A method and system for risk level classification of a power grid region

Abstract

The application discloses a power grid region risk grade division method and system, and belongs to the technical field of power grid disaster loss early warning. The method is as follows: a target monitoring power grid is divided, a plurality of space grids are obtained, and standard meteorological feature data, standard power equipment data and standard historical disaster loss data corresponding to each space grid are obtained; meteorological risk indexes, equipment exposure indexes, equipment vulnerability indexes and disaster loss prediction probabilities of each space grid are obtained based on the above data; the above data are multi-dimensionally fused to obtain comprehensive disaster loss risk indexes of each space grid, and the comprehensive disaster loss risk indexes of each space grid are divided into risk grades to determine the risk grades of each space grid. The power grid region risk grade division method provided by the application can fuse multi-dimensional disaster loss indexes of power grid equipment to construct comprehensive disaster loss risk indexes of each region of the power grid, and realize division of disaster loss risks of each region of the power grid.

Description

Technical Field

[0001] This invention relates to the field of power grid disaster early warning technology, and in particular to a method and system for classifying the risk level of a power grid area. Background Technology

[0002] With the increasing frequency of extreme weather events such as typhoons, rainstorms, severe convection, high temperatures, and freezing temperatures, the risk of damage to power equipment is constantly increasing. Power facilities such as transmission lines, substations, towers, and distribution equipment are exposed to the natural environment for extended periods, making their operational safety susceptible to meteorological factors such as wind speed, rainfall, temperature, thunderstorms, and icing. To improve the power grid's disaster prevention and mitigation capabilities, several mainstream technical solutions have emerged, relying on meteorological forecasts, equipment monitoring records, and historical fault records for risk warning and assessment. The first type is the power grid risk assessment method based on meteorological warnings. This method typically utilizes information such as typhoon paths, rainstorm warnings, strong wind warnings, high temperature warnings, and freezing warnings issued by meteorological departments to manually assess the operational risks of the power grid. For example, when a strong wind, rainstorm, or freezing weather warning is issued for a certain area, maintenance personnel, based on experience, judge that the power equipment in that area may have a high risk of failure and arrange for inspections or emergency deployment. The second category is power grid disaster risk assessment methods based on historical fault statistics. These methods primarily rely on historical fault records, disaster event records, and equipment operation logs to statistically analyze the frequency of fault occurrence in different regions and for different equipment types under severe weather conditions, thereby establishing regional or equipment risk levels. The third category is risk threshold judgment methods based on single meteorological factors. These methods typically set thresholds based on single or a few meteorological indicators such as wind speed, rainfall, temperature, and icing thickness. When a meteorological indicator exceeds a set threshold, the corresponding region or equipment is deemed to have a high risk. For example, wind speed exceeding a certain threshold indicates a risk of transmission line collapse or line breakage, while rainfall exceeding a certain threshold indicates a high risk for mountain lines or distribution equipment. The fourth category is risk visualization methods based on GIS maps. These methods typically overlay meteorological warning information, power grid equipment locations, and historical fault locations onto a GIS map, using different colors, point markings, or area labels to display the risk distribution, providing visual assistance for power grid dispatching and maintenance. The fifth category is machine learning-based equipment failure or disaster prediction methods. These methods typically use historical equipment operation data, environmental data, and fault labels to train classification or regression models to predict the probability or severity of future equipment failures.

[0003] Under the current technological background, although the above-mentioned risk assessment methods can provide assistance to power grid disaster prevention and mitigation to a certain extent, relying solely on a single meteorological dimension to determine the risk of the power grid cannot directly convert the intensity of meteorological warnings into the actual disaster risk of power equipment. Furthermore, they do not incorporate multi-dimensional evaluation factors such as equipment exposure scale and equipment vulnerability, and cannot quantify the disaster risk level of different areas of the power grid, thus leading to distorted risk assessment results. Summary of the Invention

[0004] This invention aims to provide a method and system for classifying the risk level of power grid areas, in order to solve the above-mentioned technical problems, avoid the distortion of risk assessment results caused by judging the disaster risk of power grid based on only a single dimension, and integrate multi-dimensional disaster risk indicators of power grid equipment to construct a comprehensive disaster risk index for each area of ​​the power grid, thereby realizing the classification of disaster risk in each area of ​​the power grid.

[0005] To address the aforementioned technical problems, this invention provides a method for classifying risk levels in power grid areas, comprising: The target monitoring power grid is divided into several spatial grids, and standard meteorological characteristic data, standard power equipment data, and standard historical disaster loss data corresponding to each spatial grid are obtained. Based on the standard meteorological characteristic data, standard power equipment data, and standard historical disaster damage data corresponding to each spatial grid, we obtain the following for each spatial grid: meteorological risk index, power equipment importance weight, power equipment vulnerability weight, meteorological risk index, equipment exposure index, and equipment vulnerability index. The disaster loss prediction probability of each spatial grid is calculated based on the risk index of several meteorological factors corresponding to each spatial grid, the importance weight of several power equipment corresponding to each spatial grid, the vulnerability weight of several power equipment corresponding to each spatial grid, and the importance weight of several power equipment corresponding to each spatial grid. The meteorological hazard index, equipment exposure index, equipment vulnerability index, and disaster loss prediction probability of each spatial grid are multidimensionally integrated to obtain the comprehensive disaster loss risk index of each spatial grid. The comprehensive disaster loss risk index of each spatial grid is then classified into risk levels to determine the risk level of each spatial grid.

[0006] In the aforementioned scheme, the meteorological hazard index, equipment exposure index, and equipment vulnerability index of each spatial grid are obtained by using standard meteorological characteristic data, standard power equipment data, and standard historical disaster damage data corresponding to each spatial grid. This provides quantitative indicators for subsequent multi-dimensional comprehensive assessment of power grid disaster damage risk. Next, by combining the hazard indices of several meteorological factors, the importance weights of several power equipment, the vulnerability weights of several power equipment, and the importance weights of several power equipment corresponding to each spatial grid, the disaster damage prediction probability of each spatial grid is calculated. This further enriches the multi-dimensional indicators for power grid regional risk assessment, avoiding the distortion of risk assessment results caused by judging power grid disaster damage risk based on only a single dimension. Then, by multi-dimensional fusion, the comprehensive disaster damage risk index of each spatial grid is obtained, and the risk level of the comprehensive disaster damage risk index of each spatial grid is classified. This allows for the integration of multi-dimensional disaster damage indicators of power grid equipment to construct a comprehensive disaster damage risk index for each region of the power grid, realizing the classification of disaster damage risk in each region of the power grid and determining the risk level of each spatial grid.

[0007] Furthermore, the process of dividing the target monitoring power grid into several spatial grids and acquiring standard meteorological characteristic data, standard power equipment data, and standard historical disaster damage data corresponding to each spatial grid includes: Acquire several initial multi-source meteorological data, several initial power equipment data, and several initial historical disaster damage data of the target power grid; Outlier removal and missing value filling are performed on several initial multi-source meteorological data, several initial power equipment data and several initial historical disaster damage data to obtain several preprocessed multi-source meteorological data, several preprocessed power equipment data and several preprocessed historical disaster damage data; Spatiotemporal scale unification and normalization processing are performed on several preprocessed multi-source meteorological data, several preprocessed power equipment data and several preprocessed historical disaster damage data to obtain several standard multi-source meteorological data, several standard power equipment data and several standard historical disaster damage data. The target monitoring power grid is divided into several spatial grids; Several standard multi-source meteorological data, several standard power equipment data, and several standard historical disaster loss data are mapped to several spatial grids to obtain the standard meteorological feature data, standard power equipment data, and standard historical disaster loss data corresponding to each spatial grid.

