Electric power multiple risk assessment identification and early warning method, system, equipment and medium

Abstract

The invention discloses an electric power multiple risk assessment identification and early warning method, system and device and a medium, and belongs to the technical field of electric power system safety operation and maintenance, and the method comprises the steps: obtaining meteorological events and fault events, and carrying out the statistics of the number of times of the meteorological events and the fault events; calculating association strength through the number of times of the meteorological events and the fault events, and predicting the probability of occurrence of the fault events according to the key meteorological data through a machine learning model; calculating a comprehensive risk value and determining a risk level by combining consequences caused by equipment faults; generating early warning information according to the comprehensive risk value and the corresponding fault event; according to the invention, weather forecast and meteorological disaster early warning technologies are combined, so that the advancement of risk early warning is realized; the risk level is adjusted and evaluated according to real-time monitoring data, it is ensured that early warning information and extreme weather evolution are synchronous, and the problems that traditional early warning is high in static performance, obvious in hysteresis and lack of pertinence are solved.

Description

Technical Field

[0001] This invention relates to the field of power system safety operation and maintenance technology, specifically to a method, system, equipment, and medium for power multi-risk assessment, identification, and early warning. Background Technology

[0002] As a crucial infrastructure for national economic development, the safe and stable operation of the power system is directly related to social and economic order and the protection of people's lives. However, with the intensification of global climate change, the frequency and intensity of extreme weather events such as severe convective weather, heavy rainfall, typhoons, and snow disasters have increased significantly, posing a serious threat to the safe operation of the power system, especially the distribution network. Extreme weather can not only cause direct damage to power facilities such as transmission line breaks, tower collapses, and equipment short circuits, but also trigger problems such as short-term load surges and sharp drops in renewable energy generation, resulting in an imbalance between power supply and demand, and even causing large-scale power outages.

[0003] Traditional power system risk assessment methods have significant limitations: early deterministic assessments fail to reflect the probabilistic nature of faults; while subsequent probabilistic assessments introduce reliability indicators, they neglect the severity of the consequences. There is a lack of risk warnings for low-probability but high-loss fault types; existing studies often use single indicators such as the number of broken lines and collapsed towers, failing to comprehensively consider the multi-dimensional impacts of socio-economic losses and user outage duration. Extreme weather can trigger disaster chains, such as heavy rainfall causing geological disasters and secondary power outages; existing methods struggle to generate early warning information related to these disaster chains. As a critical link directly facing users, the dynamic risk assessment and rapid early warning of the distribution network are core requirements for ensuring power supply reliability. Therefore, multi-risk assessment, identification, and early warning technologies for distribution networks in response to extreme weather are of great significance for improving the disaster prevention and mitigation capabilities of the power grid and ensuring the resilience of the power system. Summary of the Invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problem solved by this invention is that traditional power system risk assessment cannot reflect the probabilistic attributes of faults; although subsequent probabilistic assessments introduce reliability indicators, they ignore the severity of the impact of accident consequences; existing studies mostly use single indicators such as the number of broken lines and the number of collapsed towers, and fail to comprehensively consider the impact of socio-economic losses, power outage time for users, etc.

[0006] To address the aforementioned technical problems, this invention provides the following technical solution: a method for identifying and issuing early warnings of multiple risks in the power sector, comprising the following steps: Collect historical meteorological data and historical fault data, classify them to obtain meteorological events and fault events, and count the number of meteorological events and fault events; The correlation strength is calculated by the number of meteorological events and failure events, and key meteorological data that need to be focused on are identified. The probability of failure events is predicted based on key meteorological data using machine learning models; The consequences of equipment failure are assessed, and a comprehensive risk value is calculated and a risk level is determined based on the probability of the failure event. Early warning information is generated based on the comprehensive risk value and the corresponding failure event.

[0007] In a preferred embodiment of the power multi-risk assessment, identification, and early warning method of the present invention, the step of counting the number of meteorological events and fault events includes: Collect historical meteorological data, categorize it into severe convection, heavy rainfall, typhoons, and snow and ice disasters, and output it as meteorological events; Collect historical fault data and classify it into tower collapse, conductor breakage, conductor icing, and abnormal load fluctuation, and output it as fault events. Count the number of times each type of meteorological event and fault event occurs individually, and also count the number of times meteorological events and fault events occur together.

