Power failure multi-dimensional comprehensive analysis quantitative evaluation model construction method and system

Abstract

The invention discloses a power failure multi-dimensional comprehensive analysis quantitative evaluation model construction method and system, and relates to the technical field of power failure risk analysis, and the method comprises the following steps: obtaining related environment data around an electric pole, carrying out the data cleaning processing of the related environment data, obtaining first environment data, and carrying out the risk quantitative calculation, obtaining first risk data; carrying out risk division processing on the power failure risk to obtain a power failure risk evaluation table; performing power failure risk calculation based on the first risk data and a power failure risk evaluation table to obtain a power failure risk quantitative index and a power failure risk evaluation result; the method is used for solving the problems that an existing power failure risk analysis technology mainly focuses on the influence of electrical parameters on the power failure risk, the power failure risk cannot be accurately evaluated in the face of environmental factor changes, and a method for fully integrating and utilizing related environmental data and accurately evaluating the power failure risk is lacked. And meanwhile, the power failure risk is accurately analyzed, quantified and judged only by using related environment data.

Description

Technical Field

[0001] The present invention relates to the technical field of power outage risk analysis, and in particular to a method and system for constructing a multi-dimensional comprehensive analysis and quantitative evaluation model for power outages. Background Art

[0002] Power outage risk analysis technology refers to a systematic approach to evaluate and predict various factors that may cause power system interruptions. It is used to assess the possibility of power outages in the power system and the severity of the consequences that may be caused by power outages.

[0003] Existing power outage risk analysis technologies mainly focus on the impact of electrical parameters in power system operation on power outage risk, and do not fully integrate and utilize various environmental data related to power outage risk. For example, data such as atmospheric pollutant concentrations and soil characteristics may only be simply recorded separately without establishing effective associations with power outage accident data, making it impossible to deeply explore the risk information contained in these data. Moreover, some power outage risk analysis methods remain at the level of qualitative description, such as simply dividing risks into high, medium, and low levels, but lacking precise quantitative means. It is difficult to accurately evaluate and compare the relationships between risk factors and their comprehensive contribution to power outage risk. This results in a lack of sufficient quantitative basis to take targeted measures; for example, the patent application with publication number CN117277587A discloses a power outage risk monitoring method based on multi-source data analysis. This scheme analyzes the power outage risk by collecting certain electrical parameters in the operation of the power system. It does not utilize the analysis of various environmental parameters related to the power outage risk, and cannot fully reflect the complex situation of the interaction of multiple risk factors in the actual power system operation; therefore, the existing power outage risk analysis technology mainly focuses on the impact of electrical parameters on the power outage risk. When faced with changes in environmental factors, it is impossible to accurately assess the power outage risk, lacks a method of fully integrating and utilizing relevant environmental data, and only uses relevant environmental data to accurately analyze and quantify the power outage risk. Summary of the invention

[0004] The present invention aims to solve one of the technical problems in the prior art to at least a certain extent, by acquiring relevant environmental data around the electric pole, performing data cleaning processing on the relevant environmental data to obtain first environmental data, and performing risk quantification calculation to obtain first risk data; and performing risk classification processing on the power outage risk to obtain a power outage risk assessment table; and then performing power outage risk calculation to obtain a power outage risk quantification index and a power outage risk assessment result; so as to solve the problem that the existing power outage risk analysis technology mainly focuses on the influence of electrical parameters on power outage risk, cannot accurately assess the power outage risk when facing changes in environmental factors, lacks a method of fully integrating and utilizing relevant environmental data, and only uses relevant environmental data to accurately analyze and quantify the power outage risk.

[0005] To achieve the above objectives, in a first aspect, the present application provides a method for constructing a multi-dimensional comprehensive analysis and quantitative evaluation model for power outages, comprising the following steps:

[0006] Obtain relevant environmental data around the poles, including: air pollution data, soil resistance data, and soil acid-base data;

[0007] Performing data cleaning processing on the relevant environmental data to obtain first environmental data, and performing risk quantification calculation based on the first environmental data to obtain first risk data;

[0008] Perform risk classification processing on the power outage risk based on the first risk data to obtain a power outage risk evaluation table;

[0009] The power outage risk is calculated based on the first risk data and the power outage risk assessment table to obtain a power outage risk quantification index and a power outage risk assessment result.

[0010] Furthermore, obtaining relevant environmental data of the transmission line includes the following sub-steps:

[0011] The sulfur dioxide concentration, nitrogen oxide concentration and particulate matter concentration in the air around the electric pole are collected at a first time interval, and the collection time is recorded and marked as air pollution data. The first time interval is t1;

[0012] Obtain the resistivity of the soil in four directions around the pole grounding wire at a second time interval, and record the time of acquisition, marked as soil resistance data, and the second time interval is t2;

[0013] The pH value of the soil in four directions around the pole is obtained at a third time interval, and the time of acquisition is recorded and marked as soil pH data. The third time interval is t3.

[0014] Furthermore, performing data cleaning on the relevant environmental data to obtain the first environmental data includes the following sub-steps:

[0015] Air pollution data cleaning: Based on air pollution data, the mean μi and standard deviation σi of sulfur dioxide concentration, nitrogen oxide concentration and particulate matter concentration are calculated in the first time period, and the concentration data exceeding the normal pollution range is marked as abnormal concentration data. The normal pollution range is [μi-3*σi, μi+3*σi]. For abnormal concentration data, the weighted average of the same type of concentration data collected at the first n collection moments and the last n collection moments is used to replace it. The cleaned air pollution data is marked as the first pollution data.

[0016] Soil resistance data cleaning: Based on the resistivity of the soil in four directions collected at the same collection time, the average resistivity μ2 and the resistivity standard deviation σ2 of the four resistivities are calculated, and the resistivity data exceeding the normal resistance range is marked as abnormal resistivity data. The normal resistivity range is [μ2-σ2, μ2+σ2]. If the number of abnormal resistivity data in the resistivity of the soil in four directions collected at the same collection time is greater than or equal to two, the soil resistance data collected at the collection time is marked as invalid data and re-collected; otherwise, for the abnormal resistivity data, the non-abnormal resistivity data at the same collection time is used to obtain the average value for replacement; the cleaned soil resistance data is marked as the first resistance data.