[0008] In the above scheme, by acquiring several initial multi-source meteorological data, several initial power equipment data, and several initial historical disaster damage data of the target monitoring power grid, the original data sources can be provided for subsequent standardization processing and risk assessment. Next, through outlier removal and missing value imputation, the assessment interference caused by erroneous or missing data in the original data can be eliminated, resulting in several preprocessed multi-source meteorological data, several preprocessed power equipment data, and several preprocessed historical disaster damage data. Then, by unifying the spatiotemporal scale of various types of data and performing normalization processing, the problem of inconsistent dimensions caused by different data formats can be eliminated, resulting in several standard multi-source meteorological data, several standard power equipment data, and several standard historical disaster damage data that can be uniformly calculated and used. Subsequently, by dividing the target monitoring power grid, a large-scale target monitoring power grid can be divided into several spatial grids, enabling refined risk assessment by region. Finally, by matching the three types of standardized data one by one to the corresponding spatial grids, data support is provided for the subsequent calculation of multi-dimensional risk indicators.

[0009] Furthermore, the acquisition of several meteorological factor hazard indices, several power equipment importance weights, several power equipment vulnerability weights, meteorological hazard indices, equipment exposure indices, and equipment vulnerability indices for each spatial grid based on standard meteorological characteristic data, standard power equipment data, and standard historical disaster damage data corresponding to each spatial grid includes: Based on the standard meteorological characteristic data corresponding to each spatial grid, the risk index of several meteorological factors corresponding to each spatial grid is obtained, and the meteorological risk index of each spatial grid is obtained based on the risk index of several meteorological factors corresponding to each spatial grid. Based on the standard power equipment data corresponding to each spatial grid, the importance weights of several power equipment corresponding to each spatial grid are determined, and the standard power equipment data corresponding to each spatial grid and the importance weights of several power equipment corresponding to each spatial grid are weighted and fused to obtain the equipment exposure index of each spatial grid. Based on the standard historical disaster damage data corresponding to each spatial grid, the vulnerability weights of several power equipment corresponding to each spatial grid are determined, and the equipment vulnerability index of each spatial grid is obtained based on the vulnerability weights and importance weights of several power equipment corresponding to each spatial grid.

[0010] In the above scheme, several meteorological factor hazard indices are calculated for each spatial grid using standard meteorological characteristic data. These indices are then integrated to obtain the meteorological hazard index for each spatial grid. This quantifies the threat posed by meteorological disasters occurring in each spatial grid, supplementing meteorological dimension assessment indicators and avoiding reliance solely on qualitative weather descriptions to determine the disaster risk of different areas of the power grid. Next, by determining the importance weights of several power equipment corresponding to each spatial grid, the scheme avoids treating all power equipment in the region as equally important. The equipment exposure index for each spatial grid is calculated based on these importance weights, providing foundational data for obtaining the comprehensive disaster risk index of each spatial grid through multi-dimensional fusion. Finally, the vulnerability weights of power equipment are determined using standard historical disaster data for each spatial grid. This quantifies the susceptibility of power equipment within the grid to disaster damage. The equipment vulnerability index for each spatial grid is calculated based on these importance weights, providing foundational data for obtaining the comprehensive disaster risk index of each spatial grid through multi-dimensional fusion and eliminating the distortion caused by a single meteorological dimension assessment.

[0011] Further, the step of obtaining several meteorological factor hazard indices corresponding to each spatial grid based on the standard meteorological characteristic data corresponding to each spatial grid, and obtaining the meteorological hazard index of each spatial grid based on the several meteorological factor hazard indices corresponding to each spatial grid, includes: Based on the preset first threshold set and the preset second threshold set of meteorological factors, the standard meteorological characteristic data corresponding to each spatial grid are normalized to obtain the risk index of several meteorological factors corresponding to each spatial grid. The meteorological hazard index of each spatial grid is obtained by weighting and fusing several meteorological hazard indices corresponding to each spatial grid based on a preset meteorological factor weight set.

[0012] In the above scheme, the standard meteorological characteristic data corresponding to each spatial grid are normalized by pre-setting a first set of meteorological factor thresholds and a second set of meteorological factor thresholds. This unifies the numerical range of various meteorological data and enables comparison of the intensity of different types of meteorological disasters. Next, by weighting and fusing the risk indices of several meteorological factors corresponding to each spatial grid according to a pre-set set of meteorological factor weights, multiple meteorological disaster-causing factors can be integrated to obtain the meteorological risk index of each spatial grid, comprehensively quantifying the degree of threat posed by meteorological disasters to each spatial grid.

[0013] Further, the step of determining the importance weights of several power devices corresponding to each spatial grid based on the standard power device data corresponding to each spatial grid, and weighting and fusing the standard power device data and the importance weights of several power devices corresponding to each spatial grid to obtain the device exposure index of each spatial grid includes: Based on the preset equipment type table, the standard power equipment data corresponding to each spatial grid is matched to obtain the importance weights of several power equipment corresponding to each spatial grid; The standard power equipment data corresponding to each spatial grid and the importance weights of several power equipment corresponding to each spatial grid are weighted and fused to obtain the equipment exposure index of each spatial grid.

[0014] In the above scheme, by calling a preset equipment type table to match each power device within the grid, the importance weights of several power devices corresponding to each spatial grid can be obtained, thus quantifying the importance of power devices. Next, by weighted fusion of the standard power device data corresponding to each spatial grid and the several power device importance weights corresponding to each spatial grid, it is possible to avoid evaluating all power devices as objects of equal risk, thereby obtaining the equipment exposure index for each spatial grid.

[0015] Furthermore, the process of determining the vulnerability weights of several power equipment corresponding to each spatial grid based on the standard historical disaster loss data corresponding to each spatial grid, and obtaining the equipment vulnerability index of each spatial grid based on the vulnerability weights and importance weights of several power equipment corresponding to each spatial grid, includes: Based on a preset set of equipment status weights, the standard historical disaster damage data corresponding to each spatial grid is matched to obtain several power equipment vulnerability weights corresponding to each spatial grid. The importance weights and vulnerability weights of several power equipment corresponding to each spatial grid are weighted and fused to obtain the equipment vulnerability index of each spatial grid.

[0016] In the above scheme, by matching the standard historical disaster damage data corresponding to each spatial grid with a preset set of equipment status weights, the vulnerability weight of each power device can be determined, quantifying the degree to which different power devices are easily damaged under disasters. Then, by weighted fusion of the importance weights and vulnerability weights of several power devices corresponding to each spatial grid, the scheme avoids evaluating all power devices as objects of equal risk, thus obtaining the equipment vulnerability index for each spatial grid.

[0017] Furthermore, the calculation of the disaster loss prediction probability for each spatial grid based on the risk index of several meteorological factors corresponding to each spatial grid, the importance weight of several power equipment corresponding to each spatial grid, the vulnerability weight of several power equipment corresponding to each spatial grid, and the importance weight of several power equipment corresponding to each spatial grid includes: Based on the hazard index of several meteorological factors corresponding to each spatial grid, the importance weight of several power equipment corresponding to each spatial grid, and the vulnerability weight of several power equipment corresponding to each spatial grid, a multidimensional feature of several power equipment corresponding to each spatial grid is constructed. Based on the preset disaster loss prediction model and the multi-dimensional features of several power equipment corresponding to each spatial grid, the disaster loss probability of several power equipment corresponding to each spatial grid is obtained. The importance weights of several power equipment corresponding to each spatial grid and the disaster loss probabilities of several power equipment corresponding to each spatial grid are weighted and fused to obtain the disaster loss prediction probability of each spatial grid.

