real-world scenarios and inevitably leads to a loss of accuracy in the final results. Therefore, this embodiment, relying on integrated air-ground sensing technology and coupled with a criticality fuzzy inference model, fully considers the multi-dimensional spatiotemporal environmental characteristics of air and ground, and proposes a prediction framework for the risk of SF6 high-voltage circuit breaker failure to operate based on integrated air-ground sensing and criticality fuzzy coupled pattern identification. This framework enables rapid and accurate assessment and prediction of multiple levels of SF6 high-voltage circuit breaker failure to operate risk, thereby providing strong support for ensuring the stable operation of the power system.

[0113] It is understood that this embodiment realizes the mapping of multi-factor fuzzy sets to the final membership function of failure to operate risk based on the criticality fuzzy inference model. In this process, the optimized structure of the CDFI model is fully utilized to accurately transform the fuzzy information of each factor into a quantitative representation of failure to operate risk, and finally obtains the failure to operate risk degree that can provide a quantitative basis for the assessment of multi-level failure to operate fault risk of SF6 high voltage circuit breaker.

[0114] It should be understood that the deployment effect of the SF6 high-voltage circuit breaker failure-to-operate risk prediction framework based on integrated air-ground perception and criticality fuzzy coupled pattern identification in this embodiment is as follows: Figure 5 As shown, Figure 5This is a schematic diagram illustrating the deployment effect of the failure-to-operate risk prediction framework in one embodiment. The aerial monitoring platform enables full-area monitoring, the ground-based visual monitoring platform enables local monitoring of the operating modes of various equipment within the substation, and the ground-based sensor monitoring platform enables monitoring of the direct operating physical quantities of the SF6 high-voltage circuit breaker. Specifically, the wide-area monitoring network constructed by the aerial monitoring platform focuses on predicting low-risk failure-to-operate faults in SF6 high-voltage circuit breakers, the local monitoring network constructed by the ground-based visual monitoring focuses on predicting medium-risk failure-to-operate faults in SF6 high-voltage circuit breakers, and the key monitoring network constructed by the ground-based sensor monitoring focuses on predicting high-risk failure-to-operate faults in SF6 high-voltage circuit breakers.

[0115] This embodiment preprocesses historical data of SF6 high-voltage circuit breakers in the target area to obtain multiple spatiotemporal characteristic factors. The historical data is collected through an integrated air-ground sensing system, which includes an airborne data acquisition module and a ground-based data acquisition module. The historical data includes time-dimensional and spatial-dimensional data. The spatiotemporal characteristic factors are mapped to a unified matrix space to construct a spatiotemporal characteristic matrix. This matrix includes multiple historical data samples and their corresponding fault results and spatiotemporal characteristic factors. Based on the spatiotemporal characteristic matrix, a key density function is constructed for each spatiotemporal characteristic factor. Based on the key density function, a key-degree fuzzy inference model is constructed. This key-degree fuzzy inference model quantifies the fuzzy information of the spatiotemporal characteristic factors into a failure-to-operate risk level. Based on this key-degree fuzzy inference model, the failure-to-operate risk of the SF6 high-voltage circuit breakers in the target area is assessed. The invention predicts and obtains the failure-to-operate risk level of each spatiotemporal characteristic factor in the SF6 high-voltage circuit breaker. Because this invention collects historical spatiotemporal data of SF6 high-voltage circuit breakers in the target area through an integrated air-ground sensing system, and preprocesses this data to obtain multiple spatiotemporal characteristic factors, mapping these factors to a unified matrix space, it provides a comprehensive and multi-layered spatiotemporal information foundation for risk prediction. This effectively solves the problem of limited risk prediction due to spatiotemporal constraints. Based on the key density function, a key degree fuzzy inference model is constructed. Through fuzzy inference logic, a scientific and objective analysis of each spatiotemporal characteristic is achieved, accurately quantifying the impact of different spatiotemporal characteristics on the failure-to-operate risk. This is more in line with the complex and ever-changing operating characteristics of the power system, thus significantly improving the accuracy of risk assessment and timely and effectively capturing the potential risks of SF6 high-voltage circuit breakers, thereby providing strong support for ensuring the stable operation of the power system.