[0017] Furthermore, performing data cleaning on the relevant environmental data to obtain the first environmental data also includes the following sub-steps:

[0018] Soil acid-base data cleaning: Based on the soil acid-base values ​​in four directions collected at the same collection time, if the soil acid-base values ​​in the four directions all exceed the first soil acid-base range, the soil acid-base data collected at the collection time will be marked as invalid data and re-acquired. The first soil acid-base range is [3, 10];

[0019] Otherwise, calculate the average pH value μ3 and the pH standard deviation σ3 of the four pH values, and mark the pH data that exceeds the normal pH range as abnormal pH data, and the normal pH range is [μ3-σ3, μ3+σ3]; if the number of abnormal pH data in the pH values ​​of the soil in the four directions collected at the same collection time is greater than or equal to 2, then mark the soil pH data collected at the collection time as invalid data and re-acquire it, otherwise, for the abnormal pH data, use the non-abnormal pH data at the same collection time, calculate the average value and replace it; mark the cleaned soil pH data as the first pH data;

[0020] The first pollution data, the first resistance data, and the first acid-base data are marked as first environment data.

[0021] Further, performing risk quantification calculation based on the first environment data to obtain the first risk data includes the following sub-steps:

[0022] Calculation of air pollution risk: Based on the first pollution data, the pollution loads of sulfur dioxide, nitrogen oxides and particulate matter are calculated respectively by the pollution load calculation formula. The pollution load calculation formula is as follows: PL = C*k, where PL is the pollution load, C is the normalized sulfur dioxide concentration or nitrogen oxide concentration or particulate matter concentration, and k is the proportionality coefficient. The obtained sulfur dioxide pollution load is recorded as PL1, the nitrogen oxide pollution load is recorded as PL2, and the particulate matter pollution load is recorded as PL3;

[0023] The air pollution risk index PA is calculated based on the sulfur dioxide pollution load PL1, the nitrogen oxide pollution load PL2 and the particulate matter pollution load PL3. The air pollution risk index calculation formula is as follows:

[0024]

[0025] Furthermore, performing risk quantification calculation based on the first environment data to obtain the first risk data further includes the following sub-steps:

[0026] Soil resistance risk calculation: Based on the first resistance data, according to the relationship model between soil resistivity and grounding resistance, the grounding resistance of the pole grounding wire in four directions is calculated respectively, and the maximum grounding resistance is extracted by comparison, recorded as Rm; the design rated value of the pole grounding resistance is obtained, recorded as Rr, and the local lightning activity intensity coefficient of the pole, recorded as KL; then the soil resistance risk index PB is calculated. The soil resistance risk index calculation formula is as follows:

[0027] Soil acid-base risk calculation: Obtain the appropriate pH range of the pole material, recorded as [PH1, PH2]. Based on the first resistance data, calculate the acid-base deviation MC of the soil pH in four directions around the pole according to the acid-base deviation calculation formula. The acid-base deviation calculation formula is as follows: PH0 is the soil pH actually measured, and then the average pH deviation is calculated based on the pH deviation MC of the soil pH in four directions around the pole to obtain the soil pH risk index PC;

[0028] The air pollution risk index, soil resistivity risk index and soil acid-base risk index are marked as the first risk data.

[0029] Further, performing risk classification processing on the power outage risk based on the first risk data to obtain a power outage risk evaluation table includes the following sub-steps:

[0030] Set the weight of the air pollution risk index to Q1, the weight of the soil resistance risk index to Q2, and the weight of the soil acid-base risk index to Q3, Q1+Q2+Q3=1; set the seasonal environmental impact factor to Q0;

[0031] The risk standards for the air pollution risk index, soil resistance risk index and soil acid-base risk index are set respectively, and the risk standards include: low risk standard, medium risk standard, medium-high risk standard and high risk standard; denoted as A{1, 2, 3, 4}, B{1, 2, 3, 4}, C{1, 2, 3, 4}, where A, B and C represent the air pollution risk, soil resistance risk and soil acid-base risk in order, respectively, and 1, 2, 3 and 4 represent the low risk standard, medium risk standard, medium-high risk standard value and high risk standard in order;

[0032] Based on A{1, 2, 3, 4}, B{1, 2, 3, 4} and C{1, 2, 3, 4}, A, B and C are arranged in order from top to bottom, and 1, 2, 3 and 4 are arranged in order from left to right to create a table, which is marked as a power outage risk assessment table.

[0033] Further, calculating the power outage risk based on the first risk data and the power outage risk evaluation table to obtain a power outage risk quantification index and a power outage risk evaluation result includes the following sub-steps:

[0034] Q1, Q2, Q3 and Q0 form a risk weight vector, denoted as QL = Q0*{Q1, Q2, Q3};

[0035] The attribution functions of the air pollution risk index, soil resistance risk index and soil acid-base risk index are constructed. Based on the attribution function and the power outage risk evaluation table, the attribution degrees of the air pollution risk index, soil resistance risk index and soil acid-base risk index in the corresponding risk standards are calculated respectively, and the calculation results are organized into a matrix, marked as the power outage risk evaluation matrix, denoted as PP = {a1, a2, a3, a4; b1, b2, b3, b4; c1, c2, c3, c4}, where a, b, and c correspond to the attribution degrees of the air pollution risk index, soil resistance risk index and soil acid-base risk index in the corresponding risk standards, respectively.

[0036] Further, calculating the power outage risk based on the first risk data and the power outage risk evaluation table to obtain the power outage risk quantification index and the power outage risk evaluation result also includes the following sub-steps:

[0037] Multiply the risk weight vector QL by the power outage risk evaluation matrix PP to obtain the power outage risk vector QT, set the risk score based on the risk standard, and then calculate the power outage risk quantitative index based on the power outage risk vector QT and the risk score;

[0038] All components in the power outage risk vector QT are extracted, and the component sizes are compared to obtain the maximum component. According to the position of the maximum component in QT, the power outage risk assessment result is obtained, where positions 1, 2, 3, and 4 represent low risk, medium risk, medium-high risk, and high risk, respectively.

[0039] In a second aspect, the present application provides a system for constructing a multi-dimensional comprehensive analysis and quantitative evaluation model for power outages, including a data acquisition module, a data processing module, an evaluation standard module, and a risk calculation module;

[0040] The data acquisition module is used to obtain relevant environmental data around the pole, and the relevant environmental data includes: air pollution data, soil resistance data and soil acid-base data;

[0041] The data processing module includes a cleaning unit and a quantification unit. The cleaning unit is used to perform data cleaning processing on the relevant environmental data to obtain first environmental data; the quantification unit performs risk quantification calculation based on the first environmental data to obtain first risk data;

[0042] The evaluation standard module performs risk classification processing on the power outage risk based on the first risk data to obtain a power outage risk evaluation table;

[0043] The risk calculation module performs power outage risk calculation based on the first risk data and the power outage risk assessment table to obtain a power outage risk quantification index and a power outage risk assessment result.

[0044] In a third aspect, the present application provides an electronic device, comprising a processor and a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps in the above method are performed.