[0018] In the above scheme, multi-dimensional features of power equipment corresponding to each spatial grid are constructed by using several meteorological risk indices, importance weights, and vulnerability weights of power equipment corresponding to each spatial grid. This allows multiple risk factors to be integrated into data that can be identified by the pre-set disaster loss prediction model. Then, by weighted fusion of the importance weights and disaster loss probabilities of power equipment corresponding to each spatial grid, the disaster loss probability of a single power equipment can be converted into the disaster loss prediction probability of the entire grid.

[0019] This invention provides a risk level classification system for power grid areas, including a power grid data acquisition module, a multi-dimensional risk indicator calculation module, a grid disaster loss prediction probability calculation module, and a risk level classification module, specifically: The power grid data acquisition module is used to divide the target monitoring power grid, acquire several spatial grids, and acquire standard meteorological characteristic data, standard power equipment data, and standard historical disaster loss data corresponding to each spatial grid. The multi-dimensional risk index calculation module is used to obtain the following information based on the standard meteorological characteristic data, standard power equipment data, and standard historical disaster loss data corresponding to each spatial grid: the risk index of several meteorological factors, the importance weight of several power equipment, the vulnerability weight of several power equipment, the meteorological risk index, the equipment exposure index, and the equipment vulnerability index of each spatial grid. The grid disaster loss prediction probability calculation module is used to calculate the disaster loss prediction probability of each spatial grid based on several meteorological factor hazard indices corresponding to each spatial grid, several power equipment importance weights corresponding to each spatial grid, several power equipment vulnerability weights corresponding to each spatial grid, and several power equipment importance weights corresponding to each spatial grid. The risk level classification module is used to perform multi-dimensional fusion of the meteorological hazard index, equipment exposure index, equipment vulnerability index, and disaster loss prediction probability of each spatial grid to obtain the comprehensive disaster loss risk index of each spatial grid, and classify the risk level of each spatial grid based on the comprehensive disaster loss risk index of each spatial grid to determine the risk level of each spatial grid.

[0020] This invention provides a risk level classification system for power grid areas. In practical applications, it only requires a multi-dimensional risk index calculation module to obtain the meteorological hazard index, equipment exposure index, and equipment vulnerability index for each spatial grid using standard meteorological characteristic data, standard power equipment data, and standard historical disaster damage data corresponding to each spatial grid. This provides quantitative indicators for subsequent multi-dimensional comprehensive assessment of power grid disaster damage risk. Next, a grid disaster damage prediction probability calculation module is used to calculate the disaster damage prediction probability for each spatial grid by combining several meteorological factor hazard indices, several power equipment importance weights, several power equipment vulnerability weights, and several power equipment importance weights corresponding to each spatial grid. This further enriches the multi-dimensional indicators for power grid area risk assessment and avoids distortion of risk assessment results caused by judging power grid disaster damage risk based on only a single dimension. Then, a risk level classification module is used to obtain the comprehensive disaster risk index of each spatial grid through multi-dimensional fusion, and the risk level of the comprehensive disaster risk index of each spatial grid is classified. This can integrate the multi-dimensional disaster risk indicators of power grid equipment to construct the comprehensive disaster risk index of each region of the power grid, realize the classification of disaster risk in each region of the power grid, and determine the risk level of each spatial grid.

[0021] Furthermore, the power grid data acquisition module is used to divide the target monitoring power grid, acquire several spatial grids, and acquire standard meteorological characteristic data, standard power equipment data, and standard historical disaster loss data corresponding to each spatial grid, including: Acquire several initial multi-source meteorological data, several initial power equipment data, and several initial historical disaster damage data of the target power grid; Outlier removal and missing value filling are performed on several initial multi-source meteorological data, several initial power equipment data and several initial historical disaster damage data to obtain several preprocessed multi-source meteorological data, several preprocessed power equipment data and several preprocessed historical disaster damage data; Spatiotemporal scale unification and normalization processing are performed on several preprocessed multi-source meteorological data, several preprocessed power equipment data and several preprocessed historical disaster damage data to obtain several standard multi-source meteorological data, several standard power equipment data and several standard historical disaster damage data. The target monitoring power grid is divided into several spatial grids; Several standard multi-source meteorological data, several standard power equipment data, and several standard historical disaster loss data are mapped to several spatial grids to obtain the standard meteorological feature data, standard power equipment data, and standard historical disaster loss data corresponding to each spatial grid.

[0022] In the above scheme, by acquiring several initial multi-source meteorological data, several initial power equipment data, and several initial historical disaster damage data of the target monitoring power grid, the original data sources can be provided for subsequent standardization processing and risk assessment. Next, through outlier removal and missing value imputation, the assessment interference caused by erroneous or missing data in the original data can be eliminated, resulting in several preprocessed multi-source meteorological data, several preprocessed power equipment data, and several preprocessed historical disaster damage data. Then, by unifying the spatiotemporal scale of various types of data and performing normalization processing, the problem of inconsistent dimensions caused by different data formats can be eliminated, resulting in several standard multi-source meteorological data, several standard power equipment data, and several standard historical disaster damage data that can be uniformly calculated and used. Subsequently, by dividing the target monitoring power grid, a large-scale target monitoring power grid can be divided into several spatial grids, enabling refined risk assessment by region. Finally, by matching the three types of standardized data one by one to the corresponding spatial grids, data support is provided for the subsequent calculation of multi-dimensional risk indicators.

[0023] Furthermore, the multi-dimensional risk index calculation module is used to obtain, based on the standard meteorological characteristic data, standard power equipment data, and standard historical disaster loss data corresponding to each spatial grid, several meteorological factor hazard indices, several power equipment importance weights, several power equipment vulnerability weights, meteorological hazard indices, equipment exposure indices, and equipment vulnerability indices for each spatial grid, including: Based on the standard meteorological characteristic data corresponding to each spatial grid, the risk index of several meteorological factors corresponding to each spatial grid is obtained, and the meteorological risk index of each spatial grid is obtained based on the risk index of several meteorological factors corresponding to each spatial grid. Based on the standard power equipment data corresponding to each spatial grid, the importance weights of several power equipment corresponding to each spatial grid are determined, and the standard power equipment data corresponding to each spatial grid and the importance weights of several power equipment corresponding to each spatial grid are weighted and fused to obtain the equipment exposure index of each spatial grid. Based on the standard historical disaster damage data corresponding to each spatial grid, the vulnerability weights of several power equipment corresponding to each spatial grid are determined, and the equipment vulnerability index of each spatial grid is obtained based on the vulnerability weights and importance weights of several power equipment corresponding to each spatial grid.