[0116] refer to Figure 6 , Figure 6 This is a flowchart illustrating the second embodiment of the SF6 high-voltage circuit breaker failure-to-operate risk prediction method of the present invention.

[0117] Based on the first embodiment described above, in this embodiment, step S40 further includes:

[0118] Step S401: Determine the refusal criticality of each spatiotemporal feature factor based on the critical density function;

[0119] Step S402: Construct an input membership function and an output refusal membership function based on the refusal criticality. The input membership function and the output refusal membership function are constructed based on the trapezoidal membership function form and the triangular membership function form.

[0120] It is understood that this embodiment can perform fuzzification processing based on the structure and operational characteristics of the integrated air-ground sensing platform, mapping the key density function distribution of each spatiotemporal feature factor to four fuzzy sets (see reference). Figure 4 The dividing line in the middle, K is the criticality of refusal to move, reflected in Figure 7 x-axis, Figure 7 (A schematic diagram of the input membership function) is used to obtain the refusal criticality of each spatiotemporal feature factor, thereby establishing the input membership function of each feature.

[0121] It should be understood that this embodiment can fuzzify the refusal criticality of each spatiotemporal feature factor, mapping the clear features in the refusal criticality distribution to the input fuzzy set. The final output multi-level risk fuzzy set of refusal is designed using two sets of trapezoidal and two sets of triangular membership function forms.

[0122] Furthermore, in order to accurately identify potential risks, step S402 above may include:

[0123] Step S4021: Based on the data location type of each spatiotemporal feature factor, perform fuzzification processing on the refusal keyness of each spatiotemporal feature factor, and construct an input membership function based on the fuzzification result. The fuzzification processing includes mapping the refusal keyness of each spatiotemporal feature factor to an input fuzzy set, and the input fuzzy set includes multiple different feature frequency sets.

[0124] Step S4022: Construct fuzzy operation logic rules based on the aforementioned failure-to-operate criticality and the SF6 high-voltage circuit breaker failure-to-operate knowledge base;

[0125] Step S4023: Based on the fuzzy operation logic rules, perform fuzzy classification on the refusal risk and construct an output fuzzy set of multiple levels of refusal risk, wherein the output fuzzy set of multiple levels of refusal risk includes multiple different sets of refusal risk levels;

[0126] Step S4024: Determine the fuzzy mapping relationship between each spatiotemporal feature factor and each risk level set in the output refusal multi-level risk fuzzy set;

[0127] Step S4025: Construct the output rejection membership function based on the fuzzy mapping relationship.

[0128] Understandably, the prediction device fuzzifies the refusal criticality of each spatiotemporal feature factor based on its data location type. Using two sets of trapezoidal and two sets of triangular membership functions, it divides the clear features in the KDF distribution into four input fuzzy sets: sparse, less frequent, common, and frequent. Based on the numerical value of each feature at the time of its occurrence, its criticality at that moment is determined, thus finding its membership degree with respect to each fuzzy set. For example ( The explicit boundary between two adjacent fuzzy sets is determined based on the criticality of each interval in the KDF. Overlapping regions are determined through historical statistical data to fuzzify the explicit boundary, thereby establishing the final input membership function.

[0129] During fuzzification, the input membership functions of each feature factor are localized according to the structure and operational characteristics of the integrated air-ground sensing platform. For wide-area monitoring composed of airborne monitoring platforms, since it can quickly cover the entire area, its prediction interval should mainly focus on low-risk sections, i.e., the constructed fuzzy sets are mainly of two types: sparse and few. For local monitoring composed of ground-based visual monitoring platforms, since it is deployed inside substations and can monitor equipment operating status and emergencies in real time, its prediction interval should mainly focus on medium-risk sections, i.e., the constructed fuzzy sets are mainly of two types: few and normal. For key monitoring composed of ground sensors, since it directly reflects the key physical quantities in the circuit breaker operation process, and failure to operate faults are usually revealed through these key data, its prediction interval should mainly focus on high-risk sections (i.e., the constructed fuzzy sets are mainly of two types: frequent and normal).