[0008] As a preferred embodiment of the power multi-risk assessment, identification, and early warning method of the present invention, the step of determining the key meteorological data requiring attention includes: The correlation strength between each meteorological event and failure event is calculated by the number of meteorological events and failure events. The correlation strength is compared with the set correlation strength threshold. If the correlation strength is greater than the set threshold, the meteorological event corresponding to the correlation strength is a key meteorological event that needs to be paid attention to in the case of the fault event. If the correlation strength is less than or equal to the set threshold, then the meteorological event corresponding to the correlation strength is not a fault event and is a key meteorological data that needs to be monitored.

[0009] The beneficial effects of this preferred solution are as follows: by calculating the correlation strength, key meteorological events are identified, meteorological information is detected in a targeted manner, the relevance of early warning information is increased, and computing resources are used rationally; it provides accurate input for subsequent machine learning models to predict fault probabilities, conduct risk assessments and early warnings, thereby improving the relevance and efficiency of power multi-risk identification and helping the power grid to prevent and control meteorological fault risks in advance.

[0010] As a preferred embodiment of the power multi-risk assessment, identification, and early warning method of the present invention, the step of predicting the probability of a fault event based on key meteorological data using a machine learning model includes: Using meteorological data related to key meteorological events as input and the probability of the corresponding fault events as output, a machine learning model is trained. Acquire meteorological data and input it into a trained machine learning model to predict the probability of each type of failure event.

[0011] As a preferred embodiment of the power multi-risk assessment, identification, and early warning method of the present invention, the step of calculating the comprehensive risk value and determining the risk level includes: The impact of the failure event is assessed to determine the severity of the impact; The overall risk value is calculated based on the probability and severity of the failure event. Set a risk threshold, and determine the risk level based on the comparison between the comprehensive risk value and the risk threshold.

[0012] The advantages of this preferred solution are: adjusting the risk level assessment based on real-time monitoring data to ensure that early warning information is synchronized with the evolution of extreme weather, thus solving the problems of strong staticity and significant lag in traditional early warning systems; it can scientifically quantify the risk level of power failures, achieve graded risk management, and improve the power system's ability to prevent and control multiple risks and its emergency response efficiency.

[0013] As a preferred embodiment of the power multi-risk assessment, identification, and early warning method of the present invention, the step of generating early warning information based on the comprehensive risk value and the corresponding fault event includes: Determine the impact of the failure event based on historical data of the failure event, and output the risk type; Risk types are categorized according to risk level, and early warning information is generated.

[0014] The benefits of this preferred solution are: it enables maintenance personnel to develop targeted prevention and control strategies, effectively reduces the threat of extreme weather to the safe operation of the distribution network, and provides strong technical support for improving the power grid's disaster prevention and mitigation capabilities and ensuring power supply reliability.

[0015] In a preferred embodiment of the power multi-risk assessment, identification, and early warning method of the present invention, the formula for calculating the correlation strength between each meteorological event and fault event is as follows: ; in, Let i represent the correlation strength between meteorological event i and fault event j. This represents the number of times meteorological event i and fault event j occur together. This represents the number of times weather event i occurs alone. This represents the number of times fault event j occurs alone.

[0016] This invention provides a power multiple risk assessment, identification, and early warning system.

[0017] To solve the above-mentioned technical problems, the present invention further provides the following technical solution: a power multi-risk assessment, identification and early warning system, comprising: a data acquisition module: collecting historical meteorological data and historical fault data, classifying them to obtain meteorological events and fault events, and counting the number of meteorological events and fault events; The first data calculation module calculates the correlation strength by the number of meteorological events and failure events, and identifies key meteorological data that needs attention. Machine Learning Module: Predicts the probability of malfunction events based on key meteorological data using machine learning models; The second data calculation module assesses the consequences of equipment failures, calculates a comprehensive risk value based on the probability of the failure event, and determines the risk level. Early warning generation module: Generates early warning information based on the comprehensive risk value and the corresponding fault event.