[0045] In a fourth aspect, the present application provides a storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps in the above method are performed.

[0046] Beneficial effects of the present invention: The present invention obtains relevant environmental data around the electric pole, and the relevant environmental data include: air pollution data, soil resistance data and soil acid-base data; performs data cleaning processing on the relevant environmental data to obtain first environmental data, performs risk quantification calculation based on the first environmental data to obtain first risk data; performs risk classification processing on the power outage risk based on the first risk data to obtain a power outage risk evaluation table; performs power outage risk calculation based on the first risk data and the power outage risk evaluation table to obtain a power outage risk quantification index and a power outage risk evaluation result; the air pollutant concentration and soil characteristic data related to the power outage risk can be fully integrated and utilized, and the air pollutant concentration and soil characteristic data can be used to accurately analyze and quantify the power outage risk;

[0047] The present invention takes into account multiple factors such as atmospheric pollutant concentration, soil resistivity and soil pH. These factors are interrelated and influence each other in the actual operation of the power system. By considering these factors at the same time, the power outage risk can be evaluated more comprehensively, avoiding the one-sidedness of single-factor analysis. Each risk factor and the comprehensive power outage risk are evaluated by quantifying each risk factor, making the risk assessment more accurate. By calculating the risk weight and corresponding risk index of each factor, it can be determined which factors play a leading role in the power outage risk under specific circumstances. The power outage risk calculation table is used to calculate the power outage risk, which can more carefully characterize the power outage probability under different risk factor combinations, more accurately reflect the relationship between risk factors, and quantify the comprehensive power outage risk, making the risk assessment result more intuitive and specific. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 is a functional block diagram of the system of the present invention;

[0049] Figure 2 is a flow chart of the steps of the method of the present invention;

[0050] Figure 3 The soil acid-base data cleaning flow chart of the present invention;

[0051] Figure 4 is a risk calculation flow chart of the present invention;

[0052] Figure 5 It is a schematic structural diagram of the electronic device of the present invention. DETAILED DESCRIPTION

[0053] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0054] Example 1, please refer to Figure 1 As shown, the present application provides a system for constructing a multi-dimensional comprehensive analysis and quantitative evaluation model for power outages, including a data acquisition module, a data processing module, an evaluation standard module, and a risk calculation module;

[0055] The data acquisition module is used to obtain relevant environmental data around the poles, including: air pollution data, soil resistance data, and soil acid-base data;

[0056] The data collection module is configured with a data collection strategy, which includes:

[0057] The sulfur dioxide concentration, nitrogen oxide concentration and particulate matter concentration in the air around the pole are collected at a first time interval, and the collection time is recorded and marked as air pollution data. The first time interval is t1. In this embodiment, the first time interval t1 is 1 hour, so that the changes in the concentration of air pollutants in one day can be captured, including the difference between day and night, the changes under different meteorological conditions, etc.

[0058] The resistivity of the soil in four directions around the pole grounding wire is obtained at the second time interval. When obtaining, measurement points are selected in the four directions of each pole tower base, namely, east, south, west and north. The distance between the measurement points and the edge of the pole grounding wire is generally 1-3 meters. In this way, the distribution of the soil resistivity around the pole grounding wire can be obtained. At each measurement point, starting from the surface, a measurement is performed at a certain depth, such as 0.5-1 meter, until the expected maximum depth, such as 3-5 meters, is reached. Then, the average value is calculated as the final data of this measurement point, and the acquisition time is recorded and marked as soil resistance data. The second time interval is t2. In this embodiment, the second time interval t2 is 1 month. The soil resistivity is relatively stable in the short term, but with seasonal changes and fluctuations in groundwater levels, the soil resistivity will gradually change. Measuring once a month can better track these changes.

[0059] The pH value of the soil in four directions around the pole is obtained at a third time interval. The process of obtaining the pH value is similar to measuring the soil resistivity. The measuring point is generally rotated to be 0.5-1.5 meters away from the edge of the pole grounding wire. At each measuring point, starting from the surface, the pH value of the soil is collected once every 0.2-0.3 meters until a certain depth, such as 1-2 meters. Then the average value is calculated as the final data of this measuring point, and the time of acquisition is recorded and marked as soil pH data. The third time interval is t3. In this embodiment, the third time interval t3 is 3 months. The pH value of the soil changes relatively slowly. The measurement frequency of once every 3 months can effectively monitor its long-term change trend, while also taking into account the balance between cost and workload.

[0060] In the specific implementation process, pollutants in the atmosphere will gradually deposit on the surface of the pole insulators. As the pollutants accumulate, the insulation resistance of the insulators will decrease to form a conductive channel. When the leakage current reaches a certain level, a flashover phenomenon will occur, that is, the air on the surface of the insulator is broken down, causing a line short circuit or grounding fault, thereby causing a power outage. When the soil is polluted, the resistivity of the soil will change. The grounding resistance is closely related to the soil resistivity. If the grounding resistance is too large, it will affect the dissipation capacity of the grounding system and increase the shell potential of the electrical equipment. For example, in a substation, if the grounding resistance is increased from the design requirement of 0.5 ohms to 5 ohms, when a power outage occurs, When a ground short circuit occurs, the voltage on the equipment casing may increase several times, which not only threatens the safety of personnel, but may also damage the insulation of electrical equipment, leading to power outages. The acidic substances in soil pollution will corrode the concrete and metal parts in the pole foundation. For example, when the pH value of the soil drops from 7 to around 4, the strength of the concrete may drop by 30%-50%. For metal embedded parts in the pole tower foundation, such as anchor bolts, electrochemical corrosion will occur in the acidic soil environment, resulting in reduced strength and inability to effectively fix the pole tower. When the pole tower is subjected to external forces such as wind and conductor tension, it is easy to tilt or collapse, causing line disconnection and power outages.