[0024] In the above scheme, several meteorological factor hazard indices are calculated for each spatial grid using standard meteorological characteristic data. These indices are then integrated to obtain the meteorological hazard index for each spatial grid. This quantifies the threat posed by meteorological disasters occurring in each spatial grid, supplementing meteorological dimension assessment indicators and avoiding reliance solely on qualitative weather descriptions to determine the disaster risk of different areas of the power grid. Next, by determining the importance weights of several power equipment corresponding to each spatial grid, the scheme avoids treating all power equipment in the region as equally important. The equipment exposure index for each spatial grid is calculated based on these importance weights, providing foundational data for obtaining the comprehensive disaster risk index of each spatial grid through multi-dimensional fusion. Finally, the vulnerability weights of power equipment are determined using standard historical disaster data for each spatial grid. This quantifies the susceptibility of power equipment within the grid to disaster damage. The equipment vulnerability index for each spatial grid is calculated based on these importance weights, providing foundational data for obtaining the comprehensive disaster risk index of each spatial grid through multi-dimensional fusion and eliminating the distortion caused by a single meteorological dimension assessment. Attached Figure Description

[0025] To more clearly illustrate the technical solution of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0026] Figure 1 A flowchart illustrating a method for classifying risk levels of a power grid area according to an embodiment of the present invention; Figure 2This is an architecture diagram of a risk level classification system for a power grid area provided in an embodiment of the present invention; Figure 3 This is a risk heat map provided in one embodiment of the present invention. Detailed Implementation

[0027] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0028] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application; the terms “comprising” and “having”, and any variations thereof, in the specification, claims, and foregoing description of the drawings are intended to cover non-exclusive inclusion.

[0029] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly defined.

[0030] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0031] In the description of the embodiments in this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0032] In the description of the embodiments of this application, the term "multiple" refers to two or more (including two), similarly, "multiple sets" refers to two or more (including two sets), and "multiple pieces" refers to two or more (including two pieces).

[0033] In the description of the embodiments of this application, unless otherwise expressly specified and limited, technical terms such as "installation," "connection," "joining," and "fixing" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. For those skilled in the art, the specific meaning of the above terms in the embodiments of this application can be understood according to the specific circumstances.

[0034] See Figure 1 To avoid distorted risk assessment results due to judging power grid disaster risk based on a single dimension, this embodiment provides a method for classifying the risk level of power grid areas by integrating multi-dimensional disaster risk indicators of power grid equipment. The method flowchart is available in the provided text. Figure 1 ,include: Step S1: Divide the target monitoring power grid into several spatial grids, and obtain the standard meteorological characteristic data, standard power equipment data, and standard historical disaster loss data corresponding to each spatial grid. Step S2: Based on the standard meteorological characteristic data, standard power equipment data, and standard historical disaster damage data corresponding to each spatial grid, obtain the following for each spatial grid: meteorological risk index, power equipment importance weight, power equipment vulnerability weight, meteorological risk index, equipment exposure index, and equipment vulnerability index. Step S3: Calculate the disaster loss prediction probability for each spatial grid based on the risk index of several meteorological factors corresponding to each spatial grid, the importance weight of several power equipment corresponding to each spatial grid, the vulnerability weight of several power equipment corresponding to each spatial grid, and the importance weight of several power equipment corresponding to each spatial grid. Step S4: Multidimensionally integrate the meteorological hazard index, equipment exposure index, equipment vulnerability index, and disaster loss prediction probability of each spatial grid to obtain the comprehensive disaster loss risk index of each spatial grid. Then, classify the risk level of each spatial grid according to the comprehensive disaster loss risk index of each spatial grid to determine the risk level of each spatial grid.

[0035] In this embodiment, the meteorological hazard index, equipment exposure index, and equipment vulnerability index of each spatial grid are obtained by using standard meteorological characteristic data, standard power equipment data, and standard historical disaster damage data corresponding to each spatial grid. This provides quantitative indicators for subsequent multi-dimensional comprehensive assessment of power grid disaster damage risk. Next, the disaster damage prediction probability of each spatial grid is calculated by combining several meteorological factor hazard indices, several power equipment importance weights, several power equipment vulnerability weights, and several power equipment importance weights corresponding to each spatial grid. This further enriches the multi-dimensional indicators for power grid area risk assessment and avoids distortion of risk assessment results due to judging power grid disaster damage risk based on only a single dimension. Then, the comprehensive disaster damage risk index of each spatial grid is obtained through multi-dimensional fusion, and the comprehensive disaster damage risk index of each spatial grid is classified into risk levels. This allows for the integration of multi-dimensional disaster damage indicators of power grid equipment to construct a comprehensive disaster damage risk index for each region of the power grid, realizing the classification of disaster damage risk in each region of the power grid and determining the risk level of each spatial grid. Specifically: in, Let g be the comprehensive disaster risk index of the g-th spatial grid at time t; Let g be the disaster damage prediction probability of the g-th spatial grid at time t; Let g be the meteorological hazard index of the g-th spatial grid at time t; Equipment exposure index of the g-th spatial grid; The device vulnerability index for the g-th spatial grid; The preset fusion weights have a value range of [0,1]. Finally, the risk level of each spatial grid is determined based on the comprehensive disaster risk index of each spatial grid and the preset risk level classification table, as shown in Table 1 below: Table 1 Pre-defined Risk Level Classification Table The above thresholds can be adjusted based on historical disaster loss data, expert rules, or power grid business requirements.

[0036] Furthermore, the process of dividing the target monitoring power grid into several spatial grids and acquiring standard meteorological characteristic data, standard power equipment data, and standard historical disaster damage data corresponding to each spatial grid includes: Acquire several initial multi-source meteorological data, several initial power equipment data, and several initial historical disaster damage data of the target power grid; Outlier removal and missing value filling are performed on several initial multi-source meteorological data, several initial power equipment data and several initial historical disaster damage data to obtain several preprocessed multi-source meteorological data, several preprocessed power equipment data and several preprocessed historical disaster damage data; Spatiotemporal scale unification and normalization processing are performed on several preprocessed multi-source meteorological data, several preprocessed power equipment data and several preprocessed historical disaster damage data to obtain several standard multi-source meteorological data, several standard power equipment data and several standard historical disaster damage data. The target monitoring power grid is divided into several spatial grids; Several standard multi-source meteorological data, several standard power equipment data, and several standard historical disaster loss data are mapped to several spatial grids to obtain the standard meteorological feature data, standard power equipment data, and standard historical disaster loss data corresponding to each spatial grid.

[0037] In this embodiment, by acquiring several initial multi-source meteorological data, several initial power equipment data, and several initial historical disaster damage data of the target monitoring power grid, original data sources can be provided for subsequent standardization processing and risk assessment. The initial multi-source meteorological data can originate from ERA5 reanalysis data, HRES high-resolution forecast data, global meteorological model output data, ground meteorological station observation data, satellite remote sensing meteorological data, radar echo data, and severe convection monitoring data. The initial multi-source meteorological data includes at least one of the following variables: wind speed, gusts, rainfall, cumulative rainfall, temperature, humidity, air pressure, thunderstorm index, freezing index, icing index, and extreme weather duration. The power equipment types include transmission lines, towers, substations, transformers, and distribution equipment. The initial power equipment data includes the equipment number, equipment type, equipment spatial location, voltage level, commissioning time, operating years, historical failure count, equipment health score, defect level, equipment importance level, region, and historical disaster damage records for each power equipment.

[0038] Next, by removing outliers and imputing missing values, the evaluation interference caused by erroneous or missing data in the original data can be eliminated, resulting in several preprocessed multi-source meteorological data, several preprocessed power equipment data, and several preprocessed historical disaster damage data. Then, by unifying the spatiotemporal scale of various types of data and performing normalization processing, the problem of inconsistent dimensions caused by different data formats can be eliminated, resulting in several standard multi-source meteorological data, several standard power equipment data, and several standard historical disaster damage data that can be uniformly calculated and used. The normalization processing includes unifying the coordinate system of the data and normalizing the data. Subsequently, by dividing the target monitoring power grid, preferably... The spatial grid can also be set as needed. , Alternatively, it can use other spatial resolutions. It can divide a large-scale target monitoring power grid into several spatial grids, enabling refined risk assessment by region. Finally, by matching the three types of standardized data one by one to the corresponding spatial grids, it provides data support for the subsequent calculation of multi-dimensional risk indicators.

