A power distribution network equipment fire risk assessment method and system

Abstract

The application discloses a kind of power distribution network equipment fire risk assessment method and system, comprising: obtaining power distribution network equipment data and pre-processing data, based on the risk index of power distribution network equipment calculated based on pre-processing result, to identify equipment risk;When the identified power distribution network equipment is high-risk equipment, then risk simulation is carried out in combination with equipment environment characteristics, corresponding maintenance measures are implemented based on the dynamic data of risk simulation;Visual risk simulation data and store evaluation process data.The application combines the comprehensive weight calculation of expert scoring and spherical fuzzy judgment matrix, improves the evaluation accuracy of fire trigger probability, accurately simulates the fire trigger probability and expansion path through fault tree and bayesian network, provides higher priority response and maintenance measures for high-risk equipment, significantly improves the efficiency of fire risk identification and prevention, reduces resource waste, and fully supports the safe operation and maintenance management of power distribution network equipment.

Description

Technical Field

[0001] The present invention relates to the technical field of distribution network risk assessment, and in particular to a distribution network equipment fire risk assessment method and system. Background Art

[0002] Fire risk assessment and fire management for distribution network equipment have always been critical for the safe operation and maintenance of power systems. With the acceleration of urbanization and the increasing complexity of distribution network systems, the operating environment of distribution equipment has become increasingly variable, leading to a greater diversity of fire risk factors. Factors such as the equipment's own temperature, current load, and ambient temperature and humidity can directly or indirectly cause fires. Fire prevention and control often rely on perfluorohexanone fire extinguishing agents. Consequently, traditional fire monitoring and risk assessment technologies are increasingly unable to meet the demands for real-time, high-precision risk identification. Recent advances in intelligent sensing, data analysis, and machine learning have provided opportunities for the development of new methods for distribution network fire risk assessment. By collecting, preprocessing, and performing risk-weighted analysis on sensor data, studying electrical fire mechanisms in different distribution network scenarios and simulating their development, effective fire risk identification has become a key area of ​​focus in distribution network operation and maintenance. Existing methods often rely on single-source monitoring or lack multi-dimensional, comprehensive data, making them incapable of dynamically assessing fire risks in complex environments. In particular, when multiple risk factors interact, traditional approaches struggle to adjust risk assessment results in real time, resulting in delays in the timely identification and management of high-risk equipment. Summary of the Invention

[0003] The purpose of this section is to summarize some aspects of the embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the abstract and title of this application to avoid obscuring the purpose of this section, the abstract and the title of the invention, and such simplifications or omissions should not be used to limit the scope of the present invention.

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

[0005] Therefore, the present invention provides a fire risk assessment method and system for distribution network equipment to solve the problem that existing methods generally rely on single monitoring or lack multi-dimensional comprehensive data, and are unable to dynamically assess fire risks in complex environments. In particular, when multiple risk factors interact, traditional means are difficult to adjust risk assessment results in real time, resulting in high-risk equipment not being identified and processed in a timely manner.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, an embodiment of the present invention provides a method for fire risk assessment of distribution network equipment, comprising:

[0008] Acquiring distribution network equipment data and preprocessing the data, and calculating a distribution network equipment risk index based on the preprocessing results to identify equipment risks;

[0009] When the distribution network equipment is identified as high-risk equipment, risk simulation is performed based on the equipment environment characteristics, and corresponding maintenance measures are implemented based on the dynamic data of the risk simulation;

[0010] Visualize risk simulation data and store assessment process data.

[0011] As a preferred solution of the distribution network equipment fire risk assessment method of the present invention, before calculating the distribution network equipment risk index based on the preprocessing results, the method further includes: the preprocessing results are risk factors, and weights are assigned to different risk factors;

[0012] Establishing spherical fuzzy judgment matrix r=(o ij ), where element o ij It is expressed as a triple: (a ij1 , a ij2 , a ij3 ), where a ij1 is the membership degree, a ij2 Non-membership degree, a ij3 It is the degree of hesitation;

[0013] Calculate the triplet data of each row in the matrix r to generate the preliminary weight value of each risk factor:

[0014]

[0015] Among them, g i is the initial weight of risk factor i, T i is the temperature data corresponding to risk factor i, I j is the current load corresponding to risk factor j, H j is the humidity corresponding to risk factor j, U is the external ambient temperature of the entire device, I is the internal current load of the device, θ ij is the temperature interaction coefficient, δ ij is the current load interaction coefficient, a ij1 , a ij2 and a ij3 is the membership degree, non-membership degree and hesitation degree between risk factor i and risk factor j, and n represents the total number of risk factors.