[0130] Based on the magnitude of the criticality of circuit breaker refusal to operate under various spatiotemporal characteristics and the expert knowledge of circuit breaker refusal to operate, fuzzy rules are constructed, and fuzzy computation logic is established. Two sets of trapezoidal and two sets of triangular membership functions are used to design the final output multi-level risk fuzzy set for refusal to operate: low risk, medium risk, high risk, and extremely high risk, corresponding to output refusal to operate membership functions with values ​​of 0.15, 0.35, 0.65, and 1.00, respectively. The output refusal to operate membership functions are as follows: Figure 8 As shown, Figure 8 This is a schematic diagram of the output rejection membership function in one embodiment.

[0131] Step S403: Construct a multi-factor fuzzy inference framework based on the input membership function and the output rejection membership function.

[0132] In its implementation, the predictive equipment constructs fuzzy rules based on the criticality of refusal to operate under various spatiotemporal characteristics and expert knowledge of circuit breaker refusal to operate. It establishes fuzzy computation logic and designs the final output multi-level risk fuzzy set of refusal to operate (e.g., low risk, medium risk, high risk, and extremely high risk, corresponding to output refusal to operate membership functions with values ​​of 0.15, 0.35, 0.65, and 1.00, respectively) using two sets of trapezoidal and two sets of triangular membership functions. This determines the final multi-factor fuzzy inference framework reflecting the risk of refusal to operate.

[0133] Step S404: Optimize the logical operation process in the multi-factor fuzzy inference framework by organizing it in a hierarchical structure to construct hierarchical fuzzy rules;

[0134] Step S405: Construct a key-degree fuzzy inference model based on the hierarchical fuzzy rules.

[0135] It is understood that this embodiment, based on a hierarchical reasoning architecture, optimizes the logical operation process in the constructed multi-factor fuzzy reasoning framework by organizing it in a hierarchical structure (see reference). Figure 9 Operational logic, Figure 9 (A schematic diagram of the operation flow of the key-degree fuzzy inference model) establishes hierarchical fuzzy rules to construct the CDFI model, thereby reducing the computational complexity from that of the traditional MHR. Reduced to This significantly reduces the consumption of computing resources and computation time. It greatly improves the model's efficiency when processing large amounts of real-time data, thus better meeting the stringent requirements for real-time performance and accuracy in predicting the risk of SF6 high-voltage circuit breaker failure to operate. The hierarchical fuzzy rules are shown in Table 1:

[0136] Table 1, Hierarchical Fuzzy Rules

[0137]

[0138] Furthermore, in order to provide reliable quantitative assessment results and output accurate risk indicators, the keyness fuzzy inference model is configured to calculate the refusal keyness of the input spatiotemporal feature factors based on the key density function, and to fuzzify the refusal keyness of the spatiotemporal feature factors to obtain the fuzzy information of the spatiotemporal feature factors.

[0139] The key-degree fuzzy inference model is further configured to defuzzify the fuzzy information based on the centroid method, and output the refusal risk degree of the spatiotemporal feature factor, as shown in the following formula:

[0140]

[0141] in, Indicates the first The risk level of action of the spatiotemporal characteristic factors of the input group. Indicates the first Spatiotemporal feature factors of the input group This represents the total number of fuzzy sets that overlap after the input features are fuzzified. Indicates the first Membership function of a fuzzy set Representing fuzzy sets Elements in the domain of discourse.