[0039] Furthermore, the acquisition of several meteorological factor hazard indices, several power equipment importance weights, several power equipment vulnerability weights, meteorological hazard indices, equipment exposure indices, and equipment vulnerability indices for each spatial grid based on standard meteorological characteristic data, standard power equipment data, and standard historical disaster damage data corresponding to each spatial grid includes: Based on the standard meteorological characteristic data corresponding to each spatial grid, the risk index of several meteorological factors corresponding to each spatial grid is obtained, and the meteorological risk index of each spatial grid is obtained based on the risk index of several meteorological factors corresponding to each spatial grid. Based on the standard power equipment data corresponding to each spatial grid, the importance weights of several power equipment corresponding to each spatial grid are determined, and the standard power equipment data corresponding to each spatial grid and the importance weights of several power equipment corresponding to each spatial grid are weighted and fused to obtain the equipment exposure index of each spatial grid. Based on the standard historical disaster damage data corresponding to each spatial grid, the vulnerability weights of several power equipment corresponding to each spatial grid are determined, and the equipment vulnerability index of each spatial grid is obtained based on the vulnerability weights and importance weights of several power equipment corresponding to each spatial grid.

[0040] In this embodiment, a set of meteorological features corresponding to each spatial grid can be constructed using the standard meteorological feature data corresponding to each spatial grid: in, Let g be the set of meteorological features at time t. Let g be the wind speed characteristic of grid g at time t; The rainfall characteristics of grid g at time t; The temperature characteristics of grid g at time t; Let g be the thunderstorm characteristics at time t; The freezing or icing characteristics of grid g at time t are defined. Then, using standard meteorological characteristic data corresponding to each spatial grid, the hazard index of several meteorological factors for each spatial grid is calculated. Finally, the hazard indices of all power equipment meteorological factors in each spatial grid are integrated to obtain the meteorological hazard index for each spatial grid. This quantifies the threat posed by meteorological disasters occurring in each spatial grid, supplementing meteorological dimension assessment indicators and avoiding reliance solely on qualitative weather descriptions to judge the disaster risk of different areas of the power grid. Next, by determining the importance weights of several power equipment corresponding to each spatial grid, the hazard of treating all power equipment in the region as equally important is avoided. The equipment exposure index for each spatial grid is calculated based on these importance weights, providing foundational data for subsequently obtaining the comprehensive disaster risk index of each spatial grid through multi-dimensional fusion. Then, by using the standard historical disaster damage data corresponding to each spatial grid, the vulnerability weight of power equipment is determined, which can quantify the degree of difficulty of power equipment in the grid being damaged by disasters. Combined with the importance weight of several power equipment corresponding to each spatial grid, the equipment vulnerability index of each spatial grid is calculated, so as to provide basic data for obtaining the comprehensive disaster damage risk index of each spatial grid through multi-dimensional fusion, and eliminate the distortion of results caused by single meteorological dimension assessment.

[0041] Further, the step of obtaining several meteorological factor hazard indices corresponding to each spatial grid based on the standard meteorological characteristic data corresponding to each spatial grid, and obtaining the meteorological hazard index of each spatial grid based on the several meteorological factor hazard indices corresponding to each spatial grid, includes: Based on the preset first threshold set and the preset second threshold set of meteorological factors, the standard meteorological characteristic data corresponding to each spatial grid are normalized to obtain the risk index of several meteorological factors corresponding to each spatial grid. The meteorological hazard index of each spatial grid is obtained by weighting and fusing several meteorological hazard indices corresponding to each spatial grid based on a preset meteorological factor weight set.

[0042] In this embodiment, the standard meteorological feature data corresponding to each spatial grid are normalized by using a preset first set of meteorological factor thresholds and a preset second set of meteorological factor thresholds. This unifies the numerical range of various types of meteorological data and enables comparison of the intensity of different types of meteorological disasters. Specifically: in: The meteorological hazard index is the normalized meteorological factor index obtained by normalizing the k-th meteorological factor in the g-th grid. This represents the original value of the k-th meteorological factor in the standard meteorological characteristic data; The first threshold of the k-th meteorological factor in the first threshold set of preset meteorological factors is the minimum value of the meteorological factor. This refers to the second threshold value of the k-th type of meteorological factor in the preset second threshold set of meteorological factors, i.e., the maximum value of the meteorological factor. Next, by weighting and fusing the risk indices of several meteorological factors corresponding to each spatial grid according to the preset meteorological factor weight set, multiple meteorological disaster-causing factors can be integrated to obtain the meteorological risk index of each spatial grid. This comprehensively quantifies the degree of threat of meteorological disasters to each spatial grid, specifically: in, Let g be the meteorological hazard index of the g-th grid at time t; This represents the total number of meteorological factors. The weight of the k-th type of meteorological factor in the preset meteorological factor weight set; For example, when considering wind speed, rainfall, temperature, thunderstorms, and freezing conditions: in, The weights of wind speed meteorological factors, The weights of the meteorological factors related to rainfall. The weights of temperature meteorological factors, The weights of thunderstorm meteorological factors, The weights of the freezing weather factors.

[0043] Further, the step of determining the importance weights of several power devices corresponding to each spatial grid based on the standard power device data corresponding to each spatial grid, and weighting and fusing the standard power device data and the importance weights of several power devices corresponding to each spatial grid to obtain the device exposure index of each spatial grid includes: Based on the preset equipment type table, the standard power equipment data corresponding to each spatial grid is matched to obtain the importance weights of several power equipment corresponding to each spatial grid; The standard power equipment data corresponding to each spatial grid and the importance weights of several power equipment corresponding to each spatial grid are weighted and fused to obtain the equipment exposure index of each spatial grid.

[0044] In this embodiment, by calling a preset device type table to match each power device within the grid, the importance weights of several power devices corresponding to each spatial grid can be obtained, thereby quantifying the importance of the power devices. The preset device type table is shown in Table 2 below: Table 2 Preset Equipment Types Next, by weighting and fusing the standard power equipment data corresponding to each spatial grid with the importance weights of several power equipment corresponding to each spatial grid, it is possible to avoid evaluating all power equipment as objects of equal risk, and obtain the equipment exposure index for each spatial grid, specifically: in: The device exposure index for the g-th spatial grid; This represents the total number of electrical devices within the g-th spatial grid. Let be the power equipment importance weight of the i-th power equipment; This indicates taking the maximum value among all spatial grids.

[0045] Furthermore, the process of determining the vulnerability weights of several power equipment corresponding to each spatial grid based on the standard historical disaster loss data corresponding to each spatial grid, and obtaining the equipment vulnerability index of each spatial grid based on the vulnerability weights and importance weights of several power equipment corresponding to each spatial grid, includes: Based on a preset set of equipment status weights, the standard historical disaster damage data corresponding to each spatial grid is matched to obtain several power equipment vulnerability weights corresponding to each spatial grid. The importance weights and vulnerability weights of several power equipment corresponding to each spatial grid are weighted and fused to obtain the equipment vulnerability index of each spatial grid.