[0016] As a preferred solution of the distribution network equipment fire risk assessment method of the present invention, it further includes: using the risk factors as nodes of the Bayesian network, and using the weight value corresponding to each risk factor as the initial probability value of each node;

[0017] Dynamically update the conditional probability P(B|A) in the Bayesian network based on real-time collected data:

[0018] P(B|A)=(a′ ij1 , a′ ij2 , a′ ij3 )

[0019] Among them, a′ ij1 It represents the support probability of risk factor B for the overall risk under given condition A, a′ ij2 Indicates the probability of negation of risk factor B on the overall risk under condition A, a′ ij3 It represents the uncertainty probability of risk factor B to the overall risk under condition A;

[0020] Based on the updated conditional probability value, the preliminary weight vector of each node is dynamically adjusted. The dynamic weight value calculation formula of each risk factor is:

[0021] g′ i =g i ·a′ ij1 +(1-g i )·(1-a′ ij2 )+a′ ij3 ·g i ·(1-g i )

[0022] Among them, g′ i is the adjusted weight value, g i is the initial weight, a′ ij1 is the support probability, a′ ij2 is the probability of negation, a′ ij3 is the uncertainty probability;

[0023] The dynamically updated weights of the risk factors are traversed and calculated, the dynamically updated weights are normalized, and an updated weight vector is generated based on the adjusted weight values.

[0024] As a preferred embodiment of the method for fire risk assessment of distribution network equipment according to the present invention, the method comprises: calculating the risk index of distribution network equipment to identify equipment risk, comprising: performing dimensionless processing on the real-time data of the risk factors after pre-processing, and performing weighted calculation on the real-time data of the risk factors after dimensionless processing according to the adjusted weight values ​​to obtain weighted values ​​of each risk factor;

[0025] The weighted values ​​of each risk factor are accumulated to generate a comprehensive risk index R for each device. The risk threshold W is set and the comprehensive fire risk index R of each device is compared with the risk threshold W:

[0026] If R≥W, the device is marked as high-risk, otherwise it is low-risk.

[0027] As a preferred embodiment of the method for fire risk assessment of distribution network equipment of the present invention, when the identified distribution network equipment is high-risk equipment, risk simulation is performed in combination with the equipment environment characteristics, including:

[0028] Collect real-time data from high-risk devices and extract environmental feature data through feature engineering. Set critical thresholds for risk formation based on device safety indicators, including maximum safe temperature, maximum current load, and minimum humidity.

[0029] The critical thresholds of various environmental characteristics are combined into a risk benchmark condition matrix. Based on the benchmark conditions, the risk trigger event of temperature and current load exceeding the critical threshold is selected as the initial event of risk formation, and the initial event is used as the initial event node of the fault tree;

[0030] According to the actual situation of the risk formation of distribution network equipment, select the corresponding logical relationship to link each trigger event, and according to the logical relationship, connect the trigger events step by step to form a risk fault tree;

[0031] The independent occurrence probability of each event is calculated based on historical data and real-time data, and the risk triggering probability of high-risk equipment is calculated layer by layer through the logical structure of the fault tree.

[0032] As a preferred solution of the fire risk assessment method for distribution network equipment of the present invention, it further includes:

[0033] Based on the equipment layout and installation location of the distribution network, collect the physical distance and spatial orientation between high-risk equipment and adjacent equipment, and collect environmental data that affects risk expansion. Calculate the probability of a fire on high-risk equipment spreading to adjacent equipment based on the adjacent relationship between equipment and environmental factors:

[0034]

[0035] Among them, S XJ is the probability of fire spreading from device X to device J, S′ X is the fire triggering probability of device X, d XJ is the physical distance between devices X and J, v is the ventilation velocity, σ is the angle between the fire spread direction and the wind direction, and α is the attenuation coefficient;

[0036] Set the probability threshold K of fire expansion, if the probability S XJIf it is greater than or equal to K, it means that the fire will spread to adjacent devices, otherwise it will not spread. According to the calculation results of the expansion probability, a path diagram is used to mark the direction and path of fire expansion to generate a fire expansion path diagram, and the fire expansion probability, fire trigger probability and affected devices are summarized into a dynamic data set.