[0018] The present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, characterized in that the processor, when executing the computer program, implements the steps of a method for identifying and warning of multiple risks in power.

[0019] The present invention provides a computer-readable storage medium having a computer program stored thereon, characterized in that the computer program, when executed by a processor, implements the steps of a method for identifying and warning of multiple risks in power.

[0020] The beneficial effects of this invention are as follows: This invention adjusts and assesses risk levels based on real-time monitoring data, ensuring that early warning information is synchronized with the evolution of extreme weather, thus solving the problems of traditional early warning systems being highly static and significantly lagging; it identifies key meteorological events by calculating correlation strength, enabling targeted monitoring of meteorological information, increasing the relevance of early warning information, and making rational use of computing resources; the early release of early warning information ensures rapid delivery of information, buying valuable time for emergency response; it enables maintenance personnel to develop targeted prevention and control strategies, effectively reducing the threat of extreme weather to the safe operation of the distribution network, and providing strong technical support for improving the power grid's disaster prevention and mitigation capabilities and ensuring power supply reliability. Attached Figure Description

[0021] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 The above is a flowchart of a method for identifying and warning of multiple risks in the power industry, provided as an embodiment of the present invention. Detailed Implementation

[0023] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0024] Example 1, referring to Figure 1 This is the first embodiment of the present invention, which provides a method for identifying and warning of multiple risks in the power sector, including: S100: Collect historical meteorological data and historical fault data, classify them to obtain meteorological events and fault events, and count the number of meteorological events and fault events; S200: Calculate the correlation strength by the number of meteorological events and failure events, and identify key meteorological data that need to be monitored; S300: Predicts the probability of malfunction events based on key meteorological data using machine learning models; S400: Assess the consequences of equipment failure, calculate the overall risk value and determine the risk level by combining the probability of the failure event; S500: Generates early warning information based on the comprehensive risk value and the corresponding fault event.

[0025] It should be noted that existing power distribution networks rely on limited historical statistics for fault probability analysis when dealing with extreme weather, lacking high-precision modeling and simulation support. This leads to inaccurate early warnings in the face of low-probability, high-impact events. Existing studies often use single indicators such as the number of broken lines and collapsed towers, failing to comprehensively consider the impact of socio-economic losses and user power outage duration. Furthermore, the early warning mechanism is statically lagging and cannot dynamically adjust its level according to weather changes, resulting in weak emergency response capabilities. Therefore, it is crucial to propose a multi-risk assessment, identification, and early warning method for the power industry.

[0026] Therefore, to address the aforementioned issues of power grid risk assessment, identification, and early warning, a new power grid risk assessment, identification, and early warning method is constructed through steps S100-S500. This method adjusts the risk assessment level based on real-time monitoring data, ensuring that early warning information is synchronized with the evolution of extreme weather, thus solving the problems of traditional early warning systems being highly static and exhibiting significant delays. By calculating correlation strength, key meteorological events are identified, and targeted meteorological information is detected, increasing the relevance of early warning information and making rational use of computing resources. Early warning information is released in advance, ensuring rapid delivery and buying valuable time for emergency response. This enables maintenance personnel to develop targeted prevention and control strategies, effectively reducing the threat of extreme weather to the safe operation of the distribution network and providing strong technical support for improving the power grid's disaster prevention and mitigation capabilities and ensuring power supply reliability.

[0027] Example 2, refer to Figure 1 This is the second embodiment of the present invention, which provides a method for identifying and warning of multiple risks in the power industry.

[0028] In this embodiment of the application, the step S100 of counting the number of meteorological events and fault events includes the following steps A1 to A3: A1: Collect historical meteorological data, divide the historical meteorological data into severe convection, heavy rainfall, typhoon, and snow and ice disasters, and output them as meteorological events; In this application embodiment, historical meteorological data of a certain region over the past three years are collected, including temperature, rainfall, wind speed, and snow depth; Periods with wind speeds exceeding level 8 and short-term rainfall exceeding 20 mm / h are classified as severe convective weather. Periods with 24-hour rainfall exceeding 50 mm or short-term rainfall exceeding 30 mm / h are classified as heavy rainfall weather. The period when the local wind speed exceeds 32.7 m / s due to the impression of a typhoon is classified as typhoon weather; Weather with temperatures below 0°C and snowfall greater than 5 mm, and freezing rain lasting for more than 1 hour, are classified as snow and ice disaster weather. Severe convection, heavy rainfall, typhoons, and snow and ice disasters are classified as meteorological events.