[0046] In this embodiment, by matching the standard historical disaster damage data corresponding to each spatial grid with a preset set of device state weights, the vulnerability weight of each power device can be determined, quantifying the degree to which different power devices are easily damaged under disasters. Specifically: in, Let i be the vulnerability weight corresponding to the i-th power device. The normalized value of the service life of the i-th power equipment in the standard historical disaster loss data can be obtained directly from the power equipment ledger and then obtained after statistical and normalization processing. The normalized value of the number of historical faults of the i-th power equipment in the standard historical disaster loss data can be obtained directly from the historical fault records and then obtained after statistical and normalization processing. The normalized value of the equipment health score of the i-th power equipment in the standard historical disaster loss data can be obtained directly from the operation status record and then processed by statistics, level mapping and normalization. The normalized value of the equipment defect level of the i-th power equipment in the standard historical disaster loss data can be obtained directly from the defect record and then processed by statistics, level mapping and normalization. The equipment maintenance anomaly or maintenance status index of the i-th power equipment in the standard historical disaster loss data can be obtained directly from the maintenance records and then obtained after statistical and normalization processing. , , , and These are the weighting coefficients for the years of operation, the number of historical failures, the equipment health score, the equipment defect level, and the equipment maintenance in the standard historical disaster loss data, respectively, to meet the following requirements. The vulnerability index can be determined through expert experience or training with historical disaster data. Next, by weighting and fusing the importance and vulnerability weights of several power devices corresponding to each spatial grid, it is possible to avoid assessing all power devices as having equal risk, thus obtaining the device vulnerability index for each spatial grid, specifically: ,in, Let g be the device vulnerability index of the g-th spatial grid. Let i be the power equipment vulnerability weight for the i-th power equipment. Let be the power equipment importance weight of the i-th power equipment.

[0047] Furthermore, the calculation of the disaster loss prediction probability for each spatial grid based on the risk index of several meteorological factors corresponding to each spatial grid, the importance weight of several power equipment corresponding to each spatial grid, the vulnerability weight of several power equipment corresponding to each spatial grid, and the importance weight of several power equipment corresponding to each spatial grid includes: Based on the hazard index of several meteorological factors corresponding to each spatial grid, the importance weight of several power equipment corresponding to each spatial grid, and the vulnerability weight of several power equipment corresponding to each spatial grid, a multidimensional feature of several power equipment corresponding to each spatial grid is constructed. Based on the preset disaster loss prediction model and the multi-dimensional features of several power equipment corresponding to each spatial grid, the disaster loss probability of several power equipment corresponding to each spatial grid is obtained. The importance weights of several power equipment corresponding to each spatial grid and the disaster loss probabilities of several power equipment corresponding to each spatial grid are weighted and fused to obtain the disaster loss prediction probability of each spatial grid.

[0048] In this embodiment, by constructing several meteorological factor hazard indices, several power equipment importance weights, and several power equipment vulnerability weights corresponding to each spatial grid, a multi-dimensional feature of several power equipment corresponding to each spatial grid is constructed. This allows multiple risk factors to be integrated into data that can be identified by a preset disaster loss prediction model. Specifically: in, Let be the predicted probability of disaster damage for the i-th power equipment at time t; This indicates a pre-defined disaster loss prediction model; This represents the multidimensional features of the i-th power device at time t. The preset disaster loss prediction model can employ XGBoost, LightGBM, random forest, logistic regression, neural networks, or ensemble models. Next, by weighted fusion of the importance weights of several power devices corresponding to each spatial grid and the disaster loss probabilities of several power devices corresponding to each spatial grid, the disaster loss probability of a single power device can be converted into the disaster loss prediction probability of the entire grid. Specifically: ,in, Let g be the disaster damage prediction probability of the g-th spatial grid at time t; Let be the power equipment importance weight of the i-th power equipment.

[0049] This embodiment provides a risk level classification system for power grid areas, such as Figure 2 As shown, it includes a power grid data acquisition module, a multi-dimensional risk indicator calculation module, a grid disaster loss prediction probability calculation module, and a risk level classification module, specifically: The power grid data acquisition module is used to divide the target monitoring power grid, acquire several spatial grids, and acquire standard meteorological characteristic data, standard power equipment data, and standard historical disaster loss data corresponding to each spatial grid. The multi-dimensional risk index calculation module is used to obtain the following information based on the standard meteorological characteristic data, standard power equipment data, and standard historical disaster loss data corresponding to each spatial grid: the risk index of several meteorological factors, the importance weight of several power equipment, the vulnerability weight of several power equipment, the meteorological risk index, the equipment exposure index, and the equipment vulnerability index of each spatial grid. The grid disaster loss prediction probability calculation module is used to calculate the disaster loss prediction probability of each spatial grid based on several meteorological factor hazard indices corresponding to each spatial grid, several power equipment importance weights corresponding to each spatial grid, several power equipment vulnerability weights corresponding to each spatial grid, and several power equipment importance weights corresponding to each spatial grid. The risk level classification module is used to perform multi-dimensional fusion of the meteorological hazard index, equipment exposure index, equipment vulnerability index, and disaster loss prediction probability of each spatial grid to obtain the comprehensive disaster loss risk index of each spatial grid, and classify the risk level of each spatial grid based on the comprehensive disaster loss risk index of each spatial grid to determine the risk level of each spatial grid.

[0050] This embodiment provides a risk level classification system for power grid areas. In practical applications, it only requires a multi-dimensional risk indicator calculation module. By using standard meteorological characteristic data, standard power equipment data, and standard historical disaster damage data corresponding to each spatial grid, it obtains the meteorological hazard index, equipment exposure index, and equipment vulnerability index for each spatial grid. This provides quantitative indicators for subsequent multi-dimensional comprehensive assessment of power grid disaster damage risk. Next, a grid disaster damage prediction probability calculation module is used. This module combines several meteorological factor hazard indices, power equipment importance weights, power equipment vulnerability weights, and power equipment importance weights corresponding to each spatial grid to calculate the disaster damage prediction probability for each spatial grid. This further enriches the multi-dimensional indicators for power grid area risk assessment and avoids distortion of risk assessment results caused by judging power grid disaster damage risk based on only a single dimension. Then, a risk level classification module is used to obtain the comprehensive disaster risk index of each spatial grid through multi-dimensional fusion, and the risk level of the comprehensive disaster risk index of each spatial grid is classified. This can integrate the multi-dimensional disaster risk indicators of power grid equipment to construct the comprehensive disaster risk index of each region of the power grid, realize the classification of disaster risk in each region of the power grid, and determine the risk level of each spatial grid.

[0051] Furthermore, the power grid data acquisition module is used to divide the target monitoring power grid, acquire several spatial grids, and acquire standard meteorological characteristic data, standard power equipment data, and standard historical disaster loss data corresponding to each spatial grid, including: Acquire several initial multi-source meteorological data, several initial power equipment data, and several initial historical disaster damage data of the target power grid; Outlier removal and missing value filling are performed on several initial multi-source meteorological data, several initial power equipment data and several initial historical disaster damage data to obtain several preprocessed multi-source meteorological data, several preprocessed power equipment data and several preprocessed historical disaster damage data; Spatiotemporal scale unification and normalization processing are performed on several preprocessed multi-source meteorological data, several preprocessed power equipment data and several preprocessed historical disaster damage data to obtain several standard multi-source meteorological data, several standard power equipment data and several standard historical disaster damage data. The target monitoring power grid is divided into several spatial grids; Several standard multi-source meteorological data, several standard power equipment data, and several standard historical disaster loss data are mapped to several spatial grids to obtain the standard meteorological feature data, standard power equipment data, and standard historical disaster loss data corresponding to each spatial grid.