[0037] As a preferred embodiment of the fire risk assessment method for distribution network equipment of the present invention, implementing corresponding maintenance measures based on dynamic data of risk simulation includes: classifying distribution network equipment according to the dynamic data set, marking equipment with a high trigger probability and on the fire expansion path as priority equipment, and marking equipment with a high trigger probability but not on the expansion path as second priority equipment;

[0038] If the device is a priority device, the sampling frequency of the monitoring data will be increased, and the technical staff will be notified to immediately go to the site to check the status of the relevant distribution network equipment;

[0039] If the equipment is a second-priority processing device, maintain the original data sampling frequency and arrange for technicians to regularly check the status of the distribution network equipment.

[0040] In a second aspect, the present invention provides a distribution network equipment fire risk assessment system, comprising:

[0041] A data acquisition and processing module is used to acquire distribution network equipment data and preprocess the data, and calculate the distribution network equipment risk index based on the preprocessing results to identify equipment risks;

[0042] The risk simulation maintenance module is used to perform risk simulation based on the equipment environment characteristics when the distribution network equipment is identified as high-risk equipment, and implement corresponding maintenance measures based on the dynamic data of the risk simulation;

[0043] Presentation module, used to visualize risk simulation data and store assessment process data.

[0044] In a third aspect, the present invention provides an electronic device, comprising:

[0045] memory and processor;

[0046] The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the distribution network equipment fire risk assessment method are implemented.

[0047] In a fourth aspect, the present invention provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the distribution network equipment fire risk assessment method.

[0048] Compared with the existing technology, the beneficial effects of the present invention are as follows: the present invention combines expert scoring with the comprehensive weight calculation of the spherical fuzzy judgment matrix to improve the assessment accuracy of the fire trigger probability, and realizes accurate simulation of the fire trigger probability and expansion path through the fault tree and Bayesian network, providing higher priority response and maintenance measures for high-risk equipment, significantly improving the efficiency of fire risk identification and prevention, reducing resource waste, and fully supporting the safe operation and maintenance management of distribution network equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive effort. Among them:

[0050] Figure 1 This is a flow chart of a method and system for fire risk assessment of distribution network equipment according to an embodiment of the present invention. DETAILED DESCRIPTION

[0051] To make the above-mentioned objects, features, and advantages of the present invention more clearly understood, the following detailed description of the specific embodiments of the present invention is given in conjunction with the accompanying drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in this field without creative work should fall within the scope of protection of the present invention.

[0052] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0053] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0054] The present invention is described in detail with reference to schematic diagrams. For ease of illustration, cross-sectional views of device structures may be partially enlarged and not to scale when describing embodiments of the present invention. Furthermore, the schematic diagrams are merely illustrative and should not limit the scope of the present invention. Furthermore, in actual production, the three-dimensional dimensions of length, width, and depth should be included.

[0055] In the description of the present invention, it should be noted that the terms "upper, lower, inner, and outer" and other references to orientations or positional relationships are based on the orientations or positional relationships shown in the accompanying drawings and are intended solely to facilitate and simplify the description of the present invention. They are not intended to indicate or imply that the devices or components referred to must have, be constructed, or operate in a specific orientation, and therefore should not be construed as limitations on the present invention. Furthermore, the terms "first, second, or third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0056] In this disclosure, unless otherwise specified or limited, the terms "mounted," "connected," and "connected" should be interpreted broadly. For example, they may refer to fixed, removable, or integral connections. They may also refer to mechanical, electrical, or direct connections, indirect connections through an intermediary, or internal communication between two components. Those skilled in the art will understand the specific meanings of these terms in this disclosure.