[0029] A2: Collect historical fault data, classify historical fault data into tower collapse, conductor breakage, conductor icing, and abnormal load fluctuation, and output as fault events; In this application embodiment, historical fault data of a certain region over the past three years are collected, including tower tilt angle, whether the tower has completely collapsed, whether the conductor has broken, conductor ice thickness, load fluctuation and duration; A tower tilting angle greater than 15° or a tower that has completely collapsed is classified as a tower tilting situation. The occurrence of a broken wire is classified as a broken wire. Cases where the ice thickness on the conductor exceeds 10 mm are classified as conductor ice accumulation. A situation where the regional load deviates from the predicted value by more than 15% and lasts for more than 30 minutes is classified as an abnormal load fluctuation. Tower collapse, conductor breakage, conductor icing, and abnormal load fluctuations are output as fault events.

[0030] A3: Count the number of times each type of meteorological event and fault event occurs individually, and count the number of times meteorological events and fault events occur together.

[0031] In the embodiments of this application, in the historical meteorological data and historical fault data of a certain region over the past three years, the number of times snow and ice disasters occurred alone was 7, the number of times conductor icing occurred alone was 8, and the number of times snow and ice disasters and conductor icing occurred together was 21. Typhoon weather occurred alone 17 times, power line icing occurred alone 27 times, and typhoon weather and power line icing occurred together 2 times.

[0032] In this embodiment of the application, the determination of key meteorological data requiring attention in step S200 includes the following steps B1 to B3: B1: Calculate the correlation strength between each meteorological event and failure event based on the number of meteorological events and failure events; In this embodiment of the application, the formula for calculating the correlation strength between each meteorological event and the fault event is as follows: ; in, Let i represent the correlation strength between meteorological event i and fault event j. This represents the number of times meteorological event i and fault event j occur together. This represents the number of times weather event i occurs alone. The number of times fault event j occurs alone; In the embodiments of this application, in the historical meteorological data and historical fault data of a certain region over the past three years, the number of times snow and ice disasters occurred alone was 7, the number of times conductor icing occurred alone was 8, and the number of times snow and ice disasters and conductor icing occurred together was 21. Substituting into the correlation strength calculation formula, the correlation strength between snow and ice disasters and conductor icing was calculated to be 2.81. In the historical meteorological data and historical fault data of a certain region over the past three years, typhoon weather occurred alone 17 times, conductor icing occurred alone 27 times, and typhoon weather and conductor icing occurred together 2 times. Substituting these data into the correlation strength calculation formula, the correlation strength between typhoon and conductor icing is calculated to be 0.09.

[0033] In one optional implementation, the correlation strength between each meteorological event and the fault event is calculated using a chi-square test analysis. The analysis examines the correlation between strong convection and tower collapse in a certain region, and counts the number of tower collapses when strong convection occurs, the number of towers that do not collapse when strong convection occurs, the number of tower collapses when there is no strong convection, and the number of towers that do not collapse when there is no strong convection. The chi-square value is then calculated to determine the correlation, where a larger chi-square value indicates a stronger correlation between strong convection and tower collapse.

[0034] In another optional implementation, the correlation strength between each meteorological event and the failure event is calculated using a relative risk level. This involves comparing the probability of a failure event occurring when a meteorological event occurs with the probability of a failure event occurring when the meteorological event does not occur. The ratio of these two probabilities is used to measure the correlation strength between the meteorological event and the failure event. The number of times a meteorological event occurs alone, the number of times a failure event occurs alone, the number of times both occur together, and the total number of samples are counted. Then, the probability of a failure event occurring when a meteorological event occurs and the probability of a failure event occurring when the meteorological event does not occur are calculated separately. Dividing these two probabilities by the relative risk level indicates a stronger correlation between the meteorological event and the failure event.

