Power distribution system safety risk identification method and device, power equipment, readable storage medium and program product

Abstract

The invention relates to a power distribution system safety risk identification method and device, power equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring real-time information of a power distribution system; preprocessing the real-time information to improve the quality of the operation information and the environment information; determining a corresponding risk characteristic parameter according to the deviation degree of the preprocessed real-time information relative to the reference information of the power distribution system; inputting the risk characteristic parameters into a preset risk identification model; the risk identification model is obtained by training historical risk characteristic parameters of the power distribution system in a past time period, and is used for identifying the risk of the power distribution system according to the currently input risk characteristic parameters and outputting a first identification result; and performing risk level assessment based on the first identification result to generate a corresponding risk level report, and outputting the risk level report. The method can improve the efficiency and accuracy of power distribution system safety risk identification.

Description

Technical Field

[0001] The present application relates to the field of electric power technology, and in particular to a method, device, electric power equipment, computer-readable storage medium and computer program product for identifying safety risks in a power distribution system. Background Art

[0002] Traditionally, the identification of safety risks in power distribution systems mainly relies on manual inspections and empirical judgments. Although this method can detect and handle some problems to a certain extent, it has defects such as low efficiency, insufficient accuracy, and long response time. Therefore, how to improve the efficiency and accuracy of safety risk identification in power distribution systems is a problem that needs to be solved. Summary of the invention

[0003] Based on this, it is necessary to provide a distribution system safety risk identification method, device, power equipment, computer-readable storage medium and computer program product to address the above-mentioned technical problems, so as to improve the efficiency and accuracy of safety risk identification in the distribution system.

[0004] In a first aspect, the present application provides a method for identifying safety risks of a power distribution system, comprising:

[0005] Obtain real-time information of the power distribution system, including the operation information of the power distribution system and the environment information of the power distribution system;

[0006] Preprocess the real-time information to improve the quality of operation information and environmental information; preprocessing includes cleaning, denoising, fluctuation filtering and standardization;

[0007] According to the degree of deviation between the pre-processed real-time information and the reference information of the power distribution system, the corresponding risk characteristic parameters are determined; the risk characteristic parameters include: current fluctuation rate parameters, voltage deviation parameters, equipment temperature abnormality parameters, vibration amplitude exceeding standard parameters, frequency deviation parameters and environmental humidity abnormality parameters;

[0008] Inputting the risk characteristic parameters into a preset risk identification model; the risk identification model is trained based on the historical risk characteristic parameters of the power distribution system in the past period, and is used to identify the risks existing in the power distribution system according to the currently input risk characteristic parameters and output a first identification result;

[0009] Based on the first identification result, a risk level assessment is performed to generate a corresponding risk level report, and the risk level report is output.

[0010] In one embodiment, the method further comprises:

[0011] Determine the magnitude of the risk characteristic parameter compared to a preset threshold;

[0012] Determine a second recognition result corresponding to the risk feature parameter according to the size comparison result;

[0013] Based on the first identification result, a risk level assessment is performed to generate a corresponding risk level report, including:

[0014] A risk level assessment is performed based on the first recognition result and the second recognition result, and a corresponding risk level report is generated based on the result of the risk level assessment.

[0015] In one embodiment, determining the second recognition result corresponding to the risk feature parameter according to the size comparison includes:

[0016] When the risk characteristic parameter is greater than a preset threshold, it is determined that there is a safety risk in the power distribution system;

[0017] When the risk characteristic parameter is less than or equal to a preset threshold, it is determined that there is no safety risk in the power distribution system.

[0018] In one embodiment, the corresponding risk characteristic parameter is determined according to the degree of deviation of the preprocessed real-time information compared with the reference information of the power distribution system, including:

[0019] Determine the current fluctuation rate parameter: (Imax-Imin) / Iave, where Imax represents the maximum current when the power distribution system is running, Imin represents the minimum current when the power distribution system is running, and Iave represents the reference average current when the power distribution system is running;

[0020] Determine the voltage deviation parameter: (V-Vref) / Vref, where V represents the real-time voltage of the power distribution system, and Vref represents the reference voltage of the power distribution system;

[0021] Determine the equipment temperature anomaly parameter: (T-Tnorm) / Tnorm, where T represents the real-time equipment temperature of the power distribution system and Tnorm represents the reference equipment temperature of the power distribution system;

[0022] Determine the vibration amplitude exceeding the standard parameter: (A-Amax) / Amax, where A represents the real-time vibration amplitude of the power distribution system and Amax represents the maximum vibration amplitude of the power distribution system;

[0023] Determine the frequency deviation parameter: (f-fref) / fref, where f represents the current frequency when the power distribution system is running, and fref represents the reference current frequency of the power distribution system;

[0024] Determine the abnormal ambient humidity parameter: (H-Hnorm) / Hnorm, where H represents the ambient humidity when the power distribution system is running, and Hnorm represents the normal ambient humidity of the power distribution system.

[0025] In one embodiment, based on the first recognition result, a risk level assessment is performed, including:

[0026] Based on the first identification result, determining the risk characteristic result corresponding to each risk characteristic parameter;

[0027] Based on the risk feature results and their corresponding weights, the risk score is determined: ; Among them, RS is the risk score, w i is the weight of the i-th risk feature result, r i is the preset risk value corresponding to the i-th risk characteristic result;

[0028] Based on the risk score, determine the corresponding risk level of the distribution system.

[0029] In one embodiment, the risk levels include level one risk, level two risk, level three risk, and level four risk;

[0030] The method also includes: determining corresponding prevention and control recommendations based on the risk level; wherein,

[0031] Prevention and control recommendations for level 1 risk include regular inspections, equipment maintenance, and risk awareness training for operators;

[0032] Prevention and control recommendations for the secondary risk include strengthening monitoring and early warning of the power distribution system, and developing an emergency response plan;

[0033] Prevention and control recommendations for level 3 risks include taking immediate measures to reduce risks, adjusting operating parameters, and suspending the operation of some equipment;

[0034] Prevention and control recommendations corresponding to level 4 risks include immediately implementing emergency shutdown procedures, launching comprehensive safety inspections and risk assessments.