[0142] It should be noted that, based on the optimized key-degree fuzzy inference model, the mapping from multi-factor fuzzy sets to the final refusal-to-move risk membership function is achieved, referring to... Figure 9 In this process, the optimized structure of the CDFI model is fully utilized to accurately transform the fuzzy information of each factor (corresponding to the input features in Table 1) into an output membership function representation of the failure-to-operate risk. Subsequently, defuzzification is performed based on the centroid method, ultimately obtaining the failure-to-operate risk level (reference) that can provide a quantitative basis for assessing the multi-level failure-to-operate fault risk of SF6 high-voltage circuit breakers. Figure 10 Deblurring process, Figure 10 (Flowchart for defuzzifying and solving the refusal-to-move risk level). Based on the principle of reliability first and low trust level, the judgment criterion is: high risk (refusal-to-move risk level). Medium risk Risk of refusal to move Low risk Risk of refusal to move ).

[0143] This embodiment determines the criticality of each spatiotemporal characteristic factor for failure to operate based on the critical density function. Based on this criticality, it constructs input and output membership functions for failure to operate, using trapezoidal and triangular membership functions, respectively. A multi-factor fuzzy inference framework is then built based on these functions. The logical operation process within this framework is optimized using a hierarchical structure to construct hierarchical fuzzy rules. A criticality fuzzy inference model is then built based on these rules. Because this embodiment employs fuzzy inference logic, it achieves a scientific and objective analysis of each spatiotemporal characteristic. By constructing a multi-factor fuzzy inference framework based on the critical density function, which reflects the contribution of failure to operate, it more accurately quantifies the impact of different spatiotemporal characteristics on failure to operate risk. Compared to traditional deterministic analysis methods, this approach better reflects the complex and variable operating characteristics of power systems, thus significantly improving the accuracy of risk assessment.

[0144] In some embodiments, in order to verify the effect of the present invention, a regional substation network (including 110KV substations, wind power plants, photovoltaic power plants, thermal power plants, etc.) is selected as an example test system, and real-time fault records of SF6 circuit breaker failure to operate are collected for three years.

[0145] To comprehensively verify the performance of the constructed model, this invention integrates two pattern recognition performance metrics—Receiver Operating Characteristic (ROC) curves and Precision-Recall (PR) curves—to validate the failure-to-operate fault identification results. In both ROC and PR curves, the Area Under the Curve (AUC) is introduced as a standard for evaluating the quality of the identification model's prediction results. A higher AUC value indicates superior prediction performance, reflected in the ROC curve as being closer to the upper left of the image; and in the PR curve as being closer to the upper right of the image. Furthermore, the improvement effects of the CDFI constructed in this invention are compared with those of standard explicit set prediction models (Support Vector Machine (SVM), Backpropagation Neural Network (BPNN)) and initial models (Probability Density-Fuzzy Hierarchical Inference PDF-DFI, Probability Density-Multi-Factor Holistic Inference PDF-MHR). Finally, the prediction model constructed in this invention is used to predict the failure-to-operate fault risk of an SF6 high-voltage circuit breaker in a substation, and the prediction results are visualized. Figure 11 As shown, Figure 11 The visualization results of the refusal-to-operate risk prediction are shown, where brighter colors within the prediction interval indicate a higher refusal-to-operate risk. Figures 12(a), 12(b), 13(a), and 13(b) show that Figures 12(a) and 12(b) are comparison charts of the ROC curve for SF6 refusal-to-operate fault, and Figures 13(a) and 13(b) are comparison charts of the PR curve for SF6 refusal-to-operate fault. When using multi-dimensional spatiotemporal characteristics of air and ground as input data, the AUC value of the CDFI model is significantly higher than other pattern recognition models when compared with the standard explicit set model and the initial model.

[0146] This result fully demonstrates that the CDFI model constructed in this invention has superior performance in predicting SF6 high-voltage circuit breaker failure to operate. Specifically, in terms of AUC (ROC), the score is improved by 28.6% compared to the standard explicit set model SVM, and by 19.34% compared to BPNN. Compared with the initial model, there are performance improvements of 21% (compared to PDF-DFI) and 23% (compared to PDF-MHR). In terms of AUC (PR), compared with the standard explicit set models SVM and BPNN, the scores are improved by 25.1% and 17.1%, respectively; compared with the initial models PDF-DFI and PDF-MHR, the scores are improved by 15.5% and 19.2%, respectively.