[0035] B2: Compare the correlation strength with the set correlation strength threshold. If the correlation strength is greater than the set threshold, the meteorological event corresponding to the correlation strength is a key meteorological event that needs to be paid attention to in the case of the fault event. In this embodiment of the application, the correlation strength threshold is set to 1; The correlation strength between snow and ice disasters and conductor icing is 2.81, which is greater than the correlation strength threshold, indicating that snow and ice disasters are a key meteorological event that needs attention when monitoring conductor icing. When training the machine learning model in the future, the probability of conductor icing must be predicted by taking snow and ice disaster conditions as input.

[0036] B3: If the correlation strength is less than or equal to the set threshold, then the meteorological event corresponding to the correlation strength is not a fault event and is a key meteorological data that needs to be monitored.

[0037] In this embodiment of the application, the correlation strength threshold is set to 1; The correlation strength between typhoons and power line icing is 0.09, which is less than the correlation strength threshold, indicating that typhoons are not a key meteorological event to watch for when power line icing occurs. Therefore, when training the machine learning model, typhoon occurrences will not be included in the training to predict the probability of power line icing.

[0038] In this embodiment of the application, step S300, which uses a machine learning model to predict the probability of a failure event based on key meteorological data, includes the following steps C1~C2: C1: Use meteorological data related to key meteorological events as input and the probability of the corresponding fault events as output to train a machine learning model; In this embodiment of the application, the machine learning model selected is the BP neural network model; Taking the prediction of the probability of conductor icing through snow and ice disasters as an example, we select the temperature, snowfall and freezing rain duration related to snow and ice disasters in the past three years as inputs and the probability of conductor icing as output. We then train a BP neural network model to obtain a BP neural network model that can map snow and ice meteorological data - the probability of icing.

[0039] C2: Acquire meteorological data and input it into a trained machine learning model to predict the probability of each type of failure event.

[0040] In this embodiment of the application, meteorological data of a certain area is monitored in real time, specifically including temperature, snowfall and duration of freezing rain. This meteorological data is input into the BP neural network model trained in step C1. The BP neural network model outputs the probability of conductor icing based on the meteorological data. In the embodiments of this application, the meteorological data acquired at a certain moment includes a temperature of -3°C, a snowfall of 8 mm, a freezing rain duration of 1.5 h, and the BP neural network model outputs a probability of icing on the conductor of 0.85 based on the meteorological data.

[0041] In this embodiment of the application, the calculation of the comprehensive risk value and determination of the risk level in step S400 includes the following steps D1 to D3: In one alternative implementation, the probability of a failure event can also be predicted using a random forest model. Taking the prediction of the probability of a pole collapsing during severe convective weather as an example, wind speed, thunderstorm frequency, and short-duration rainfall related to severe convection over the past three years are selected as inputs, and the probability of pole collapse is used as the output. The random forest model is then trained. This model learns from multiple decision trees to capture the relationship between severe convective weather data and the probability of pole collapse, thus obtaining a random forest model that can map severe convective weather data to the probability of pole collapse.

[0042] In another alternative implementation, the probability of a failure event can be predicted using a support vector machine. Taking the prediction of the probability of a conductor breakage due to snow and ice disasters as an example, the temperature, snow thickness, and ice thickness related to snow and ice disasters in the past three years are selected as inputs, and the probability of conductor breakage is used as the output to train the support vector machine model. Taking advantage of its advantages in small sample and nonlinear scenarios, the relationship between snow and ice meteorological data and the probability of conductor breakage can be fitted to obtain a support vector machine model that can map snow and ice meteorological data to the probability of conductor breakage.