[0035] In a second aspect, the present application also provides a power distribution system safety risk identification device, comprising:

[0036] An acquisition module is used to acquire real-time information of the power distribution system, including operation information of the power distribution system and environmental information of the power distribution system;

[0037] The parameter determination module is used to pre-process the real-time information to improve the quality of the operation information and the environmental information; the pre-processing includes cleaning, denoising, fluctuation filtering and standardization processing; the corresponding risk characteristic parameters are determined according to the degree of deviation of the pre-processed real-time information compared with the reference information of the power distribution system; the risk characteristic parameters include: current fluctuation rate parameter, voltage deviation parameter, equipment temperature abnormality parameter, vibration amplitude exceeding standard parameter, frequency deviation parameter and environmental humidity abnormality parameter;

[0038] A risk identification module is used to input risk characteristic parameters into a preset risk identification model; the risk identification model is trained based on the historical risk characteristic parameters of the distribution system in the past period, and is used to identify the risks existing in the distribution system according to the currently input risk characteristic parameters and output a first identification result; based on the first identification result, a risk level assessment is performed to generate a corresponding risk level report, and the risk level report is output.

[0039] In a third aspect, the present application further provides an electric power device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method in the first aspect when executing the computer program.

[0040] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of the method in the first aspect when executed by a processor.

[0041] In a fifth aspect, the present application further provides a computer program product, comprising a computer program, which implements the steps of the method in the first aspect when executed by a processor.

[0042] The above-mentioned distribution system safety risk identification method, device, power equipment, computer-readable storage medium and computer program product improve the quality of the real-time information of the distribution system by preprocessing it; determine the corresponding risk characteristic parameters according to the degree of deviation of the preprocessed real-time information compared with the reference information of the distribution system; and input the risk characteristic parameters into a preset risk identification model; and perform risk level assessment according to the first identification result output by the risk identification model to generate and output a corresponding risk level report. In this way, the automatic identification of the safety risks of the distribution system is realized and the identification efficiency of the safety risks of the distribution system is improved; because the risk identification model is trained based on the historical risk characteristic parameters of the distribution system in the past period, it is used to identify the risks existing in the distribution system and output the first identification result according to the currently input risk characteristic parameters, so the obtained first identification result has good accuracy, which helps to improve the accuracy of the identification of the safety risks of the distribution system. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0044] Figure 1 A schematic diagram of a first process of a method for identifying safety risks of a power distribution system in one embodiment;

[0045] Figure 2 A schematic diagram of a second process of a method for identifying safety risks of a power distribution system in one embodiment;

[0046] Figure 3 A third flow chart of a method for identifying safety risks in a power distribution system in one embodiment;

[0047] Figure 4 A schematic diagram of a fourth process of a method for identifying safety risks of a power distribution system in one embodiment;

[0048] Figure 5 It is a structural block diagram of a power distribution system safety risk identification device in one embodiment;

[0049] Figure 6 FIG. 4 is a diagram showing the internal structure of an electric power device in one embodiment. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0051] The section of the power system from the step-down distribution substation (high-voltage distribution substation) to the user end is called the distribution system. The distribution system is a power network system composed of a variety of distribution equipment (or components) and distribution facilities that transforms voltage and directly distributes electric energy to end users. With the development of society and the advancement of science and technology, the complexity of the distribution system has increased, and its safe and stable operation is crucial to safeguarding the national economy and people's lives. However, the distribution system faces various internal and external risks during operation, such as equipment aging, natural disasters, human operational errors, etc. These risks may lead to power supply interruptions and even cause serious safety accidents.

[0052] Traditional methods for identifying and preventing safety risks in power distribution systems mainly rely on manual inspections and empirical judgments. Although this method can detect and handle some problems to a certain extent, it has defects such as low efficiency, insufficient accuracy, and long response time. With the development of information technology, although computer-aided monitoring and automated control have been introduced, there is still a lack of intelligent analysis and real-time early warning capabilities for complex risk factors.

[0053] Although the existing intelligent identification and prevention and control technologies have improved the safety management level of distribution systems to a certain extent, there are still some shortcomings. For example, the real-time and accuracy of data collection and processing are insufficient, the generalization ability of risk assessment models is limited, and the automation and intelligence level of prevention and control measures are not high. These problems limit the further development and application of intelligent identification and prevention and control technologies for safety risks in distribution systems.

[0054] Based on the above analysis, the present application provides a method for identifying safety risks in a power distribution system, in which real-time information of the power distribution system is obtained and preprocessed to obtain real-time information of better quality; corresponding risk characteristic parameters are extracted based on the real-time information, and artificial intelligence model technology is used to analyze the risk characteristics and identify the risks. This is described below through multiple embodiments.

[0055] In one embodiment, Figure 1 As shown, a method for identifying safety risks in a power distribution system is provided. This embodiment uses the method applied to a power distribution system as an example. It can be understood that the method can also be applied to terminals and / or servers involved in the power distribution system. In this embodiment, the method includes the following steps S101 to S105:

[0056] Step S101: Acquire real-time information of a power distribution system, where the real-time information includes operation information of the power distribution system and environmental information of the power distribution system.

[0057] The operation information may be various types of information related to the operation of the power distribution system, such as current, voltage and other related information.

[0058] The environmental information may be information characterizing the actual environment in which the power distribution system is located, such as environmental humidity.

[0059] In some possible embodiments, dedicated sensors may be provided to collect real-time information of the power distribution system.

[0060] In some embodiments, low-power intelligent sensors can be selected and edge computing devices can be used to collect real-time information of the power distribution system. During or after the collection process, the collected raw data can be preliminarily preprocessed to obtain real-time information, which is then transmitted back to the power distribution system. This can reduce the amount of real-time data transmission and improve the real-time data processing capability.

[0061] Step S102: pre-process the real-time information to improve the quality of the operation information and the environmental information; the pre-processing includes cleaning, denoising, fluctuation filtering and standardization.

[0062] In some possible embodiments, data cleaning can be used to remove invalid and erroneous data records in real-time information to ensure the accuracy of real-time information; denoising processing uses filtering algorithms to eliminate noise in real-time information and improve the purity of real-time information; fluctuation filtering uses data mean deviation and standard deviation technology to smooth data fluctuations and reduce the impact of outliers on risk assessment; standardization processing converts data into a unified format and dimension to facilitate subsequent analysis and processing.