[0061] The data processing module includes a cleaning unit and a quantification unit. The cleaning unit is used to perform data cleaning processing on the relevant environmental data to obtain first environmental data; the quantification unit performs risk quantification calculation based on the first environmental data to obtain first risk data;

[0062] The cleaning unit configures the data cleaning strategy, which includes: air pollution data cleaning: based on the air pollution data, the mean μi and standard deviation σi of sulfur dioxide concentration, nitrogen oxide concentration and particulate matter concentration are calculated in the first time period, and the concentration data exceeding the normal pollution range is marked as abnormal concentration data. The normal pollution range is [μi-3*σi, μi+3*σi]; for abnormal concentration data, the weighted average of the same type of concentration data collected at the first n collection moments and the last n collection moments is used to replace it; the cleaned air pollution data is marked as the first pollution data. According to; In this embodiment, n is equal to 2, that is, when the weighted average is performed using the first two data and the last two data of the abnormal concentration data, the closer the data in time distance is, the greater the weight is. For example, a certain section of data is 0.52, 0.58, 0.95, 0.57, 0.55, of which 0.95 is the abnormal concentration data, then 0.58 is closest to 0.57, and a weight of 0.3 is given, and the remaining two data are given a weight of 0.2, and 0.3*0.58+0.3*0.57+0.2*0.52+0.2*0.55=0.559 is calculated, and 0.95 is replaced by 0.559;

[0063] Soil resistance data cleaning: Based on the resistivity of the soil in four directions collected at the same collection time, the average resistivity μ2 and the resistivity standard deviation σ2 of the four resistivities are calculated, and the resistivity data exceeding the normal resistance range is marked as abnormal resistivity data. The normal resistivity range is [μ2-σ2, μ2+σ2]. Because the resistivity of the soil in four directions should be basically the same under normal circumstances, the normal resistivity range is generally small; if the number of abnormal resistivity data in the resistivity of the soil in four directions collected at the same collection time is greater than or equal to two, that is, more than half of the data are abnormal resistivity data, then the soil resistance data collected at the collection time is marked as invalid data and re-collected; otherwise, for abnormal resistivity data, that is, when only one data is abnormal resistivity data, use the non-abnormal resistivity data at the same collection time to calculate the average value for replacement; mark the cleaned soil resistance data as the first resistance data;

[0064] Soil acid-base data cleaning: please refer to Figure 3 As shown, based on the soil pH values ​​collected in four directions at the same collection time, if the soil pH values ​​in the four directions all exceed the first soil pH value range, the soil pH data collected at the collection time is marked as invalid data and re-acquired. The first soil pH value range is [3, 10]. In terms of pH value, the normal soil pH value range is between 4.5 and 8.5. The pH value of contaminated acidic soil can be less than 4.5 and greater than 9, and generally will not exceed 3-10. If the soil pH value obtained for the second time still exceeds the first soil pH value range, it can be recorded as normal data.

[0065] Otherwise, calculate the average pH value μ3 and the pH standard deviation σ3 of the four pH values, and mark the pH data that exceeds the normal pH range as abnormal pH data, and the normal pH range is [μ3-σ3, μ3+σ3]; if the number of abnormal pH data in the pH values ​​of the soil in the four directions collected at the same collection time is greater than or equal to 2, then mark the soil pH data collected at the collection time as invalid data and re-acquire it, otherwise, for the abnormal pH data, use the non-abnormal pH data at the same collection time, calculate the average value and replace it; mark the cleaned soil pH data as the first pH data;

[0066] marking the first pollution data, the first resistance data, and the first acid-base data as first environment data;

[0067] The quantification unit is configured with a quantification strategy, which includes: atmospheric pollution risk calculation: based on the first pollution data, the pollution loads of sulfur dioxide, nitrogen oxides and particulate matter are calculated respectively by the pollution load calculation formula, and the pollution load calculation formula is as follows: PL = C*k, where PL is the pollution load, C is the normalized sulfur dioxide concentration or nitrogen oxide concentration or particulate matter concentration, and k is the proportional coefficient, because the influence of pollutant concentration on power outage risk is different under different seasonal temperatures, and it can be adjusted according to actual conditions. In this embodiment, k = 1;

[0068] The obtained sulfur dioxide pollution load is recorded as PL1, the nitrogen oxide pollution load is recorded as PL2, and the particulate matter pollution load is recorded as PL3;

[0069] The air pollution risk index PA is calculated based on the sulfur dioxide pollution load PL1, the nitrogen oxide pollution load PL2 and the particulate matter pollution load PL3. The air pollution risk index calculation formula is as follows: For example, PL1 = 0.71, PL2 = 0.54, PL3 = 0.83, then PA = √(0.71^2+0.54^2+0.83^2) = 1.22;

[0070] Soil resistance risk calculation: Based on the first resistance data, according to the relationship model between soil resistivity and grounding resistance, the grounding resistance of the pole grounding wire in four directions is calculated respectively, and the maximum grounding resistance is extracted by comparison, recorded as Rm; the design rated value of the pole grounding resistance is obtained, recorded as Rr, and the local lightning activity intensity coefficient of the pole, recorded as KL; then the soil resistance risk index PB is calculated. The soil resistance risk index calculation formula is as follows: Common soil resistivity and ground resistance relationship models include uniform soil model and double-layer soil model. In this embodiment, the uniform soil model is used. The uniform soil model formula is: Where R is the grounding resistance, β is the soil resistivity, L is the length of the grounding body, and d is the diameter of the grounding body; the lightning activity intensity coefficient is an indicator used to measure the frequency and intensity of lightning activity in a certain area, which can be determined based on local lightning statistical data. In this embodiment, KL is 8.52;

[0071] Soil acid-base risk calculation: obtain the appropriate pH range of the pole material, recorded as [PH1, PH2]. In this embodiment, [PH1, PH2] is [6, 8];

[0072] Based on the first resistance data, the acid-base deviation MC of the soil pH in four directions around the pole is calculated according to the acid-base deviation calculation formula. The acid-base deviation calculation formula is as follows: Where PH0 is the soil pH actually measured, for example, [PH1, PH2] is [6, 8], PHO is 5, then MC = (6-5) / (8-2) = 0.5; then the average pH deviation is calculated based on the pH deviation MC of the soil pH in four directions around the pole to obtain the soil pH risk index PC;

[0073] The air pollution risk index, soil resistance risk index and soil acid-base risk index are marked as the first risk data;

[0074] In the specific implementation process, the comprehensive risk index of atmospheric pollutants is calculated, and the square root of the sum of squares is used to take into account the comprehensive impact of the synergy between different pollutants on the risk; for example, assuming that there are two atmospheric pollutants, if they are simply added together to calculate the comprehensive risk, the possibility that they may interact to enhance the risk is ignored, and the mutual offset of risk contributions is avoided, and the sensitivity to high-risk pollutants is higher; when the risk contribution of a certain pollutant suddenly increases, the comprehensive risk index will have a more obvious change; and the use of quantitative methods to evaluate each risk factor makes risk assessment more accurate.