[0057] Example 1

[0058] Reference Figure 1 , is an embodiment of the present invention, which provides a method for fire risk assessment of distribution network equipment, comprising:

[0059] S100: Acquire distribution network equipment data and preprocess the data, and calculate the distribution network equipment risk index based on the preprocessing results to identify equipment risks;

[0060] It should be noted that this application deploys temperature and humidity sensors and current sensors on distribution network equipment, adjusts the data collection cycle according to the working characteristics of the equipment and the frequency of environmental changes, collects the temperature and current load inside the distribution network equipment and the ambient temperature and humidity around the distribution network equipment, cleans, standardizes, smoothes and denoises the collected data, and uses the preprocessed data as a risk factor.

[0061] In an optional embodiment, multiple sensors work together to help achieve comprehensive coverage of fire risks and ensure the diversity and accuracy of fire risk assessment data. By dynamically adjusting the collection cycle, the present application can flexibly set the frequency of data collection based on the operating characteristics of the equipment and environmental fluctuations. Data cleaning, standardization, and data smoothing and denoising processing can ensure the high quality and consistency of sensor data. In fire risk assessment, using preprocessed data as a risk factor can more accurately characterize the characteristics of equipment fire risks.

[0062] Furthermore, assigning weights to different fire risk factors refers to inviting fire protection and power system experts to score the importance of internal and external risk factors and then generating expert scoring data.

[0063] In the embodiment of the present application, before calculating the risk index of the distribution network equipment based on the preprocessing results, the method further includes: using the preprocessing results as risk factors and assigning weights to different risk factors;

[0064] Establishing spherical fuzzy judgment matrix r=(o ij ), where element o ij It is expressed as a triple: (a ij1 , a ij2 , a ij3 ), where a ij1 is the membership degree, a ij2 Non-membership degree, a ij3 It is the degree of hesitation;

[0065] Specifically, membership is used to reflect the probability of factor i and factor j supporting the overall risk, non-membership is used to reflect the probability of factor i and factor j denying the overall risk, and hesitation is used to represent the probability of subjective uncertainty;

[0066] In the embodiment of the present application, the triplet data of each row in the matrix r is calculated to generate the preliminary weight value of each risk factor:

[0067]

[0068] Among them, g i is the initial weight of risk factor i, T i is the temperature data corresponding to risk factor i, I j is the current load corresponding to risk factor j, H j is the humidity corresponding to risk factor j, U is the external ambient temperature of the entire device, I is the internal current load of the device, θ ij is the temperature interaction coefficient, δ ij is the current load interaction coefficient, a ij1 , a ij2 and a ij3 is the membership degree, non-membership degree and hesitation degree between risk factor i and risk factor j, and n represents the total number of risk factors.

[0069] Specifically, the temperature interaction coefficient is used to adjust the risk impact of ambient temperature on the equipment and is set based on historical data and actual operating conditions. The current load interaction coefficient is used to adjust the impact of the internal current load of the equipment and is set based on the actual load situation. The membership, non-membership, and hesitation between risk factors i and j are generated by expert scores. n represents the total number of risk factors. Non-linear The impact of humidity fluctuations can be reduced to avoid excessive interference with the weights of other factors when humidity is abnormal.

[0070] In an optional embodiment, the geometric mean method can be used to calculate the triple data in each row to generate the preliminary weight value of each risk factor:

[0071]

[0072] The above formula only considers the membership, non-membership, and hesitation of each risk factor, and simply calculates the geometric mean of the triples without introducing other influencing factors. Therefore, it is insufficiently expressive for fire risk assessment of distribution network equipment in complex environments. Based on the traditional method, actual measurement data such as equipment temperature, humidity, and current load are introduced to dynamically adapt to the actual operating status of the equipment, which can more comprehensively reflect the fire risk faced by the equipment. Based on the different data characteristics of temperature, current load, and humidity, a more adaptable mapping function is designed, so that each factor in the weight calculation can more realistically reflect its contribution to the equipment fire risk.