[0043] D1: Assess the impact of the failure event to determine the severity of the impact; In this application embodiment, the assessment of the impact of the failure event includes assigning weights to the equipment damage, economic losses and user power outage time caused by the failure event to calculate the severity of the impact; The formula for calculating the severity of the impact is: ; in, To determine the severity of the impact, For equipment damage weighting coefficient, This is the economic loss weighting coefficient. The power outage time weighting coefficient for users. Assess the equipment damage score. As a score for assessing economic losses, The user's power outage time is assessed with a score, which includes a score for equipment damage assessment, a score for economic loss assessment, and a score for user power outage time assessment. The maximum score is 10 points, and the minimum score is 0 points. The assessment is based on the impact of the fault event. In this embodiment, the weighting coefficient for equipment damage is set to 0.3, the weighting coefficient for economic loss is 0.4, the weighting coefficient for user power outage time is 0.3, the fault event is conductor icing, the equipment damage assessment score is assessed by conductor icing thickness and is set to 6 points, the economic loss assessment score is assessed by de-icing cost and is set to 5 points, and the user power outage loss is assessed by user power outage time and is set to 5 points. Substituting these values ​​into the severity formula, the severity of the impact is calculated to be 5.3.

[0044] In one alternative implementation, the impact of the fault event can be assessed, and the severity of the impact can be obtained through Fault Mode and Effects Analysis (FMA). For tower collapse faults, FMA is conducted to identify the fault mode of tower collapse and assess its impact level on equipment, power supply area, and users, which is divided into minor, moderate, severe, and extremely severe. Combined with the probability level of the fault occurrence, it is divided into low, medium, and high. By using the risk priority number approach of FMA, the severity is determined by focusing only on the impact level.

[0045] In another alternative implementation, the impact of the fault event can be assessed and the severity of the impact can be obtained through a Bayesian network. Taking conductor icing fault as the research object, a Bayesian network containing nodes such as meteorological conditions, equipment status, and operating environment is constructed. The network parameters are trained by using historical fault data, and relevant information of the current fault, such as icing thickness and tower material, is input. Bayesian inference is used to calculate the posterior probability of the impact results such as equipment damage, economic loss, and power outage for users. The severity of the impact is determined based on the concentration and peak value of the probability distribution.

[0046] D2: Calculate the overall risk value based on the probability and severity of the impact of the failure event; In this embodiment of the application, the formula for calculating the comprehensive risk value is: ; in, For the comprehensive risk value, The probability of a fault event occurring for the i-th type of fault event. Let represent the severity of the impact corresponding to the i-th type of fault event, and n represent the possible types of fault events.

[0047] In this embodiment of the application, only one type of fault event, conductor icing, is set to occur. The probability of the conductor icing fault event is 0.85, and the severity of the impact of this conductor icing fault event is 5.3. Substituting these values ​​into the formula for the comprehensive risk value, the comprehensive risk value is calculated to be 4.505.

[0048] In an alternative implementation, the comprehensive risk value can also be calculated through risk coupling, taking into account the interaction and risk superposition effect between different fault events. Taking the scenario where snow and ice disasters simultaneously cause conductor icing and tower collapse as an example, the probability and severity of the occurrence of conductor icing fault and the probability and severity of the occurrence of tower collapse fault are determined separately. Then, a coupling coefficient is introduced to quantify the degree to which the two fault risks mutually reinforce each other. The product of the occurrence probability and the severity of the impact of the two faults is multiplied and summed, and finally the coupling coefficient is calculated. The result is the comprehensive risk value.

[0049] In another alternative implementation, the comprehensive risk value can also be calculated using risk entropy. Risk entropy quantifies the uncertainty of fault risk, and then the comprehensive risk value is derived by combining it with the severity of the impact. First, the three core faults that ice and snow disasters may induce are identified: conductor icing, tower collapse, and conductor breakage. Historical data is collected to determine the probability of each fault occurring, and the severity of the impact of each type of fault is assessed. Then, the risk entropy of the probability distribution of these three types of faults is calculated. The larger the entropy value, the stronger the uncertainty of the fault occurrence. The average severity of the impact of the three types of faults is calculated. Finally, the risk entropy is multiplied by the average severity of the impact, and the result is the comprehensive risk value.

[0050] D3: Set a risk threshold and determine the risk level based on the comparison between the comprehensive risk value and the risk threshold.