[0147] Depend on Figure 14 It can be seen that, Figure 14 The chart shows a comparison of the speed of SF6 failure to operate faults. The CDFI model significantly outperforms other comparative models. Under the same hardware environment, the running times of each model are: 11 seconds (SVM), 14.23 seconds (BPNN), 12.54 seconds (PDF-MHR), 5.31 seconds (PDF-DFI), and 5.2 seconds (CDFI). Specifically, the CDFI model reduces the time required by 52.7% and 63.5% compared to the standard explicit set models SVM and BPNN, respectively, and by 2.5% and 58.5% compared to the initial models PDF-DFI and PDF-MHR, respectively. This efficient computational speed allows the model to maintain high-accuracy predictions while rapidly responding to system changes, thus enabling real-time early warning.

[0148] The above data strongly confirms that the model of this invention has stronger fault identification capabilities and calculation speed when predicting SF6 high-voltage circuit breaker failure to operate, and can provide technical support for real-time and accurate prediction of future failure to operate risk levels in complex real-world environments.

[0149] The comparison of AUC parameters for each model is shown in Table 2:

[0150] Table 2, Comparison of AUC for each model

[0151]

[0152] Understandably, the predictive framework of this invention comprehensively integrates multi-source data from the air and ground through air-ground integrated sensing technology, effectively overcoming the limitation of traditional predictive methods that rely on a single data source. This multi-dimensional data collection approach provides a comprehensive and multi-layered information foundation for risk prediction, greatly improving the accuracy and applicability of the predictive model.

[0153] In the data processing stage, this invention employs fuzzy reasoning logic, rather than using definite sets for subjective discretization of continuous features, thus achieving a scientific and objective analysis of various spatiotemporal features. Furthermore, compared to the PDF used in traditional methods, this invention designs multi-level risk fuzzy sets based on KDF, which reflects the contribution of failure-to-operate faults, enabling more precise quantification of the impact of different spatiotemporal features on failure-to-operate risk. Compared to traditional deterministic analysis methods, this approach better reflects the complex and variable operating characteristics of power systems, thereby significantly improving the accuracy of risk assessment.

[0154] The prediction framework constructed in this invention exhibits superior performance in both prediction accuracy and computational efficiency. The CDFI model, based on an optimized and improved hierarchical reasoning architecture, can rapidly output accurate prediction results of failure-to-operate risk while processing large amounts of data, meeting the requirements for efficient and real-time prediction and making it suitable for modern power systems with high sensing requirements. This model effectively solves the problems of high complexity, long computation time, and high resource consumption that often exist in MHR (Multiple-factor Holistic Reasoning) when dealing with large amounts of complex data, significantly improving the system's computational efficiency and response speed.

[0155] Furthermore, this embodiment of the invention also proposes a computer-readable storage medium storing an SF6 high-voltage circuit breaker failure-to-operate risk prediction program. When the SF6 high-voltage circuit breaker failure-to-operate risk prediction program is executed by a processor, it implements the steps of the SF6 high-voltage circuit breaker failure-to-operate risk prediction method described above.

[0156] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0157] The aforementioned computer-readable storage medium may be included in the SF6 high-voltage circuit breaker failure-to-operate risk prediction device; or it may exist independently and not be assembled into the SF6 high-voltage circuit breaker failure-to-operate risk prediction device.

[0158] Furthermore, this invention also proposes a computer program product, including an SF6 high-voltage circuit breaker failure-to-operate risk prediction program, which, when executed by a processor, implements the steps of the SF6 high-voltage circuit breaker failure-to-operate risk prediction method as described above.

[0159] The specific implementation of the computer program product of the present invention is basically the same as the embodiments of the above-mentioned SF6 high-voltage circuit breaker failure to operate risk prediction method, and will not be repeated here.

[0160] Reference Figure 15 , Figure 15 This is a structural block diagram of the first embodiment of the SF6 high-voltage circuit breaker failure-to-operate risk prediction device of the present invention.