[0063] In some embodiments, real-time data may be preprocessed based on a machine learning algorithm to improve the efficiency and quality of the preprocessing.

[0064] Step S103: Determine the corresponding risk characteristic parameters according to the degree of deviation of the preprocessed real-time information compared with the reference information of the power distribution system; the risk characteristic parameters include: current fluctuation rate parameter, voltage deviation parameter, equipment temperature abnormality parameter, vibration amplitude exceeding standard parameter, frequency deviation parameter and ambient humidity abnormality parameter.

[0065] The reference information of the power distribution system may be information corresponding to when the power distribution system is in a normal operating state, thereby providing a corresponding reference function.

[0066] In some embodiments, risk feature parameters may be extracted from real-time information using specific techniques or algorithms, such as data mining techniques, enhanced ensemble learning algorithms, and adaptive K-nearest neighbor algorithms.

[0067] In some possible embodiments, the corresponding degree of deviation can be determined by comparing the preprocessed real-time information with the reference information. For example, the real-time information indicates that the temperature of the distribution cabinet in the power distribution system is 75°C, while the reference information indicates that the temperature of the distribution cabinet is between -10°C and 45°C when the power distribution system is operating normally, so (75-45) = 30°C can be obtained as the corresponding degree of deviation.

[0068] For example, the risk characteristic parameters of the power distribution system can be determined by the degree of deviation, wherein the risk characteristic parameters can be relevant characteristic parameters that characterize the existence of safety risks in the power distribution system.

[0069] Step S104: input the risk characteristic parameters into a preset risk identification model; the risk identification model is trained based on the historical risk characteristic parameters of the distribution system in the past period, and is used to identify the risks existing in the distribution system according to the currently input risk characteristic parameters and output a first identification result.

[0070] The historical risk characteristic parameters may be risk characteristic parameters characterizing the power distribution system acquired in the past period. In some possible embodiments, the power distribution system corresponding to the historical risk characteristic parameters and the power distribution system corresponding to the risk characteristic parameters may be the same power distribution system.

[0071] In some possible embodiments, basic information of the power distribution system, such as the specific number and model of equipment included in the power distribution system, can also be input into the risk identification model, or the risk identification model can obtain the basic information of the power distribution system in real time, so that the first identification result output by the risk identification model can include the risks existing in the power distribution system and the specific equipment information corresponding to the risks.

[0072] In some possible embodiments, the first identification result output by the risk identification model may include specific safety risks existing in the power distribution system, for example, safety risks existing in a specific device or devices in the power distribution system, and specific safety risk data, for example, high temperature risks existing in the distribution cabinet, the temperature is 85 degrees Celsius, and the location, model, maintenance record, etc. of the distribution cabinet.

[0073] In some possible embodiments, blockchain technology can be combined to build a distributed risk identification model to intelligently identify and track distribution system safety risks in real time, ensuring the security and transparency of risk identification.

[0074] Step S105: Based on the first identification result, a risk level assessment is performed to generate a corresponding risk level report, and the risk level report is output.

[0075] Among them, risk level assessment can be to analyze the risks existing in the distribution system and determine the corresponding level.

[0076] For example, through risk level assessment, the magnitude of the risk in the power distribution system can be assessed, thereby generating a corresponding risk level report, and outputting the risk level report for reference by the staff of the power distribution system.

[0077] In this embodiment, the quality of the real-time information of the power distribution system is improved by preprocessing it; the corresponding risk characteristic parameters are determined according to the degree of deviation of the preprocessed real-time information compared with the reference information of the power distribution system; and the risk characteristic parameters are input into a preset risk identification model; and the risk level assessment is performed according to the first identification result output by the risk identification model to generate and output a corresponding risk level report. In this way, the automatic identification of the safety risks of the power distribution system is realized and the efficiency of identifying the safety risks of the power distribution system is improved; because the risk identification model is trained based on the historical risk characteristic parameters of the power distribution system in the past period, it is used to identify the risks existing in the power distribution system according to the currently input risk characteristic parameters and output the first identification result, so the first identification result obtained has good accuracy, which helps to improve the accuracy of identifying the safety risks of the power distribution system.

[0078] In one embodiment, if Figure 2As shown, the power distribution system safety risk identification method in the above embodiment may further include steps S201 to S203, which are specifically as follows:

[0079] Step S201: Determine the comparison between the risk characteristic parameter and a preset threshold value.

[0080] The preset threshold value may be a parameter threshold value of the power distribution system under normal operation, and the corresponding item is the same as the item corresponding to the risk characteristic parameter, so that the preset threshold value and the risk characteristic parameter are comparable. For example, if the risk characteristic parameter includes that the cabinet temperature of the power distribution system is 86°C, then the preset threshold value may be 40°C, and the corresponding items of both are the cabinet temperature of the power distribution system.

[0081] In some embodiments, each collected risk characteristic parameter value is analyzed at a fine-grained level and compared with specific numerical thresholds set in the system to ensure safety. These thresholds are set based on past experience and data analysis to distinguish between normal operating ranges and operating conditions that may cause safety risks.

[0082] Step S202: Determine a second recognition result corresponding to the risk feature parameter according to the size comparison result.

[0083] In some embodiments, if a risk characteristic parameter significantly exceeds the preset normal operating range, this parameter will trigger an additional risk assessment procedure for deeper data analysis. If all parameters are within the preset range, the system will consider the current state to be normal and no further action is required.

[0084] In some possible embodiments, the time corresponding to the size comparison situation may be a specific period of time or multiple time points, for example, the size comparison situation of the cabinet temperature in the power distribution system for 30 consecutive minutes.

[0085] In some possible embodiments, a specific algorithm or condition can be designed to determine the second identification result based on the size comparison. For example, based on the size comparison of the cabinet temperature in the power distribution system for 30 consecutive minutes, multiple differences between the risk characteristic parameters and the preset threshold value can be obtained, and the variance or standard deviation of the multiple differences can be calculated, so as to obtain multiple differences as a set of data fluctuations, and determine the corresponding confidence level based on the fluctuations. For example, the greater the fluctuation, the lower the confidence level. The second identification result is thus determined based on the confidence level. For example, when the confidence level is lower than the preset confidence level, it is not included in the second identification result.