[0052] In this embodiment, by acquiring several initial multi-source meteorological data, several initial power equipment data, and several initial historical disaster damage data of the target monitoring power grid, the original data sources can be provided for subsequent standardization processing and risk assessment. Next, through outlier removal and missing value imputation, assessment interference caused by erroneous or missing data in the original data can be eliminated, resulting in several preprocessed multi-source meteorological data, several preprocessed power equipment data, and several preprocessed historical disaster damage data. Then, by unifying the spatiotemporal scale of various types of data and performing normalization processing, the problem of inconsistent dimensions caused by different data formats can be eliminated, resulting in several standard multi-source meteorological data, several standard power equipment data, and several standard historical disaster damage data that can be uniformly calculated and used. Subsequently, by dividing the target monitoring power grid, a large-scale target monitoring power grid can be divided into several spatial grids, achieving regionally refined risk assessment. Finally, by matching the three types of standardized data one by one to the corresponding spatial grids, data support is provided for the subsequent calculation of multi-dimensional risk indicators.

[0053] Furthermore, the multi-dimensional risk index calculation module is used to obtain, based on the standard meteorological characteristic data, standard power equipment data, and standard historical disaster loss data corresponding to each spatial grid, several meteorological factor hazard indices, several power equipment importance weights, several power equipment vulnerability weights, meteorological hazard indices, equipment exposure indices, and equipment vulnerability indices for each spatial grid, including: Based on the standard meteorological characteristic data corresponding to each spatial grid, the risk index of several meteorological factors corresponding to each spatial grid is obtained, and the meteorological risk index of each spatial grid is obtained based on the risk index of several meteorological factors corresponding to each spatial grid. Based on the standard power equipment data corresponding to each spatial grid, the importance weights of several power equipment corresponding to each spatial grid are determined, and the standard power equipment data corresponding to each spatial grid and the importance weights of several power equipment corresponding to each spatial grid are weighted and fused to obtain the equipment exposure index of each spatial grid. Based on the standard historical disaster damage data corresponding to each spatial grid, the vulnerability weights of several power equipment corresponding to each spatial grid are determined, and the equipment vulnerability index of each spatial grid is obtained based on the vulnerability weights and importance weights of several power equipment corresponding to each spatial grid.

[0054] In this embodiment, several meteorological factor hazard indices are calculated for each spatial grid using standard meteorological characteristic data. These indices are then integrated with the meteorological factor hazard indices of all power equipment within each spatial grid to obtain the meteorological hazard index for each grid. This quantifies the threat posed by meteorological disasters occurring in each spatial grid, supplementing meteorological dimension assessment indicators and avoiding reliance solely on qualitative weather descriptions to determine the disaster risk of different areas of the power grid. Next, by determining the importance weights of several power equipment corresponding to each spatial grid, the assumption that all power equipment within a region is equally important is avoided. The equipment exposure index for each spatial grid is calculated based on these importance weights, providing foundational data for subsequently obtaining the comprehensive disaster risk index for each spatial grid through multi-dimensional fusion. Finally, the vulnerability weights of power equipment are determined using standard historical disaster data corresponding to each spatial grid. This quantifies the susceptibility of power equipment within the grid to disaster damage. The equipment vulnerability index for each spatial grid is calculated based on these importance weights, providing foundational data for subsequently obtaining the comprehensive disaster risk index for each spatial grid through multi-dimensional fusion and eliminating the distortion caused by a single meteorological dimension assessment.

[0055] This embodiment can also map the comprehensive disaster risk index of each spatial grid onto the corresponding color according to a preset risk color mapping table to form a risk heat map, such as... Figure 3 As shown in Table 3 below, the preset risk color mapping table is a pre-defined table.

[0056] Table 3 Preset Risk Color Mapping Table Furthermore, the risk heatmap can be displayed according to different forecast time windows, such as the next 6 hours, the next 24 hours, and the next 72 hours, or according to different disaster types, such as strong wind risk heatmap, rainstorm risk heatmap, high temperature risk heatmap, thunderstorm risk heatmap, freezing risk heatmap, and comprehensive disaster loss risk heatmap. Finally, this embodiment can also determine high-risk spatial grids based on the risk heatmap, and spatially associate the high-risk spatial grids with the power equipment ledger to output a high-risk equipment list. This high-risk equipment list includes: power equipment number, power equipment type, region, power equipment disaster probability, power equipment risk level, main meteorological influencing factors, reasons for equipment vulnerability, and early warning suggestions, thereby providing support for early warning assessment, key inspections, and emergency deployment.

[0057] The power equipment number, power equipment type, region, power equipment disaster probability, and power equipment risk level are shown in Table 4 below: Table 4. List of High-Risk Equipment This embodiment also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the functions of the system as described above.

[0058] It is understood that the above system embodiments correspond to the method embodiments of the present invention, and can implement the method for classifying the risk level of a power grid area provided by any of the above method embodiments of the present invention.

[0059] It should be noted that the system embodiments described above are merely illustrative, and some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0060] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A method for classifying the risk level of a power grid area, characterized in that, include: The target monitoring power grid is divided into several spatial grids, and standard meteorological characteristic data, standard power equipment data, and standard historical disaster loss data corresponding to each spatial grid are obtained. Based on the standard meteorological characteristic data, standard power equipment data, and standard historical disaster damage data corresponding to each spatial grid, we obtain the following for each spatial grid: meteorological risk index, power equipment importance weight, power equipment vulnerability weight, meteorological risk index, equipment exposure index, and equipment vulnerability index. The disaster loss prediction probability of each spatial grid is calculated based on the risk index of several meteorological factors corresponding to each spatial grid, the importance weight of several power equipment corresponding to each spatial grid, the vulnerability weight of several power equipment corresponding to each spatial grid, and the importance weight of several power equipment corresponding to each spatial grid. The meteorological hazard index, equipment exposure index, equipment vulnerability index, and disaster loss prediction probability of each spatial grid are multidimensionally integrated to obtain the comprehensive disaster loss risk index of each spatial grid. The comprehensive disaster loss risk index of each spatial grid is then classified into risk levels to determine the risk level of each spatial grid.

2. The method for classifying risk levels of a power grid area according to claim 1, characterized in that, The process of dividing the target monitoring power grid into several spatial grids and acquiring standard meteorological characteristic data, standard power equipment data, and standard historical disaster loss data corresponding to each spatial grid includes: Acquire several initial multi-source meteorological data, several initial power equipment data, and several initial historical disaster damage data of the target power grid; Outlier removal and missing value filling are performed on several initial multi-source meteorological data, several initial power equipment data and several initial historical disaster damage data to obtain several preprocessed multi-source meteorological data, several preprocessed power equipment data and several preprocessed historical disaster damage data; Spatiotemporal scale unification and normalization processing are performed on several preprocessed multi-source meteorological data, several preprocessed power equipment data and several preprocessed historical disaster damage data to obtain several standard multi-source meteorological data, several standard power equipment data and several standard historical disaster damage data. The target monitoring power grid is divided into several spatial grids; Several standard multi-source meteorological data, several standard power equipment data, and several standard historical disaster loss data are mapped to several spatial grids to obtain the standard meteorological feature data, standard power equipment data, and standard historical disaster loss data corresponding to each spatial grid.

3. The method for classifying risk levels of a power grid area according to claim 1, characterized in that, The process of obtaining several meteorological factor hazard indices, several power equipment importance weights, several power equipment vulnerability weights, meteorological hazard indices, equipment exposure indices, and equipment vulnerability indices for each spatial grid based on standard meteorological characteristic data, standard power equipment data, and standard historical disaster damage data corresponding to each spatial grid includes: Based on the standard meteorological characteristic data corresponding to each spatial grid, the risk index of several meteorological factors corresponding to each spatial grid is obtained, and the meteorological risk index of each spatial grid is obtained based on the risk index of several meteorological factors corresponding to each spatial grid. Based on the standard power equipment data corresponding to each spatial grid, the importance weights of several power equipment corresponding to each spatial grid are determined, and the standard power equipment data corresponding to each spatial grid and the importance weights of several power equipment corresponding to each spatial grid are weighted and fused to obtain the equipment exposure index of each spatial grid. Based on the standard historical disaster damage data corresponding to each spatial grid, the vulnerability weights of several power equipment corresponding to each spatial grid are determined, and the equipment vulnerability index of each spatial grid is obtained based on the vulnerability weights and importance weights of several power equipment corresponding to each spatial grid.