[0075] The evaluation standard module performs risk classification processing on the power outage risk based on the first risk data to obtain a power outage risk evaluation table;

[0076] The evaluation standard module is configured with an evaluation standard establishment strategy, which includes: setting the weight of the air pollution risk index to Q1, the weight of the soil resistivity risk index to Q2, and the weight of the soil acid-base risk index to Q3, Q1+Q2+Q3=1; setting the seasonal environmental impact factor to Q0, because seasonal changes have an impact on air pollution, soil resistivity and soil acidity, so all seasonal environmental impact factors are added; in this embodiment, Q1 is 0.4, Q2 is 0.5, Q3 is 0.1, and Q0 is 1.0;

[0077] The risk standards of the air pollution risk index, the soil resistance risk index and the soil acid-base risk index are set respectively, and the risk standards include: low risk standard, medium risk standard, medium-high risk standard and high risk standard; recorded as A{1, 2, 3, 4}, B{1, 2, 3, 4}, C{1, 2, 3, 4}, wherein A, B and C represent the air pollution risk, the soil resistance risk and the soil acid-base risk in order, respectively, and 1, 2, 3 and 4 represent the low risk standard, the medium risk standard, the medium-high risk standard value and the high risk standard in order, respectively; for example, A2 represents the medium risk standard of air pollution, based on A{1, 2, 3, 4}, B{1, 2, 3, 4} and C{1, 2, 3, 4}, A, B and C are arranged in order from top to bottom, and 1, 2, 3 and 4 are arranged in order from left to right to establish a table, which is marked as a power outage risk evaluation table. In this embodiment, the power outage risk evaluation table is shown in Table 1;

[0078] Table 1 Power outage risk assessment table

[0079] Low risk criteria Medium risk standard Medium and high risk standards High risk standards Air pollution risk 0.10 0.20 0.30 0.50 Soil resistance risk 0.25 0.35 0.5 0.65 Soil acidity and alkalinity risk 0.25 0.4 0.60 0.70

[0080] In the specific implementation process, insulator flashover and other faults caused by air pollution occur from time to time, and grounding faults caused by abnormal soil resistivity are also one of the common faults of transmission lines. Power outages caused by corrosion of tower foundations and grounding devices caused by soil acidity and alkalinity are relatively rare, so Q2>Q1>Q3; the determination of weights and risk standards can be based on statistical analysis of historical data, for example, the air pollution conditions, soil resistivity data, and soil acidity and alkalinity information at the time of each accident; it can also be determined through experiments and simulation studies.

[0081] See also Figure 4 As shown, the risk calculation module performs power outage risk calculation based on the first risk data and the power outage risk evaluation table to obtain a power outage risk quantitative index and a power outage risk evaluation result;

[0082] The risk calculation module is configured with a risk calculation strategy, which includes: Q1, Q2, Q3 and Q0 form a risk weight vector, recorded as QL = Q0*{Q1, Q2, Q3}; in this embodiment, QL = {0.4, 0.5, 0.1};

[0083] Construct the attribution function of the air pollution risk index, the soil resistivity risk index and the soil acid-base risk index. In this embodiment, the attribution function formula is as follows: Where U represents the degree of attribution, x represents the actual data value, y and z represent the risk standard; based on the attribution function and the power outage risk evaluation table, the degrees of attribution of the air pollution risk index, soil resistance risk index and soil acid-base risk index in the corresponding risk standards are calculated respectively, and the calculation results are combined into a matrix, marked as the power outage risk evaluation matrix, recorded as PP = {a1, a2, a3, a4; b1, b2, b3, b4; c1, c2, c3, c4}, where a, b, c correspond to the degrees of attribution of the air pollution risk index, soil resistance risk index and soil acid-base risk index in the corresponding risk standards in order; before calculating the degree of attribution, the first risk data needs to be normalized and the data size therein is scaled to [0, 1] to meet the risk standard; for example, the air pollution risk index is 0.12, that is, x = 0.12, based on the risk standard of air pollution in Table 1, So a1 = (0.2-0.12) / (0.2-0.1) = 0.8, a2 = (0.12-0.1) / (0.2-0.1) = 0.2, a3 = 0, a4 = 0;

[0084] Multiply the risk weight vector QL by the power outage risk evaluation matrix PP to obtain the power outage risk vector QT. For example, PP = {0.8, 0.2, 0, 0; 0, 0.45, 0.55, 0; 0, 0, 0.7, 0.3}, QL = {0.4, 0.5, 0.1}, then QT = QL*PP = {0.32, 0.305, 0.345, 0.03}. Set the risk score based on the risk standard, that is, set each risk standard In this embodiment, the low risk standard is 10 points, the medium risk standard is 7 points, the medium-high risk standard is 4 points, and the high risk standard is 0 points. The power outage risk quantitative index is calculated based on the power outage risk vector QT and the risk score; for example, QT = {0.32, 0.305, 0.345, 0.03}, then the power outage risk quantitative index is 0.32*10+0.305*7+0.345*4+0.03*0=6.17;

[0085] Extract all components in the power outage risk vector QT, compare the component sizes, and obtain the maximum component. According to the position of the maximum component in QT, the power outage risk assessment result is obtained, where positions 1, 2, 3, and 4 represent low risk, medium risk, medium-high risk, and high risk, respectively; for example, QT = {0.32, 0.305, 0.345, 0.03}, the maximum component is 0.345 at position 3, and the assessment result is medium-high risk;

[0086] In the specific implementation process, the status of risk factors is often not absolute, but rather ambiguous. Traditional methods may simply divide risk factors into discrete categories for evaluation. However, by constructing a power outage risk assessment matrix, the degree of attribution of each risk factor to different risk standards is fully considered. For example, for the risk of atmospheric pollutant concentration, it is not a simple matter of determining whether it is low risk, medium risk, or high risk, but rather the possibility of it belonging to each risk level to varying degrees at the same time is allowed, which is more in line with the actual situation. Moreover, the interrelationships between various risk factors and their joint impact on the comprehensive power outage risk are comprehensively considered. For example, even if a certain risk factor may be in a relatively low risk state when viewed alone, if other risk factors contribute more to the comprehensive power outage risk, through calculation, the final comprehensive evaluation vector will reasonably reflect this comprehensive impact, making the assessment of the comprehensive power outage risk more comprehensive.

[0087] Example 2, please refer to Figure 2 As shown, the present application provides a method for constructing a multi-dimensional comprehensive analysis and quantitative evaluation model for power outages, comprising the following steps:

[0088] Step S1, obtaining relevant environmental data around the electric pole, the relevant environmental data including: air pollution data, soil resistance data and soil acid-base data; Step S1 includes the following sub-steps:

[0089] Step S101, collecting sulfur dioxide concentration, nitrogen oxide concentration and particulate matter concentration in the air around the pole at a first time interval, and recording the collection time, marked as air pollution data, the first time interval is t1;

[0090] Step S102, obtaining the resistivity of the soil in four directions around the pole grounding wire at a second time interval, and recording the time of obtaining, marked as soil resistance data, the second time interval is t2;

[0091] Step S103, obtaining the pH value of the soil in four directions around the pole at a third time interval, and recording the time of obtaining, marked as soil pH data, the third time interval is t3.