[0086] The “based on the first recognition result, performing risk level assessment to generate a corresponding risk level report” in the aforementioned embodiment may include step S203: performing risk level assessment based on the first recognition result and the second recognition result, and generating a corresponding risk level report based on the result of the risk level assessment.

[0087] In this embodiment, by determining the size comparison of the risk characteristic parameter compared to the preset threshold, and according to the size comparison, the second recognition result corresponding to the risk characteristic parameter is determined. Finally, based on the first recognition result and the second recognition result, the risk level is comprehensively evaluated and a corresponding risk level report is generated. Since the risk level is comprehensively evaluated and the risk level report is generated from the two aspects of the risk identification model and the threshold comparison, the risk identification and evaluation and the generated risk level report are more accurate and comprehensive.

[0088] In one of the embodiments, determining the second identification result corresponding to the risk characteristic parameter based on the size comparison in the aforementioned embodiment may include: when the risk characteristic parameter is greater than a preset threshold, determining that there is a safety risk in the distribution system; when the risk characteristic parameter is less than or equal to the preset threshold, determining that there is no safety risk in the distribution system.

[0089] In some embodiments, when a risk characteristic parameter is greater than a preset threshold, it is determined that there is a safety risk in the power distribution system; when the risk characteristic parameter is greater than the preset threshold, it is clearly pointed out what specific type of safety risk exists, for example: excessive current fluctuation rate may cause system overload, excessive voltage deviation may cause equipment damage, abnormal equipment temperature anomalies may indicate internal component failure, vibration amplitude exceeding the standard may indicate physical structural instability, abnormal frequency deviation may indicate system instability or external interference, and high ambient humidity abnormalities may increase the risk of condensation or short circuit.

[0090] When the risk characteristic parameter is less than or equal to the preset threshold, it is determined that there is no safety risk in the distribution system. When the risk characteristic parameter is less than or equal to the preset threshold, a specific explanation is provided to clearly point out that the distribution system currently has no risk of exceeding the normal operating range and can continue to operate according to the existing monitoring process. It is recommended to regularly check the effectiveness of the threshold setting to ensure long-term safe operation.

[0091] In this embodiment, the risk characteristic parameters are measured by a pre-set threshold value, thereby providing another way to identify the safety risks of the distribution system based on the risk characteristic parameters in addition to the above-mentioned risk identification model, thereby helping to improve the accuracy of risk identification of the distribution system.

[0092] In one embodiment, determining the corresponding risk characteristic parameter according to the deviation degree of the preprocessed real-time information compared with the reference information of the power distribution system in the above embodiment may include:

[0093] Determine the current fluctuation rate parameter: (Imax-Imin) / Iave, where Imax represents the maximum current when the power distribution system is in operation, Imin represents the minimum current when the power distribution system is in operation, and Iave represents the reference average current when the power distribution system is in operation; evaluate the frequency and duration of current fluctuations based on these values ​​to more accurately reflect the impact of current fluctuations on system safety;

[0094] Determine the voltage deviation parameter: (V-Vref) / Vref, where V represents the real-time voltage of the power distribution system and Vref represents the reference voltage of the power distribution system; analyze the time period and frequency of voltage deviation to evaluate the impact of voltage instability on the power distribution system;

[0095] Determine the abnormal equipment temperature parameter: (T-Tnorm) / Tnorm, where T represents the real-time equipment temperature of the power distribution system and Tnorm represents the reference equipment temperature of the power distribution system; combine the equipment's working status and historical temperature data to analyze whether the temperature change is caused by external reasons or is a sign of aging or failure of internal components;

[0096] Determine the vibration amplitude exceeding standard parameter: (A-Amax) / Amax, where A represents the real-time vibration amplitude of the power distribution system and Amax represents the maximum vibration amplitude of the power distribution system. The vibration mode and location need to be considered, because different vibration modes may indicate different potential faults.

[0097] Determine the frequency deviation parameter: (f-fref) / fref, where f represents the current frequency of the power distribution system during operation and fref represents the reference current frequency of the power distribution system. Slight changes in frequency may have a significant impact on the system, especially for load-sensitive or precision equipment, so more detailed monitoring of frequency deviation is required.

[0098] Determine the abnormal ambient humidity parameter: (H-Hnorm) / Hnorm, where H represents the ambient humidity when the power distribution system is running, and Hnorm represents the normal ambient humidity of the power distribution system. The evaluation of humidity anomaly takes into account the influence of factors such as temperature and air pressure to ensure the accuracy of the evaluation results.

[0099] In this embodiment, the above-mentioned specific calculation method helps to accurately determine the specific numerical value corresponding to each risk characteristic parameter, and the determined specific numerical value corresponding to each risk characteristic parameter can more accurately reflect the actual operation of the distribution system.

[0100] In one embodiment, the risk level assessment based on the first identification result in the aforementioned embodiment may include: determining the risk characteristic result corresponding to each risk characteristic parameter based on the first identification result; and determining the risk score according to the risk characteristic result and its corresponding weight: ; Among them, RS is the risk score, w i is the weight of the i-th risk feature result, r i is the preset risk value corresponding to the i-th risk characteristic result; based on the risk score, the corresponding risk level of the distribution system is determined.

[0101] In some possible embodiments, the weight of the risk feature result is calculated as follows: Weight calculation formula: ; Among them, I i is the importance of the ith risk feature result in the system. For example, the importance of the risk feature result in the system can be preset, and the set standard can be adjusted according to actual needs, for example, according to the specific equipment in the distribution system corresponding to the risk feature result

[0102] In this embodiment, the risk characteristic results corresponding to each risk characteristic parameter are determined through the first identification result, and risk scores are performed according to weights, thereby achieving more accurate risk grading according to the risk scores.

[0103] In one of the embodiments, the risk levels in the aforementioned embodiment include level one risk, level two risk, level three risk and level four risk; the distribution system safety risk identification method in the aforementioned embodiment may also include: determining corresponding prevention and control suggestions based on the risk level; wherein, the prevention and control suggestions corresponding to level one risk include regular inspection, maintenance of equipment, and risk awareness training for operators; the prevention and control suggestions corresponding to level two risk include strengthening monitoring and early warning of the distribution system, and formulating an emergency response plan; the prevention and control suggestions corresponding to level three risk include taking immediate measures to reduce risks, adjusting operating parameters, and suspending the operation of some equipment; the prevention and control suggestions corresponding to level four risk include immediately executing emergency shutdown procedures, initiating comprehensive safety inspections and risk assessments.