4. The method for classifying the risk level of a power grid area according to claim 3, characterized in that, The process of obtaining several meteorological factor hazard indices corresponding to each spatial grid based on standard meteorological characteristic data corresponding to each spatial grid, and obtaining the meteorological hazard index of each spatial grid based on several meteorological factor hazard indices corresponding to each spatial grid, includes: Based on the preset first threshold set and the preset second threshold set of meteorological factors, the standard meteorological characteristic data corresponding to each spatial grid are normalized to obtain the risk index of several meteorological factors corresponding to each spatial grid. The meteorological hazard index of each spatial grid is obtained by weighting and fusing several meteorological hazard indices corresponding to each spatial grid based on a preset meteorological factor weight set.

5. The method for classifying risk levels of a power grid area according to claim 3, characterized in that, The process involves determining the importance weights of several power devices corresponding to each spatial grid based on the standard power device data corresponding to each spatial grid, and then weighting and fusing the standard power device data and the importance weights of several power devices corresponding to each spatial grid to obtain the device exposure index for each spatial grid, including: Based on the preset equipment type table, the standard power equipment data corresponding to each spatial grid is matched to obtain the importance weights of several power equipment corresponding to each spatial grid; The standard power equipment data corresponding to each spatial grid and the importance weights of several power equipment corresponding to each spatial grid are weighted and fused to obtain the equipment exposure index of each spatial grid.

6. The method for classifying risk levels of a power grid area according to claim 3, characterized in that, The process involves determining the vulnerability weights of several power equipment corresponding to each spatial grid based on standard historical disaster loss data, and obtaining the equipment vulnerability index for each spatial grid based on the vulnerability weights and importance weights of several power equipment corresponding to each spatial grid, including: Based on a preset set of equipment status weights, the standard historical disaster damage data corresponding to each spatial grid is matched to obtain several power equipment vulnerability weights corresponding to each spatial grid. The importance weights and vulnerability weights of several power equipment corresponding to each spatial grid are weighted and fused to obtain the equipment vulnerability index of each spatial grid.

7. The method for classifying risk levels of a power grid area according to claim 1, characterized in that, The calculation of the disaster loss prediction probability for each spatial grid based on the risk index of several meteorological factors corresponding to each spatial grid, the importance weight of several power equipment corresponding to each spatial grid, the vulnerability weight of several power equipment corresponding to each spatial grid, and the importance weight of several power equipment corresponding to each spatial grid includes: Based on the hazard index of several meteorological factors corresponding to each spatial grid, the importance weight of several power equipment corresponding to each spatial grid, and the vulnerability weight of several power equipment corresponding to each spatial grid, a multidimensional feature of several power equipment corresponding to each spatial grid is constructed. Based on the preset disaster loss prediction model and the multi-dimensional features of several power equipment corresponding to each spatial grid, the disaster loss probability of several power equipment corresponding to each spatial grid is obtained. The importance weights of several power equipment corresponding to each spatial grid and the disaster loss probabilities of several power equipment corresponding to each spatial grid are weighted and fused to obtain the disaster loss prediction probability of each spatial grid.

8. A risk level classification system for power grid areas, characterized in that, It includes a power grid data acquisition module, a multi-dimensional risk indicator calculation module, a grid disaster loss prediction probability calculation module, and a risk level classification module, specifically: The power grid data acquisition module is used to divide the target monitoring power grid, acquire several spatial grids, and acquire standard meteorological characteristic data, standard power equipment data, and standard historical disaster loss data corresponding to each spatial grid. The multi-dimensional risk index calculation module is used to obtain the following information based on the standard meteorological characteristic data, standard power equipment data, and standard historical disaster loss data corresponding to each spatial grid: the risk index of several meteorological factors, the importance weight of several power equipment, the vulnerability weight of several power equipment, the meteorological risk index, the equipment exposure index, and the equipment vulnerability index of each spatial grid. The grid disaster loss prediction probability calculation module is used to calculate the disaster loss prediction probability of each spatial grid based on several meteorological factor hazard indices corresponding to each spatial grid, several power equipment importance weights corresponding to each spatial grid, several power equipment vulnerability weights corresponding to each spatial grid, and several power equipment importance weights corresponding to each spatial grid. The risk level classification module is used to perform multi-dimensional fusion of the meteorological hazard index, equipment exposure index, equipment vulnerability index, and disaster loss prediction probability of each spatial grid to obtain the comprehensive disaster loss risk index of each spatial grid, and classify the risk level of each spatial grid based on the comprehensive disaster loss risk index of each spatial grid to determine the risk level of each spatial grid.

9. A risk level classification system for a power grid area according to claim 8, characterized in that, The power grid data acquisition module is used to divide the target monitoring power grid, acquire several spatial grids, and acquire standard meteorological characteristic data, standard power equipment data, and standard historical disaster loss data corresponding to each spatial grid, including: Acquire several initial multi-source meteorological data, several initial power equipment data, and several initial historical disaster damage data of the target power grid; Outlier removal and missing value filling are performed on several initial multi-source meteorological data, several initial power equipment data and several initial historical disaster damage data to obtain several preprocessed multi-source meteorological data, several preprocessed power equipment data and several preprocessed historical disaster damage data; Spatiotemporal scale unification and normalization processing are performed on several preprocessed multi-source meteorological data, several preprocessed power equipment data and several preprocessed historical disaster damage data to obtain several standard multi-source meteorological data, several standard power equipment data and several standard historical disaster damage data. The target monitoring power grid is divided into several spatial grids; Several standard multi-source meteorological data, several standard power equipment data, and several standard historical disaster loss data are mapped to several spatial grids to obtain the standard meteorological feature data, standard power equipment data, and standard historical disaster loss data corresponding to each spatial grid.

10. A risk level classification system for a power grid area according to claim 8, characterized in that, The multi-dimensional risk index calculation module is used to obtain, based on the standard meteorological characteristic data, standard power equipment data, and standard historical disaster loss data corresponding to each spatial grid, several meteorological factor hazard indices, several power equipment importance weights, several power equipment vulnerability weights, meteorological hazard indices, equipment exposure indices, and equipment vulnerability indices for each spatial grid, including: Based on the standard meteorological characteristic data corresponding to each spatial grid, the risk index of several meteorological factors corresponding to each spatial grid is obtained, and the meteorological risk index of each spatial grid is obtained based on the risk index of several meteorological factors corresponding to each spatial grid. Based on the standard power equipment data corresponding to each spatial grid, the importance weights of several power equipment corresponding to each spatial grid are determined, and the standard power equipment data corresponding to each spatial grid and the importance weights of several power equipment corresponding to each spatial grid are weighted and fused to obtain the equipment exposure index of each spatial grid. Based on the standard historical disaster damage data corresponding to each spatial grid, the vulnerability weights of several power equipment corresponding to each spatial grid are determined, and the equipment vulnerability index of each spatial grid is obtained based on the vulnerability weights and importance weights of several power equipment corresponding to each spatial grid.

Images