[0092] Step S2, performing data cleaning processing on the relevant environmental data to obtain first environmental data, and performing risk quantification calculation based on the first environmental data to obtain first risk data; Step S2 includes the following sub-steps:

[0093] Step S201, air pollution data cleaning: based on the air pollution data, the mean μi and standard deviation σi of sulfur dioxide concentration, nitrogen oxide concentration and particulate matter concentration are calculated in the first time period, and the concentration data exceeding the normal pollution range is marked as abnormal concentration data. The normal pollution range is [μi-3*σi, μi+3*σi];

[0094] Step S202: For abnormal concentration data, replace the data by weighted average using the same type of concentration data collected at the first n collection moments and the last n collection moments; mark the cleaned atmospheric pollution data as the first pollution data;

[0095] Step S203, soil resistance data cleaning: based on the soil resistivity in four directions collected at the same collection time, the average resistivity μ2 and the resistivity standard deviation σ2 of the four resistivities are calculated, and the resistivity data exceeding the normal resistance range is marked as abnormal resistivity data. The normal resistivity range is [μ2-σ2, μ2+σ2];

[0096] Step S204: if the number of abnormal resistivity data in the resistivity of the soil in four directions collected at the same collection time is greater than or equal to two, the soil resistance data collected at the collection time is marked as invalid data and re-collected; otherwise, for the abnormal resistivity data, the non-abnormal resistivity data at the same collection time is used to calculate the average value for replacement; the cleaned soil resistance data is marked as the first resistance data;

[0097] Step S205, soil acid-base data cleaning: based on the soil acid-base values ​​in four directions collected at the same collection time, if the soil acid-base values ​​in the four directions all exceed the first soil acid-base value range, the soil acid-base data collected at the collection time is marked as invalid data and re-acquired. The first soil acid-base value range is [3, 10];

[0098] Step S206, otherwise, the average pH value μ3 and the pH standard deviation σ3 of the four pH values ​​are calculated, and the pH data exceeding the normal pH range are marked as abnormal pH data, and the normal pH range is [μ3-σ3, μ3+σ3];

[0099] Step S207: if the number of abnormal pH data in the pH values ​​of the soil in the four directions collected at the same collection time is greater than or equal to 2, the soil pH data collected at the collection time is marked as invalid data and re-acquired; otherwise, for the abnormal pH data, the average value is calculated and replaced by the non-abnormal pH data at the same collection time; the cleaned soil pH data is marked as the first pH data;

[0100] Step S208, marking the first pollution data, the first resistance data, and the first acid-base data as first environment data;

[0101] Step S209, air pollution risk calculation: based on the first pollution data, the pollution loads of sulfur dioxide, nitrogen oxides and particulate matter are calculated respectively by the pollution load calculation formula, and the pollution load calculation formula is as follows: PL = C*k, wherein PL is the pollution load, C is the normalized sulfur dioxide concentration or nitrogen oxide concentration or particulate matter concentration, and k is the proportionality coefficient. The obtained sulfur dioxide pollution load is recorded as PL1, the nitrogen oxide pollution load is recorded as PL2, and the particulate matter pollution load is recorded as PL3;

[0102] Step S210, calculate the air pollution risk index PA based on the sulfur dioxide pollution load PL1, the nitrogen oxide pollution load PL2 and the particulate matter pollution load PL3. The air pollution risk index calculation formula is as follows:

[0103] Step S211, soil resistance risk calculation: based on the first resistance data, according to the relationship model between soil resistivity and grounding resistance, the grounding resistances of the pole grounding wire in four directions are calculated respectively, and the maximum grounding resistance is extracted by comparison, which is recorded as Rm; the design rated value of the pole grounding resistance is obtained, which is recorded as Rr, and the local lightning activity intensity coefficient of the pole, which is recorded as KL; and then the soil resistance risk index PB is calculated. The soil resistance risk index calculation formula is as follows:

[0104] Step S212, soil acid-base risk calculation: obtain the appropriate pH range of the pole material, recorded as [PH1, PH2], and calculate the acid-base deviation MC of the soil pH in four directions around the pole based on the first resistance data according to the acid-base deviation calculation formula. The acid-base deviation calculation formula is as follows: PH0 is the soil pH actually measured, and then the average pH deviation is calculated based on the pH deviation MC of the soil pH in four directions around the pole to obtain the soil pH risk index PC;

[0105] Step S213, marking the air pollution risk index, the soil resistivity risk index and the soil acid-base risk index as first risk data.

[0106] Step S3, performing risk classification processing on the power outage risk based on the first risk data to obtain a power outage risk evaluation table; Step S3 includes the following sub-steps:

[0107] Step S301, setting the weight of the air pollution risk index to Q1, the weight of the soil resistance risk index to Q2, the weight of the soil acid-base risk index to Q3, Q1+Q2+Q3=1; setting the seasonal environmental impact factor to Q0;

[0108] Step S302, respectively setting risk standards for the air pollution risk index, the soil resistance risk index, and the soil acid-base risk index, the risk standards including: low risk standard, medium risk standard, medium-high risk standard, and high risk standard; denoted as A{1, 2, 3, 4}, B{1, 2, 3, 4}, C{1, 2, 3, 4}, wherein A, B, and C represent the air pollution risk, the soil resistance risk, and the soil acid-base risk, respectively, and 1, 2, 3, and 4 represent the low risk standard, the medium risk standard, the medium-high risk standard value, and the high risk standard, respectively;

[0109] Step S303, based on A{1, 2, 3, 4}, B{1, 2, 3, 4} and C{1, 2, 3, 4}, create a table with A, B and C in order from top to bottom and 1, 2, 3 and 4 in order from left to right, marked as a power outage risk assessment table.