[0104] In this embodiment, the risk levels are divided into four levels, and different prevention and control suggestions are determined for different levels, so that corresponding prevention and control suggestions can be given based on the identification of the safety risks existing in the distribution system, which helps to timely and accurately discover and deal with the safety risks existing in the distribution system.

[0105] In one embodiment, a method for intelligently identifying and preventing safety risks of a power distribution system is provided, the method comprising:

[0106] Collection steps: Use sensor equipment to obtain detailed information on the real-time operating status of the power distribution system and environmental conditions, including but not limited to current, voltage, equipment temperature, vibration amplitude, frequency and environmental humidity data;

[0107] Data preprocessing step: Perform a series of preprocessing operations on the collected real-time information to improve the quality and reliability of the data, including but not limited to data cleaning, noise elimination, signal fluctuation filtering, and standardization processing required for data analysis;

[0108] Risk characteristic parameter calculation steps: By performing deviation analysis on the pre-processed real-time information and the known reference data of the power distribution system, the risk characteristic parameters of each component of the power distribution system are obtained; these parameters include current fluctuation rate, voltage deviation, equipment temperature anomaly, vibration amplitude exceeding the scale, frequency deviation and ambient humidity anomaly;

[0109] Intelligent risk identification steps: The risk characteristic parameters are used as input items and sent to a pre-trained machine learning risk identification model. The model can accurately identify the potential risks of the distribution system based on the current input parameters and output the identification results.

[0110] Risk assessment step: Based on the identification results of the previous step, further risk level assessment is performed, combined with weight setting, and finally a system risk level report is generated;

[0111] Steps for generating prevention and control recommendations: Based on the resulting risk level, corresponding risk prevention and control guidance is automatically provided. The recommendations are designed to take different safety measures based on the severity of the risk, including routine maintenance, increased monitoring, adjustment of operating parameters, or emergency shutdown.

[0112] In one embodiment, a method for intelligent identification and prevention of power distribution system safety risks is provided. This method is not only applicable to medium-sized urban power distribution systems and large industrial area power distribution systems, but can also be widely used in other power distribution systems that require high reliability and safety, such as data centers, hospitals, airports and other key infrastructure. Figure 3 As shown, the method may include the following steps:

[0113] Step 1: Data collection: Real-time information such as power distribution system operation status data, environmental data, and equipment health status data are collected through sensors. Sensors are installed at key nodes of the power distribution system to monitor current, voltage, temperature, vibration, frequency, ambient humidity, ambient temperature, and equipment operation status parameters in real time. Wireless communication technologies, including LoRa (Long Range Radio), NB-IoT (Narrow Band Internet of Things), and 5G, are used to achieve real-time data transmission and ensure the security and stability of the transmission process.

[0114] Step 2: Data preprocessing: The collected raw data is cleaned, denoised, fluctuation filtered and standardized to improve data quality. Data cleaning removes invalid and erroneous data records to ensure data accuracy; denoising uses filtering algorithms to eliminate noise in the data and improve data purity; fluctuation filtering uses the mean deviation and standard deviation technology of the data to smooth data fluctuations and reduce the impact of outliers on risk assessment; standardization converts the data into a unified format and dimension to facilitate subsequent analysis and processing.

[0115] Step three, feature extraction: use data mining technology to extract risk-related feature parameters (i.e., risk feature parameters) from the preprocessed data. Data mining technology includes ensemble learning algorithm, K-nearest neighbor algorithm, and neural network algorithm to improve the accuracy and efficiency of feature extraction. Feature parameters include current fluctuation rate parameters, voltage deviation parameters, equipment temperature abnormality parameters, vibration amplitude exceeding standard parameters, frequency deviation parameters, and ambient humidity abnormality parameters. The specific calculation method of the above parameters can refer to the relevant technical scheme for determining risk feature parameters in the aforementioned embodiment, which will not be repeated here.

[0116] When the absolute value of any of the above characteristic parameters exceeds the preset threshold, it is considered that there is a risk feature. Among them, when the current fluctuation rate parameter exceeds 10%, the voltage deviation parameter exceeds 5%, the equipment temperature abnormality parameter exceeds 15%, the vibration amplitude exceeds 10%, the frequency deviation parameter exceeds 2%, and the ambient humidity abnormality parameter exceeds 10%, it is considered that there is a risk feature. This corresponds to "determining the size comparison of the distribution system risk characteristic parameter compared to the preset threshold; according to the distribution system size comparison, determining the second identification result corresponding to the distribution system risk characteristic parameter" and other related content.

[0117] Step 4: Risk identification: Based on the extracted characteristic parameters, a risk identification model is constructed to intelligently identify the safety risks of the power distribution system. Figure 4 As shown, a possible method for constructing a risk identification model is provided, which may include the following steps:

[0118] Step 1: Use the extracted feature parameters to establish an initial risk database.

[0119] Step 2, based on the initial risk database and machine learning algorithm, train to obtain a preliminary risk identification model. Exemplarily, a specific machine learning algorithm can be designed, and the initial risk data can be used to build an initial model, that is, a preliminary risk identification model. Of course, an existing model can also be selected, and a specific algorithm can be designed to adaptively adjust the existing model to make it better fit the current distribution system safety risk identification scenario. At the same time, the initial risk data can also be input into the existing model for training to obtain a preliminary risk identification model.

[0120] Step 3: Continuously optimize and adjust model parameters through simulation testing and actual application feedback to improve the recognition accuracy and generalization ability of the model.

[0121] Step 4: Deploy the optimized model to the actual power distribution system for real-time risk identification and early warning. Regularly evaluate and update the risk identification model to ensure that the model can adapt to changes in the distribution system operating environment.