[0161] like Figure 15 As shown, the SF6 high-voltage circuit breaker failure-to-operate risk prediction device proposed in this embodiment of the invention includes:

[0162] Data processing module 10 is used to preprocess the historical data of SF6 high-voltage circuit breakers in the target area to obtain multiple spatiotemporal characteristic factors. The historical data is collected through an air-ground integrated sensing system, which includes an air-based data acquisition module and a ground-based data acquisition module. The historical data includes time dimension data and spatial dimension data.

[0163] The feature mapping module 20 is used to map the spatiotemporal feature factors to a unified matrix space to construct a spatiotemporal feature matrix. The spatiotemporal feature matrix includes multiple historical records and the fault results and spatiotemporal feature factors corresponding to each historical record.

[0164] Key density function module 30 is used to construct key density functions for each spatiotemporal feature factor based on the spatiotemporal feature matrix;

[0165] The model building module 40 is used to build a key degree fuzzy inference model based on the key density function. The key degree fuzzy inference model is used to quantify the fuzzy information of spatiotemporal feature factors into a refusal risk degree.

[0166] The risk prediction module 50 is used to predict the failure to operate risk of SF6 high-voltage circuit breakers in the target area based on the criticality fuzzy inference model, and to obtain the failure to operate risk degree of each spatiotemporal characteristic factor in the SF6 high-voltage circuit breaker.

[0167] This embodiment preprocesses historical data of SF6 high-voltage circuit breakers in the target area to obtain multiple spatiotemporal characteristic factors. The historical data is collected through an integrated air-ground sensing system, which includes an airborne data acquisition module and a ground-based data acquisition module. The historical data includes time-dimensional and spatial-dimensional data. The spatiotemporal characteristic factors are mapped to a unified matrix space to construct a spatiotemporal characteristic matrix. This matrix includes multiple historical data samples and their corresponding fault results and spatiotemporal characteristic factors. Based on the spatiotemporal characteristic matrix, a key density function is constructed for each spatiotemporal characteristic factor. Based on the key density function, a key-degree fuzzy inference model is constructed. This key-degree fuzzy inference model quantifies the fuzzy information of the spatiotemporal characteristic factors into a failure-to-operate risk level. Based on this key-degree fuzzy inference model, the failure-to-operate risk of the SF6 high-voltage circuit breakers in the target area is assessed. The invention predicts and obtains the failure-to-operate risk level of each spatiotemporal characteristic factor in the SF6 high-voltage circuit breaker. Because this invention collects historical spatiotemporal data of SF6 high-voltage circuit breakers in the target area through an integrated air-ground sensing system, and preprocesses this data to obtain multiple spatiotemporal characteristic factors, mapping these factors to a unified matrix space, it provides a comprehensive and multi-layered spatiotemporal information foundation for risk prediction. This effectively solves the problem of limited risk prediction due to spatiotemporal constraints. Based on the key density function, a key degree fuzzy inference model is constructed. Through fuzzy inference logic, a scientific and objective analysis of each spatiotemporal characteristic is achieved, accurately quantifying the impact of different spatiotemporal characteristics on the failure-to-operate risk. This is more in line with the complex and ever-changing operating characteristics of the power system, thus significantly improving the accuracy of risk assessment and timely and effectively capturing the potential risks of SF6 high-voltage circuit breakers, thereby providing strong support for ensuring the stable operation of the power system.

[0168] The SF6 high-voltage circuit breaker failure-to-operate risk prediction device provided in this application adopts the SF6 high-voltage circuit breaker failure-to-operate risk prediction method in the above embodiments, and can solve the technical problem of SF6 high-voltage circuit breaker failure-to-operate risk prediction. Compared with the prior art, the beneficial effects of the SF6 high-voltage circuit breaker failure-to-operate risk prediction device provided in this application are the same as the beneficial effects of the SF6 high-voltage circuit breaker failure-to-operate risk prediction method provided in the above embodiments, and other technical features in the SF6 high-voltage circuit breaker failure-to-operate risk prediction device are the same as the features disclosed in the methods of the above embodiments, and will not be repeated here.