[0110] Step S4, calculating the power outage risk based on the first risk data and the power outage risk assessment table to obtain a power outage risk quantification index and a power outage risk assessment result; Step S4 includes the following sub-steps:

[0111] Step S401, Q1, Q2, Q3 and Q0 form a risk weight vector, recorded as QL = Q0*{Q1, Q2, Q3};

[0112] Step S402, constructing the attribution function of the air pollution risk index, the soil resistance risk index and the soil acid-base risk index, and calculating the attribution degree of the air pollution risk index, the soil resistance risk index and the soil acid-base risk index in the corresponding risk standards based on the attribution function and the power outage risk evaluation table, and forming the calculation results into a matrix, marked as the power outage risk evaluation matrix, recorded as PP = {a1, a2, a3, a4; b1, b2, b3, b4; c1, c2, c3, c4}, where a, b, c correspond to the attribution degree of the air pollution risk index, the soil resistance risk index and the soil acid-base risk index in the corresponding risk standards in order;

[0113] Step S403, multiplying the risk weight vector QL by the power outage risk evaluation matrix PP to obtain a power outage risk vector QT, setting a risk score based on the risk standard, and then calculating a power outage risk quantitative index based on the power outage risk vector QT and the risk score;

[0114] Step S404, extract all components in the power outage risk vector QT, and compare the component sizes to obtain the maximum component. According to the position of the maximum component in QT, the power outage risk assessment result is obtained, where positions 1, 2, 3 and 4 represent low risk, medium risk, medium-high risk and high risk respectively.

[0115] Example 3, please refer to Figure 5 As shown, Figure 5 The structural schematic diagram of an electronic device is illustrated, and the electronic device may include: a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus. The memory stores computer-readable instructions, and the processor may call the instructions in the memory. When the computer-readable instructions are executed by the processor, the steps in a method for constructing a multi-dimensional comprehensive analysis and quantitative evaluation model for power outage are executed to achieve the following functions: obtaining relevant environmental data around the pole, the relevant environmental data including: atmospheric pollution data, soil resistance data and soil acid-base data; performing data cleaning processing on the relevant environmental data to obtain first environmental data, performing risk quantification calculation based on the first environmental data to obtain first risk data; performing risk classification processing on the power outage risk based on the first risk data to obtain a power outage risk evaluation table; performing power outage risk calculation based on the first risk data and the power outage risk evaluation table to obtain a power outage risk quantification index and a power outage risk evaluation result.

[0116] In addition, the logic instructions in the above-mentioned memory can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art, and the computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk.

[0117] Embodiment 4, the present application also provides a computer-readable storage medium, the present application provides a storage medium, on which a computer program is stored, and when the computer program is executed by the processor, the steps in the above method for constructing a multi-dimensional comprehensive analysis and quantitative evaluation model for power outages are executed to achieve the following functions: obtaining relevant environmental data around the poles, the relevant environmental data including: atmospheric pollution data, soil resistance data, and soil acid-base data; performing data cleaning processing on the relevant environmental data to obtain first environmental data, performing risk quantification calculation based on the first environmental data to obtain first risk data; performing risk classification processing on the power outage risk based on the first risk data to obtain a power outage risk evaluation table; performing power outage risk calculation based on the first risk data and the power outage risk evaluation table to obtain a power outage risk quantification index and a power outage risk evaluation result.

[0118] Through the description of the above implementation methods, the embodiments of the present invention can be provided as methods, systems or computer program products. Based on such an understanding, the above technical solutions can be essentially or partly contributed to the prior art in the form of software products, which can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and include several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0119] In the embodiments provided in the present application, it should be understood that the disclosed system or method can be implemented in other ways. The embodiments described above are merely schematic. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation. For example, multiple modules or units can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of systems, modules and units can be electrical, mechanical or other forms.

[0120] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for constructing a multi-dimensional comprehensive analysis and quantitative evaluation model for power outages, characterized in that: The steps include: Obtain relevant environmental data around the poles, including: air pollution data, soil resistance data, and soil acid-base data; Performing data cleaning processing on the relevant environmental data to obtain first environmental data, and performing risk quantification calculation based on the first environmental data to obtain first risk data; Perform risk classification processing on the power outage risk based on the first risk data to obtain a power outage risk evaluation table; The power outage risk is calculated based on the first risk data and the power outage risk assessment table to obtain a power outage risk quantification index and a power outage risk assessment result.

2. The method for constructing a multi-dimensional comprehensive analysis and quantitative evaluation model for power outages according to claim 1 is characterized in that: Obtaining relevant environmental data of the transmission line includes the following sub-steps: The sulfur dioxide concentration, nitrogen oxide concentration and particulate matter concentration in the air around the electric pole are collected at a first time interval, and the collection time is recorded and marked as air pollution data. The first time interval is t1; Obtain the resistivity of the soil in four directions around the pole grounding wire at a second time interval, and record the time of acquisition, marked as soil resistance data, and the second time interval is t2; The pH value of the soil in four directions around the pole is obtained at a third time interval, and the time of acquisition is recorded and marked as soil pH data. The third time interval is t3.

3. The method for constructing a multi-dimensional comprehensive analysis and quantitative evaluation model for power outages according to claim 2 is characterized in that: Performing data cleaning on the relevant environmental data to obtain the first environmental data includes the following sub-steps: Air pollution data cleaning: Based on air pollution data, the mean μi and standard deviation σi of sulfur dioxide concentration, nitrogen oxide concentration and particulate matter concentration are calculated in the first time period, and the concentration data exceeding the normal pollution range is marked as abnormal concentration data. The normal pollution range is [μi-3*σi, μi+3*σi]. For abnormal concentration data, the weighted average of the same type of concentration data collected at the first n collection moments and the last n collection moments is used to replace it. The cleaned air pollution data is marked as the first pollution data. Soil resistance data cleaning: Based on the resistivity of the soil in four directions collected at the same collection time, the average resistivity μ2 and the resistivity standard deviation σ2 of the four resistivities are calculated, and the resistivity data exceeding the normal resistance range is marked as abnormal resistivity data. The normal resistivity range is [μ2-σ2, μ2+σ2]. If the number of abnormal resistivity data in the resistivity of the soil in four directions collected at the same collection time is greater than or equal to two, the soil resistance data collected at the collection time is marked as invalid data and re-collected; otherwise, for the abnormal resistivity data, the non-abnormal resistivity data at the same collection time is used to obtain the average value for replacement; the cleaned soil resistance data is marked as the first resistance data.

4. The method for constructing a multi-dimensional comprehensive analysis and quantitative evaluation model for power outages according to claim 3 is characterized in that: Performing data cleaning on the relevant environmental data to obtain the first environmental data also includes the following sub-steps: Soil acid-base data cleaning: Based on the soil acid-base values ​​in four directions collected at the same collection time, if the soil acid-base values ​​in the four directions all exceed the first soil acid-base range, the soil acid-base data collected at the collection time will be marked as invalid data and re-acquired. The first soil acid-base range is [3, 10]; Otherwise, calculate the average pH value μ3 and the pH standard deviation σ3 of the four pH values, and mark the pH data that exceeds the normal pH range as abnormal pH data, and the normal pH range is [μ3-σ3, μ3+σ3]; if the number of abnormal pH data in the pH values ​​of the soil in the four directions collected at the same collection time is greater than or equal to 2, then mark the soil pH data collected at the collection time as invalid data and re-acquire it, otherwise, for the abnormal pH data, use the non-abnormal pH data at the same collection time, calculate the average value and replace it; mark the cleaned soil pH data as the first pH data; The first pollution data, the first resistance data, and the first acid-base data are marked as first environment data.