[0122] Step 5, risk assessment: Based on the identification results, the identified risks are classified and assessed, and a corresponding risk level report is provided. The risk level is divided into four levels, from low to high, namely level 1 (low risk), level 2 (medium risk), level 3 (high risk) and level 4 (extremely high risk). The risk level assessment can be carried out in the form of risk scoring. Here, reference can be made to the relevant schemes in the aforementioned embodiments.

[0123] In some possible embodiments, the risk level report may be displayed graphically, including a risk level distribution map, trend map, and heat map, to intuitively display the temporal and spatial distribution characteristics and changing trends of the risk, so as to facilitate decision makers to quickly understand and respond.

[0124] Step 6, risk prevention and control: Based on the risk assessment results, provide corresponding prevention and control suggestions, and automatically generate implementation plans for prevention and control measures. The first-level risk prevention and control suggestions include regular inspection and maintenance of equipment, and risk awareness training for operators; the second-level risk prevention and control suggestions involve strengthening the construction of monitoring and early warning systems, and formulating emergency response plans; the third-level risk prevention and control suggestions include taking immediate measures to reduce risks, adjusting operating parameters and suspending the operation of some equipment; the fourth-level risk prevention and control suggestions require immediate implementation of emergency shutdown procedures and the initiation of comprehensive safety inspections and risk assessments.

[0125] In one embodiment, the method for identifying safety risks of the power distribution system in the above embodiment is used in a power distribution system of a medium-sized city. The power distribution system may cover multiple power distribution substations and multiple power distribution facilities, for example, 200 power distribution substations and 1,000 power distribution facilities, with a wide service range and high requirements for system safety and stability. The specific implementation steps are as follows:

[0126] 1. Data Collection

[0127] (1) Deployment of sensors: Different types of sensors are installed at key nodes of each distribution substation, including current sensors, voltage sensors, temperature sensors, vibration sensors, ambient humidity sensors, and ambient temperature sensors. These sensors are connected to the data acquisition system in the central control room in real time through LoRa and 5G communication technologies to ensure the security and reliability of data transmission.

[0128] (2) Data collection frequency: The sensor’s data collection frequency is set to once per minute. For parameters that change slowly, such as ambient temperature and humidity, the data collection frequency can be appropriately reduced to once every 5 minutes.

[0129] 2. Data preprocessing

[0130] (1) Data cleaning: The collected data first passes through the data cleaning module to remove invalid and erroneous records to ensure the accuracy of the data. For example, abnormal data caused by sensor failure is eliminated.

[0131] (2) De-noising: Use a low-pass filtering algorithm to denoise the current, voltage and vibration data to reduce random noise in the data and improve the purity of the data.

[0132] (3) Fluctuation filtering: Use sliding window technology to calculate the mean and standard deviation of the data, smooth the data with large fluctuations, and reduce the impact of outliers on subsequent analysis. For example, for the current fluctuation rate parameter, a 10-minute sliding window is used for calculation.

[0133] (4) Standardization processing: All data are converted into standardized values ​​between 0 and 1 to ensure that different types of parameters have the same dimension in subsequent analysis.

[0134] 3. Feature extraction

[0135] (1) Data mining technology: Ensemble learning algorithms (such as Random Forest), K-nearest neighbors algorithm (K-NN) and neural network algorithms (such as DNN, deep neural network) are used for feature extraction. These algorithms can extract risk-related feature parameters from large amounts of data.

[0136] (2) Extract current fluctuation rate parameters, voltage deviation parameters, equipment temperature abnormality parameters, vibration amplitude exceeding standard parameters, frequency deviation parameters, and ambient humidity abnormality parameters, and set thresholds: current fluctuation rate parameters exceeding 10%, voltage deviation parameters exceeding 5%, equipment temperature abnormality parameters exceeding 15%, vibration amplitude exceeding standard parameters exceeding 10%, frequency deviation parameters exceeding 2%, and ambient humidity abnormality parameters exceeding 10%.

[0137] (IV) Risk identification

[0138] Build the model:

[0139] (1) Initial risk database: Use the collected characteristic parameters to establish an initial risk database.

[0140] (2) Preliminary model training: The Random Forest algorithm is used to train the initial risk database to form a preliminary risk identification model.

[0141] (3) Model optimization: Continuously optimize and adjust model parameters through simulation tests and actual application feedback. For example, add regularization terms to reduce overfitting, and adjust the number and depth of decision trees to improve the generalization ability of the model.

[0142] (4) Model deployment: Deploy the optimized model to the actual power distribution system for real-time risk identification and early warning.

[0143] (5) Simulation test: Verify the recognition accuracy and response time of the model by simulating different fault scenarios. For example, simulate high-voltage cable failure, transformer overheating and other scenarios.

[0144] (V) Risk Assessment

[0145] (1) The identified risks are evaluated using the following calculation formula: ;

[0146] Among them, w i is the weight of the i-th risk feature result, r i is the risk value of the i-th risk characteristic result.

[0147] (2) The weight calculation method is as follows: Weight calculation formula: ;

[0148] Among them, I i is the importance of the i-th risk feature result in the system.

[0149] (3) Risk level classification:

[0150] Level 1: risk score ≤ 20, low risk;

[0151] Level 2: 20<risk score≤40, medium risk;

[0152] Level 3: 40<risk score≤60, high risk;

[0153] Level 4: Risk score > 60, extremely high risk.

[0154] (VI) Risk prevention and control

[0155] Prevention and control suggestions:

[0156] (1) Level 1: Regularly inspect and maintain equipment and provide risk awareness training to operators.

[0157] (2) Level 2: Strengthen the construction of monitoring and early warning systems and formulate emergency response plans.

[0158] (3) Level 3: Take immediate measures to reduce risks, adjust operating parameters, and suspend the operation of some equipment.

[0159] (4) Level 4: Immediately execute emergency shutdown procedures and initiate comprehensive safety inspections and risk assessments.

[0160] A possible specific implementation is given below:

[0161] (1) Level 1: Set up a regular inspection and maintenance plan, conduct a comprehensive inspection of all equipment every quarter, organize training courses, and conduct risk awareness training for operators every month.

[0162] (2) Level 2: Add more monitoring equipment to the central control room to display changes in key parameters in real time. Develop an emergency response manual to ensure that measures can be taken quickly when medium risks occur.