[0169] It should be understood that the above are merely illustrative examples and do not constitute any limitation on the technical solutions of the present invention. In specific applications, those skilled in the art can make settings as needed, and the present invention does not impose any restrictions on this.

[0170] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of this invention. In practical applications, those skilled in the art can select some or all of the workflow to achieve the purpose of this embodiment according to actual needs, and no restrictions are imposed here.

[0171] In addition, for technical details not described in detail in this embodiment, please refer to the SF6 high-voltage circuit breaker failure-to-operate risk prediction method provided in any embodiment of the present invention, which will not be repeated here.

[0172] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0173] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0174] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as read-only memory / random access memory, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0175] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A method for predicting the risk of SF6 high-voltage circuit breaker failure to operate, characterized in that, The method for predicting the risk of SF6 high-voltage circuit breaker failure to operate includes: The historical data of SF6 high-voltage circuit breakers in the target area are preprocessed to obtain multiple spatiotemporal characteristic factors. The historical data is collected by an air-ground integrated sensing system, which includes an air-based data acquisition module and a ground-based data acquisition module. The historical data includes time dimension data and spatial dimension data. The spatiotemporal feature factors are mapped to a unified matrix space to construct a spatiotemporal feature matrix, which includes multiple historical records and the fault results and spatiotemporal feature factors corresponding to each historical record. Based on the spatiotemporal feature matrix, the probability density function of each spatiotemporal feature factor is generated, and the fault correlation information between each spatiotemporal feature factor and the failure to operate fault, as well as the severity information of the failure to operate fault, are determined. The fault contribution weight and severity weight of each spatiotemporal characteristic factor are determined based on the fault association information and the fault severity information. Based on the probability density function, the fault contribution weight, and the severity weight, a key density function is constructed for each spatiotemporal characteristic factor. The key density function describes the weight of continuous random variables in each value interval that influences the occurrence of faults. The mathematical expression of the key density function is as follows: in, Represents spatiotemporal characteristic factors The key to the refusal to move. Represents spatiotemporal characteristic factors The probability density function value, which represents the frequency of occurrence of spatiotemporal characteristic factors under different states. Indicates the fault contribution weight. Indicates severity weight; The criticality of each spatiotemporal characteristic factor is determined based on the critical density function. Based on the aforementioned refusal criticality, an input membership function and an output refusal membership function are constructed. The input membership function and the output refusal membership function are constructed based on trapezoidal membership function form and triangular membership function form, respectively. A multi-factor fuzzy reasoning framework is constructed based on the input membership function and the output rejection membership function; The logical operation process in the multi-factor fuzzy reasoning framework is optimized by organizing it in a hierarchical structure to construct hierarchical fuzzy rules; Based on the hierarchical fuzzy rules, a key degree fuzzy inference model is constructed. The key degree fuzzy inference model is used to quantify the fuzzy information of spatiotemporal feature factors into a refusal risk degree. Based on the criticality fuzzy inference model, the failure-to-operate risk prediction of SF6 high-voltage circuit breakers in the target area is performed to obtain the failure-to-operate risk degree of each spatiotemporal characteristic factor in the SF6 high-voltage circuit breaker.

2. The method for predicting the risk of SF6 high-voltage circuit breaker failure to operate as described in claim 1, characterized in that, The construction of the input membership function and the output membership function based on the refusal-to-move criticality includes: Based on the data location type of each spatiotemporal feature factor, the refusal keyness of each spatiotemporal feature factor is fuzzified, and an input membership function is constructed based on the fuzzification result. The fuzzification process includes mapping the refusal keyness of each spatiotemporal feature factor to an input fuzzy set, and the input fuzzy set includes multiple different feature frequency sets. Based on the aforementioned failure-to-operate criticality and the SF6 high-voltage circuit breaker failure-to-operate knowledge base, fuzzy operation logic rules are constructed. Based on the fuzzy operation logic rules, the risk of refusal to act is fuzzy classified, and a fuzzy set of output refusal to act multi-level risk is constructed. The fuzzy set of output refusal to act multi-level risk includes multiple different sets of refusal risk levels. Determine the fuzzy mapping relationship between each spatiotemporal feature factor and each risk level set in the output refusal multi-level risk fuzzy set; The output rejection membership function is constructed based on the fuzzy mapping relationship.