5. The method for constructing a multi-dimensional comprehensive analysis and quantitative evaluation model for power outages according to claim 4 is characterized in that: Performing risk quantification calculation based on the first environment data to obtain the first risk data includes the following sub-steps: Calculation of air pollution risk: Based on the first pollution data, the pollution loads of sulfur dioxide, nitrogen oxides and particulate matter are calculated respectively by the pollution load calculation formula. The pollution load calculation formula is as follows: PL = C*k, where PL is the pollution load, C is the normalized sulfur dioxide concentration or nitrogen oxide concentration or particulate matter concentration, and k is the proportionality coefficient. The obtained sulfur dioxide pollution load is recorded as PL1, the nitrogen oxide pollution load is recorded as PL2, and the particulate matter pollution load is recorded as PL3; The air pollution risk index PA is calculated based on the sulfur dioxide pollution load PL1, the nitrogen oxide pollution load PL2 and the particulate matter pollution load PL3. The air pollution risk index calculation formula is as follows:

6. The method for constructing a multi-dimensional comprehensive analysis and quantitative evaluation model for power outages according to claim 5 is characterized in that: Performing risk quantification calculation based on the first environment data to obtain the first risk data also includes the following sub-steps: Soil resistance risk calculation: Based on the first resistance data, according to the relationship model between soil resistivity and grounding resistance, the grounding resistance of the pole grounding wire in four directions is calculated respectively, and the maximum grounding resistance is extracted by comparison, recorded as Rm; the design rated value of the pole grounding resistance is obtained, recorded as Rr, and the local lightning activity intensity coefficient of the pole, recorded as KL; then the soil resistance risk index PB is calculated. The soil resistance risk index calculation formula is as follows: Soil acid-base risk calculation: Obtain the appropriate pH range of the pole material, recorded as [PH1, PH2]. Based on the first resistance data, calculate the acid-base deviation MC of the soil pH in four directions around the pole according to the acid-base deviation calculation formula. The acid-base deviation calculation formula is as follows: PH0 is the soil pH actually measured, and then the average pH deviation is calculated based on the pH deviation MC of the soil pH in four directions around the pole to obtain the soil pH risk index PC; The air pollution risk index, soil resistivity risk index and soil acid-base risk index are marked as the first risk data.

7. The method for constructing a multi-dimensional comprehensive analysis and quantitative evaluation model for power outages according to claim 6 is characterized in that: Performing risk classification processing on the power outage risk based on the first risk data to obtain a power outage risk evaluation table includes the following sub-steps: Set the weight of the air pollution risk index to Q1, the weight of the soil resistance risk index to Q2, and the weight of the soil acid-base risk index to Q3, Q1+Q2+Q3=1; Set the seasonal environmental impact factor to Q0; The risk standards for the air pollution risk index, soil resistance risk index and soil acid-base risk index are set respectively, and the risk standards include: low risk standard, medium risk standard, medium-high risk standard and high risk standard; denoted as A{1, 2, 3, 4}, B{1, 2, 3, 4}, C{1, 2, 3, 4}, where A, B and C represent the air pollution risk, soil resistance risk and soil acid-base risk in order, respectively, and 1, 2, 3 and 4 represent the low risk standard, medium risk standard, medium-high risk standard value and high risk standard in order; Based on A{1, 2, 3, 4}, B{1, 2, 3, 4} and C{1, 2, 3, 4}, A, B and C are arranged in order from top to bottom, and 1, 2, 3 and 4 are arranged in order from left to right to create a table, which is marked as a power outage risk assessment table.

8. The method for constructing a multi-dimensional comprehensive analysis and quantitative evaluation model for power outages according to claim 7 is characterized in that: Calculating the power outage risk based on the first risk data and the power outage risk assessment table to obtain a power outage risk quantification index and a power outage risk assessment result includes the following sub-steps: Q1, Q2, Q3 and Q0 form a risk weight vector, denoted as QL = Q0*{Q1, Q2, Q3}; The attribution functions of the air pollution risk index, soil resistance risk index and soil acid-base risk index are constructed. Based on the attribution function and the power outage risk evaluation table, the attribution degrees of the air pollution risk index, soil resistance risk index and soil acid-base risk index in the corresponding risk standards are calculated respectively, and the calculation results are organized into a matrix, marked as the power outage risk evaluation matrix, denoted as PP = {a1, a2, a3, a4; b1, b2, b3, b4; c1, c2, c3, c4}, where a, b, and c correspond to the attribution degrees of the air pollution risk index, soil resistance risk index and soil acid-base risk index in the corresponding risk standards, respectively.

9. The method for constructing a multi-dimensional comprehensive analysis and quantitative evaluation model for power outages according to claim 8, characterized in that: Calculating the power outage risk based on the first risk data and the power outage risk assessment table to obtain the power outage risk quantification index and the power outage risk assessment result also includes the following sub-steps: Multiply the risk weight vector QL by the power outage risk evaluation matrix PP to obtain the power outage risk vector QT, set the risk score based on the risk standard, and then calculate the power outage risk quantitative index based on the power outage risk vector QT and the risk score; All components in the power outage risk vector QT are extracted, and the component sizes are compared to obtain the maximum component. According to the position of the maximum component in QT, the power outage risk assessment result is obtained, where positions 1, 2, 3, and 4 represent low risk, medium risk, medium-high risk, and high risk, respectively.

10. A system for constructing a multi-dimensional comprehensive analysis and quantitative evaluation model for power outages, applicable to a method for constructing a multi-dimensional comprehensive analysis and quantitative evaluation model for power outages according to any one of claims 1 to 9, characterized in that: It includes data collection module, data processing module, evaluation criteria module and risk calculation module; The data acquisition module is used to obtain relevant environmental data around the pole, and the relevant environmental data includes: air pollution data, soil resistance data and soil acid-base data; The data processing module includes a cleaning unit and a quantification unit. The cleaning unit is used to perform data cleaning processing on the relevant environmental data to obtain first environmental data; the quantification unit performs risk quantification calculation based on the first environmental data to obtain first risk data; The evaluation standard module performs risk classification processing on the power outage risk based on the first risk data to obtain a power outage risk evaluation table; The risk calculation module performs power outage risk calculation based on the first risk data and the power outage risk assessment table to obtain a power outage risk quantification index and a power outage risk assessment result.

Images