[0163] (3) Level 3: When a high risk is identified, the central control room immediately notifies the on-site operator to adjust the equipment operating parameters, such as reducing the load or adjusting the working mode of the cooling system. Some high-risk equipment will be suspended to prevent the spread of the fault.

[0164] (4) Level 4: When an extremely high risk is identified, the emergency shutdown procedure is immediately triggered and all related equipment stops operating. At the same time, a comprehensive safety inspection is initiated, including a physical inspection of the equipment and an overall assessment of the system.

[0165] To sum up, the method for identifying safety risks of the distribution system provided in this embodiment has the following beneficial effects: Improved intelligence level: The method of this application can help improve the risk identification accuracy of the distribution system and shorten the response time, thereby improving the intelligence level of the system; Enhanced system stability: By applying the technical solution provided in this embodiment, it is helpful to timely discover and deal with the safety risks of the distribution system, thereby helping to reduce the failure rate of the distribution system and enhance the stability and reliability of the system; Improved management efficiency: Since the technical solution provided in this embodiment realizes the identification of safety risks of the distribution system through automation and intelligence, this can reduce the burden of manual inspection of the distribution system and save labor costs.

[0166] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0167] Based on the same inventive concept, the embodiment of the present application also provides a power distribution system safety risk identification device for implementing the power distribution system safety risk identification method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more power distribution system safety risk identification device embodiments provided below can refer to the limitations of the power distribution system safety risk identification method above, and will not be repeated here.

[0168] In an exemplary embodiment, Figure 5 As shown, a power distribution system safety risk identification device 500 is provided, comprising:

[0169] An acquisition module 501 is used to acquire real-time information of a power distribution system, where the real-time information includes operation information of the power distribution system and environmental information of the power distribution system;

[0170] The parameter determination module 502 is used to pre-process the real-time information to improve the quality of the operation information and the environmental information; the pre-processing includes cleaning, denoising, fluctuation filtering and standardization processing; according to the deviation degree of the pre-processed real-time information compared with the reference information of the power distribution system, the corresponding risk characteristic parameters are determined; the risk characteristic parameters include: current fluctuation rate parameters, voltage deviation parameters, equipment temperature abnormality parameters, vibration amplitude exceeding standard parameters, frequency deviation parameters and environmental humidity abnormality parameters;

[0171] The risk identification module 503 is used to input the risk characteristic parameters into a preset risk identification model; the risk identification model is trained based on the historical risk characteristic parameters of the distribution system in the past period, and is used to identify the risks existing in the distribution system according to the currently input risk characteristic parameters and output a first identification result; based on the first identification result, a risk level assessment is performed to generate a corresponding risk level report, and the risk level report is output.

[0172] In one embodiment, the risk identification module 503 is also used to determine the size comparison of the risk characteristic parameter compared to a preset threshold value; based on the size comparison, determine the second identification result corresponding to the risk characteristic parameter; based on the first identification result, perform a risk level assessment to generate a corresponding risk level report, including: based on the first identification result and the second identification result, perform a risk level assessment to generate a corresponding risk level report.

[0173] In one embodiment, the risk identification module 503 is further used to determine a second identification result corresponding to the risk feature parameter according to the size comparison, including:

[0174] When the risk characteristic parameter is greater than a preset threshold, it is determined that there is a safety risk in the power distribution system;

[0175] When the risk characteristic parameter is less than or equal to a preset threshold, it is determined that there is no safety risk in the power distribution system.

[0176] In one embodiment, the parameter determination module 502 is further configured to determine corresponding risk characteristic parameters according to the degree of deviation between the pre-processed real-time information and the reference information of the power distribution system, including:

[0177] Determine the current fluctuation rate parameter: (Imax-Imin) / Iave, where Imax represents the maximum current when the power distribution system is running, Imin represents the minimum current when the power distribution system is running, and Iave represents the reference average current when the power distribution system is running;

[0178] Determine the voltage deviation parameter: (V-Vref) / Vref, where V represents the real-time voltage of the power distribution system, and Vref represents the reference voltage of the power distribution system;

[0179] Determine the equipment temperature anomaly parameter: (T-Tnorm) / Tnorm, where T represents the real-time equipment temperature of the power distribution system and Tnorm represents the reference equipment temperature of the power distribution system;

[0180] Determine the vibration amplitude exceeding the standard parameter: (A-Amax) / Amax, where A represents the real-time vibration amplitude of the power distribution system and Amax represents the maximum vibration amplitude of the power distribution system;

[0181] Determine the frequency deviation parameter: (f-fref) / fref, where f represents the current frequency when the power distribution system is running, and fref represents the reference current frequency of the power distribution system;

[0182] Determine the abnormal ambient humidity parameter: (H-Hnorm) / Hnorm, where H represents the ambient humidity when the power distribution system is running, and Hnorm represents the normal ambient humidity of the power distribution system.

[0183] In one embodiment, the risk identification module 503 is further used to perform risk level assessment based on the first identification result, including: determining the risk characteristic result corresponding to each risk characteristic parameter based on the first identification result; and determining the risk score according to the risk characteristic result and its corresponding weight: ; Among them, RS is the risk score, w i is the weight of the i-th risk feature result, r i is the preset risk value corresponding to the i-th risk characteristic result; based on the risk score, the corresponding risk level of the distribution system is determined.

[0184] In one of the embodiments, the risk levels include level one risk, level two risk, level three risk and level four risk; the risk identification module 503 is also used to determine corresponding prevention and control suggestions according to the risk level; among them, the prevention and control suggestions corresponding to level one risk include regular inspection, equipment maintenance and risk awareness training for operators; the prevention and control suggestions corresponding to level two risk include strengthening the monitoring and early warning of the distribution system, and formulating an emergency response plan; the prevention and control suggestions corresponding to level three risk include taking immediate measures to reduce risks, adjusting operating parameters and suspending the operation of some equipment; the prevention and control suggestions corresponding to level four risk include immediately executing emergency shutdown procedures, initiating comprehensive safety inspections and risk assessments.

[0185] Each module in the above-mentioned power distribution system safety risk identification device can be implemented in whole or in part by software, hardware and their combination. Each of the above-mentioned modules can be embedded in or independent of the processor in the power equipment in the form of hardware, or can be stored in the memory in the power equipment in the form of software, so that the processor can call and execute the corresponding operations of each of the above modules.