3. The SF6 high-voltage circuit breaker failure-to-operate risk prediction method as described in claim 2, characterized in that, The keyness fuzzy inference model is configured to calculate the refusal keyness of the spatiotemporal feature factors based on the key density function, and to fuzzify the refusal keyness of the spatiotemporal feature factors to obtain the fuzzy information of the spatiotemporal feature factors. The key-degree fuzzy inference model is further configured to defuzzify the fuzzy information based on the centroid method, and output the refusal risk degree of the spatiotemporal feature factor, as shown in the following formula: in, Indicates the first The risk of refusal to move based on the spatiotemporal characteristic factors of the input group. Indicates the first Spatiotemporal feature factors of the input group This represents the total number of fuzzy sets that overlap after the input features are fuzzified. Indicates the first Membership function of a fuzzy set Representing fuzzy sets Elements in the domain of discourse.

4. The method for predicting the risk of SF6 high-voltage circuit breaker failure to operate as described in claim 1, characterized in that, The historical data of SF6 high-voltage circuit breakers in the target area are preprocessed to obtain multiple spatiotemporal characteristic factors, including: The historical data of SF6 high-voltage circuit breakers in the target area are cleaned using a linear interpolation strategy to obtain initial feature factors. The initial feature factors are normalized to obtain multiple spatiotemporal feature factors.

5. A device for predicting the risk of SF6 high-voltage circuit breaker failure to operate, characterized in that, The device employs the SF6 high-voltage circuit breaker failure-to-operate risk prediction method according to any one of claims 1 to 4, and the SF6 high-voltage circuit breaker failure-to-operate risk prediction device comprises: The data processing module is used to preprocess the historical data of SF6 high-voltage circuit breakers in the target area to obtain multiple spatiotemporal characteristic factors. The historical data is collected through an air-ground integrated sensing system, which includes an air-based data acquisition module and a ground-based data acquisition module. The historical data includes time dimension data and spatial dimension data. The feature mapping module is used to map the spatiotemporal feature factors to a unified matrix space to construct a spatiotemporal feature matrix. The spatiotemporal feature matrix includes multiple historical records and the fault results and spatiotemporal feature factors corresponding to each historical record. The key density function module is used to construct key density functions for each spatiotemporal feature factor based on the spatiotemporal feature matrix. The model building module is used to build a key degree fuzzy inference model based on the key density function. The key degree fuzzy inference model is used to quantify the fuzzy information of spatiotemporal feature factors into a refusal risk degree. The risk prediction module is used to predict the failure to operate risk of SF6 high-voltage circuit breakers in the target area based on the criticality fuzzy inference model, and to obtain the failure to operate risk degree of each spatiotemporal characteristic factor in the SF6 high-voltage circuit breaker.

6. A device for predicting the risk of SF6 high-voltage circuit breaker failure to operate, characterized in that, The SF6 high-voltage circuit breaker failure-to-operate risk prediction device includes: a memory, a processor, and an SF6 high-voltage circuit breaker failure-to-operate risk prediction program stored in the memory and executable on the processor. The SF6 high-voltage circuit breaker failure-to-operate risk prediction program is configured to implement the SF6 high-voltage circuit breaker failure-to-operate risk prediction method as described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores an SF6 high-voltage circuit breaker failure-to-operate risk prediction program, which, when executed by a processor, implements the SF6 high-voltage circuit breaker failure-to-operate risk prediction method as described in any one of claims 1 to 4.

8. A computer program product, characterized in that, The computer program product includes an SF6 high-voltage circuit breaker failure-to-operate risk prediction program, which, when executed by a processor, implements the steps of the SF6 high-voltage circuit breaker failure-to-operate risk prediction method as described in any one of claims 1 to 4.

Images