[0051] In this application embodiment, the risk value threshold includes a first risk value threshold and a second risk value threshold. When the comprehensive risk value is less than the first risk value threshold, it is a low risk level. When the comprehensive risk value is between the first risk value threshold and the second risk value threshold, it is a medium risk level. When the comprehensive risk value is greater than the second risk value threshold, it is a high risk level. In this embodiment of the application, the first risk threshold is 2, the second risk threshold is 4, when the comprehensive risk value is less than 2, it is a low risk level, when 2 ≤ comprehensive risk value ≤ 4, it is a medium risk level, and when the comprehensive risk value is greater than the second risk threshold, it is a high risk level; step D2 calculates that the comprehensive risk value of this conductor icing is 4.505, which is a high risk level.

[0052] In this embodiment of the application, the step S500 of generating early warning information based on the comprehensive risk value and the corresponding fault event includes the following steps E1~E2: E1: Determine the impact of the failure event based on historical data of the failure event, and output the risk type; In this application embodiment, the impact of conductor icing in historical data of a certain region is obtained. It is found that conductor icing will lead to a decrease in conductor mechanical strength and a reduction in insulation performance, causing line tripping, resulting in power outages for users and increased costs for de-icing operations. Therefore, the risk type is determined to be equipment damage, power outage, and economic loss.

[0053] E2: Classify risk types according to risk level and generate early warning information.

[0054] In this application's implementation, taking the impact of conductor icing as an example, the risk types are equipment damage, power outage, and economic loss. If the risk level is low, in terms of equipment damage, there will be equipment damage due to conductor icing thickness of 3-5mm, and the mechanical strength of the conductor will decrease by less than 10%. The maintenance team to which the line belongs needs to be notified to include the line in the daily inspection plan. In terms of power outage, there will be voltage fluctuations for about 3,000 nearby residents. The power service company needs to remind users to pay attention to the operation of their electrical equipment and report any abnormalities in a timely manner. In terms of economic loss, there will be no significant economic loss. Relevant departments need to send electricity safety tips to users to reduce the cost of reporting internal equipment failures caused indirectly by icing. If the risk level is medium, equipment damage will occur, with ice thickness reaching 6-8mm on the conductors, reducing their mechanical strength by 20%-30%. Maintenance personnel will need to conduct daily ground inspections of the line, focusing on the ice accumulation on tension towers and conductor joints. Regarding power outages, approximately 15,000 households in the vicinity will experience short-term power outages. The power service company needs to remind users to monitor the operation of their electrical equipment, and the distribution maintenance team should prepare emergency generator dispatch, prioritizing power supply to key users such as hospitals and schools. As for economic losses, the cost of de-icing operations is expected to be substantial. The maintenance department needs to optimize the de-icing time to avoid peak electricity consumption periods and reduce additional power loss costs. If the risk level is high, equipment damage will occur, with ice thickness on conductors exceeding 10mm and conductor mechanical strength decreasing by more than 30%. Immediate dispatch of maintenance personnel to conduct detailed inspections of each tower in the affected section is required. Regarding power outages, approximately 30,000 households in the vicinity will experience power outages exceeding one hour. The power service company will need to send outage warning text messages to users in the area, notifying them to prepare backup power supplies in advance. As for economic losses, the cost of ice-melting operations is expected to be substantial, requiring the economic operations department to assist affected businesses and the power grid in developing production adjustment plans. In this embodiment of the application, step D2 calculates the comprehensive risk value of the conductor icing to be 4.505, which is a high-risk level. The early warning information to be generated includes: immediately dispatching the line's maintenance personnel to conduct detailed inspections of each tower in the section; the power service company sending outage warning text messages to approximately 30,000 users in the area, notifying users to prepare backup power in advance; and the economic operation department assisting affected enterprises and the power grid in formulating production adjustment plans.

[0055] Example 3, referring to Figure 1 This is the third embodiment of the present invention, which provides a power multi-risk assessment, identification, and early warning system, including: Data acquisition module: Collects historical meteorological data and historical fault data, classifies them into meteorological events and fault events, and counts the number of meteorological events and fault events; The first data calculation module calculates the correlation strength by the number of meteorological events and failure events, and identifies key meteorological data that needs attention. Machine Learning Module: Predicts the probability of malfunction events based on key meteorological data using machine learning models; The second data calculation module assesses the consequences of equipment failures, calculates a comprehensive risk value based on the probability of the failure event, and determines the risk level. Early warning generation module: Generates early warning information based on the comprehensive risk value and the corresponding fault event.