[0186] In an exemplary embodiment, a power device is provided. The power device may be a server, and its internal structure diagram may be as shown in FIG. Figure 6 As shown. The power equipment includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the power equipment is used to provide computing and control capabilities. The memory of the power equipment includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the power equipment is used to store data required for executing the distribution system safety risk identification method, such as real-time information of the distribution system, risk characteristic parameters, etc. The input / output interface of the power equipment is used to exchange information between the processor and the external device. The communication interface of the power equipment is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a distribution system safety risk identification method is implemented.

[0187] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the scheme of the present application, and does not constitute a limitation on the power equipment to which the scheme of the present application is applied. The specific power equipment may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0188] In an exemplary embodiment, an electric power device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0189] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0190] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0191] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0192] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0193] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for identifying safety risks in a power distribution system, characterized in that: include: Acquire real-time information of the power distribution system, wherein the real-time information includes operation information of the power distribution system and environment information of the power distribution system; Preprocessing the real-time information to improve the quality of the operation information and the environmental information; the preprocessing includes cleaning, denoising, fluctuation filtering and standardization; Determining corresponding risk characteristic parameters according to the degree of deviation of the preprocessed real-time information compared with the reference information of the power distribution system; The risk characteristic parameters include: current fluctuation rate parameter, voltage deviation parameter, equipment temperature abnormality parameter, vibration amplitude exceeding standard parameter, frequency deviation parameter and environmental humidity abnormality parameter; Inputting the risk characteristic parameters into a preset risk identification model; the risk identification model is trained based on the historical risk characteristic parameters of the power distribution system in the past period, and is used to identify the risks existing in the power distribution system according to the currently input risk characteristic parameters and output a first identification result; Based on the first identification result, a risk level assessment is performed to generate a corresponding risk level report, and the risk level report is output.

2. The method according to claim 1, characterized in that The method further comprises: Determine the magnitude comparison of the risk characteristic parameter compared to a preset threshold value; Determining a second recognition result corresponding to the risk feature parameter according to the size comparison result; The step of performing risk level assessment based on the first identification result to generate a corresponding risk level report includes: Based on the first recognition result and the second recognition result, a risk level assessment is performed to generate a corresponding risk level report.

3. The method according to claim 2, characterized in that Determining the second recognition result corresponding to the risk feature parameter according to the size comparison includes: When the risk characteristic parameter is greater than the preset threshold, determining that there is a safety risk in the power distribution system; When the risk characteristic parameter is less than or equal to the preset threshold, it is determined that there is no safety risk in the power distribution system.

4. The method according to claim 1, characterized in that The step of determining corresponding risk characteristic parameters according to the degree of deviation between the pre-processed real-time information and the reference information of the power distribution system includes: Determine the current fluctuation rate parameter: (Imax-Imin) / Iave, wherein Imax represents the maximum current when the power distribution system is running, Imin represents the minimum current when the power distribution system is running, and Iave represents the reference average current when the power distribution system is running; Determine the voltage deviation parameter: (V-Vref) / Vref, wherein V represents the real-time voltage of the power distribution system, and Vref represents the reference voltage of the power distribution system; Determine the device temperature anomaly parameter: (T-Tnorm) / Tnorm, where T represents the real-time device temperature of the power distribution system, and Tnorm represents the reference device temperature of the power distribution system; Determine the vibration amplitude exceeding standard parameter: (A-Amax) / Amax, wherein A represents the real-time vibration amplitude of the power distribution system, and Amax represents the maximum vibration amplitude of the power distribution system; Determine the frequency deviation parameter: (f-fref) / fref, wherein f represents the current frequency when the power distribution system is running, and fref represents the reference current frequency of the power distribution system; The abnormal environmental humidity parameter is determined: (H-Hnorm) / Hnorm, wherein H represents the environmental humidity when the power distribution system is running, and Hnorm represents the normal environmental humidity of the power distribution system.

5. The method according to claim 1, characterized in that The performing risk level assessment based on the first identification result includes: Based on the first identification result, determining the risk characteristic result corresponding to each of the risk characteristic parameters; Based on the risk characteristics and their corresponding weights, a risk score is determined: ; Wherein, RS is the risk score, w i is the weight of the i-th risk feature result, r i is the preset risk value corresponding to the i-th risk characteristic result; Based on the risk score, a corresponding risk level of the power distribution system is determined.

6. The method according to claim 5, characterized in that The risk levels include level one risk, level two risk, level three risk and level four risk; The method further includes: determining corresponding prevention and control recommendations according to the risk level; wherein, Prevention and control recommendations for the first-level risk include regular inspections, equipment maintenance, and risk awareness training for operators; The prevention and control suggestions corresponding to the secondary risk include strengthening the monitoring and early warning of the power distribution system and formulating an emergency response plan; The prevention and control suggestions for the three-level risks include taking immediate measures to reduce risks, adjusting operating parameters, and suspending the operation of some equipment; The prevention and control recommendations corresponding to the four levels of risks include immediately implementing emergency shutdown procedures, initiating comprehensive safety inspections and risk assessments.

7. A power distribution system safety risk identification device, characterized in that: The device comprises: An acquisition module, used to acquire real-time information of a power distribution system, wherein the real-time information includes operation information of the power distribution system and environmental information of the power distribution system; A parameter determination module is used to preprocess the real-time information to improve the quality of the operation information and the environmental information; the preprocessing includes cleaning, denoising, fluctuation filtering and standardization processing; according to the deviation degree of the real-time information after preprocessing compared with the reference information of the power distribution system, the corresponding risk characteristic parameters are determined; the risk characteristic parameters include: current fluctuation rate parameter, voltage deviation parameter, equipment temperature abnormality parameter, vibration amplitude exceeding standard parameter, frequency deviation parameter and environmental humidity abnormality parameter; A risk identification module is used to input the risk characteristic parameters into a preset risk identification model; the risk identification model is trained based on the historical risk characteristic parameters of the distribution system in the past period, and is used to identify the risks existing in the distribution system according to the risk characteristic parameters currently input and output a first identification result; based on the first identification result, a risk level assessment is performed to generate a corresponding risk level report, and the risk level report is output.

8. An electric power device, comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images