[0056] Example 4, the fourth embodiment of the present invention, differs from the previous three embodiments in that: if the function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0057] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0058] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0059] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0060] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for identifying and warning of multiple risks in the power sector, characterized in that, include: Collect historical meteorological data and historical fault data, classify them to obtain meteorological events and fault events, and count the number of meteorological events and fault events; The correlation strength is calculated by the number of meteorological events and failure events, and key meteorological data that need to be focused on are identified. The probability of failure events is predicted based on key meteorological data using machine learning models; The consequences of equipment failure are assessed, and a comprehensive risk value is calculated and a risk level is determined based on the probability of the failure event. Early warning information is generated based on the comprehensive risk value and the corresponding failure event.

2. The method for power multi-risk assessment, identification, and early warning as described in claim 1, characterized in that, The steps for counting the number of weather events and malfunction events include: Collect historical meteorological data, categorize it into severe convection, heavy rainfall, typhoons, and snow and ice disasters, and output it as meteorological events; Collect historical fault data and classify it into tower collapse, conductor breakage, conductor icing, and abnormal load fluctuation, and output it as fault events. Count the number of times each type of meteorological event and fault event occurs individually, and also count the number of times meteorological events and fault events occur together.

3. The method for power multi-risk assessment, identification, and early warning as described in claim 2, characterized in that, The steps to identify key meteorological data to focus on include: The correlation strength between each meteorological event and failure event is calculated by the number of meteorological events and failure events. The correlation strength is compared with the set correlation strength threshold. If the correlation strength is greater than the set threshold, the meteorological event corresponding to the correlation strength is a key meteorological event that needs to be paid attention to in the case of the fault event. If the correlation strength is less than or equal to the set threshold, then the meteorological event corresponding to the correlation strength is not a fault event and is a key meteorological data that needs to be monitored.

4. The method for power multi-risk assessment, identification, and early warning as described in claim 3, characterized in that, The steps involved in predicting the probability of a failure event based on key meteorological data using machine learning models include: Using meteorological data related to key meteorological events as input and the probability of the corresponding fault events as output, a machine learning model is trained. Acquire meteorological data and input it into a trained machine learning model to predict the probability of each type of failure event.

5. The method for power multi-risk assessment, identification, and early warning as described in claim 4, characterized in that, The steps for calculating the overall risk value and determining the risk level include: The impact of the failure event is assessed to determine the severity of the impact; The overall risk value is calculated based on the probability and severity of the failure event. Set a risk threshold, and determine the risk level based on the comparison between the comprehensive risk value and the risk threshold.

6. The method for identifying and issuing early warning of multiple risks in the power sector as described in claim 5, characterized in that, The steps for generating early warning information based on the comprehensive risk value and the corresponding fault event include: Determine the impact of the failure event based on historical data of the failure event, and output the risk type; Risk types are categorized according to risk level, and early warning information is generated.

7. The method for power multi-risk assessment, identification, and early warning as described in claim 3, characterized in that, The formula for calculating the correlation strength between each meteorological event and the fault event is as follows: ； in, Let i represent the correlation strength between meteorological event i and fault event j. This represents the number of times meteorological event i and fault event j occur together. This represents the number of times weather event i occurs alone. This represents the number of times fault event j occurs alone.

8. A power multiple risk assessment, identification, and early warning system, employing the power multiple risk assessment, identification, and early warning method as described in any one of claims 1 to 7, characterized in that, include: Data acquisition module: Collects historical meteorological data and historical fault data, classifies them into meteorological events and fault events, and counts the number of meteorological events and fault events; The first data calculation module calculates the correlation strength by the number of meteorological events and failure events, and identifies key meteorological data that needs attention. Machine Learning Module: Predicts the probability of malfunction events based on key meteorological data using machine learning models; The second data calculation module assesses the consequences of equipment failures, calculates a comprehensive risk value based on the probability of the failure event, and determines the risk level. Early warning generation module: Generates early warning information based on the comprehensive risk value and the corresponding fault event.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the power multi-risk assessment, identification, and early warning method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the power multi-risk assessment, identification, and early warning method according to any one of claims 1 to 7.

Images