[0073] It should be noted that compared with the simple multiplication structure of the traditional geometric mean method, a nonlinear mapping function is added to more carefully balance the impact of various factors on equipment risk and improve the flexibility and accuracy of the formula. In order to consider the interaction between different environmental factors, sine and cosine interaction terms are added to the denominator so that the ambient temperature and current load of the equipment have a direct interactive effect on the overall weight. The structure of the denominator is: 1+sin(θ ij U)+cos(δ ij L), the traditional method does not introduce interaction terms, so it cannot reflect the dynamic relationship between risk factors. By introducing sine and cosine modulation of ambient temperature and internal current load, the interactive influence of various factors is realized, thus enhancing dynamic adaptability;

[0074] In the embodiment of the present application, the method further includes: using risk factors as nodes of the Bayesian network, and using the weight value corresponding to each risk factor as the initial probability value of each node;

[0075] Dynamically update the conditional probability P(B|A) in the Bayesian network based on real-time collected data:

[0076] P(B|A)=(a′ ij1 , a′ ij2 , a′ ij3 )

[0077] Among them, a′ ij1 It represents the support probability of risk factor B for the overall risk under given condition A, a′ ij2 Indicates the probability of negation of risk factor B on the overall risk under condition A, a′ ij3 It represents the uncertainty probability of risk factor B to the overall risk under condition A.

[0078] Furthermore, a′ ij1 is the support probability, which indicates the degree of support of risk factor B for the overall risk under the condition A. The higher the value, the more favorable factor B is for the occurrence of risk under the current conditions. ij2 It is the probability of negation, which indicates the degree to which risk factor B negates the overall risk when condition A exists. The higher the value, the greater the negative impact of factor B on the risk under the current conditions. a′ ij3 It is the uncertainty probability, which reflects the ambiguity or uncertainty of risk factor B on the overall risk when condition A exists. The higher the value, the less clear judgment there is on the risk impact of factor B under the current conditions.

[0079] Specifically, a′ ij1 It indicates the probability that risk factor B supports the overall risk under given condition A. The higher the value, the greater the positive impact of factor B on the risk under the current conditions. The calculation method is as follows:

[0080]

[0081] Among them, P(A) is the prior probability of event A, which means the probability of event A occurring without any other information or conditions; P(B) is the prior probability of event B, which means the probability of event B occurring without other conditions; P(A|B) is the conditional probability of event A occurring under the condition that event B has occurred;

[0082] Specifically, a′ ij2 It represents the probability of negation of the overall risk by risk factor B under condition A. The higher the value, the greater the negative effect of factor B on the risk under the current conditions. In order to ensure that the sum of membership and non-membership is 1, this probability is defined as the complement of the support probability:

[0083] a′ ij2 =1-a′ ij1

[0084] Specifically, a′ ij3 It represents the uncertainty probability of risk factor B on the overall risk under condition A. The hesitation reflects the ambiguity between support and denial, that is, the lack of a definite judgment on the risk impact of factor B under the current conditions. The calculation formula is as follows:

[0085]

[0086] This formula ensures that the triplet satisfies the constraint a′ of the spherical fuzzy number 2 ij1 +a′ 2 ij2 +a′ 2 ij3=1, so that the sum of the probabilities of support, rejection, and uncertainty is equal to 1;

[0087] Based on the updated conditional probability value, the preliminary weight vector of each node is dynamically adjusted. The dynamic weight value calculation formula of each risk factor is:

[0088] g′ i =g i ·a′ ij1 +(1-g i )·(1-a′ ij2 )+a′ ij3 ·g i ·(1-g i )

[0089] Among them, g′ i is the adjusted weight value, g i is the initial weight, a′ ij1 is the support probability, a′ ij2 is the probability of negation, a′ ij3 is the uncertainty probability;

[0090] The dynamically updated weights of the risk factors are traversed and calculated, the dynamically updated weights are normalized, and an updated weight vector is generated based on the adjusted weight values.

[0091] It should be noted that by inviting fire protection and power system experts to score fire risk factors, the present invention can fully integrate professional knowledge and practical experience, generate a spherical fuzzy judgment matrix, and accurately express the subjective uncertainty and multidimensional characteristics of each risk factor. On the basis of the triplet scoring data, the geometric mean method is used to calculate the preliminary weight vector so that the weight distribution of each risk factor is balanced and not interfered with by extreme values. Subsequently, normalization processing is performed to obtain the normalization coefficient S, unify the weight distribution and ensure that the sum of the weights of all factors is 1, thereby avoiding the problems of bias and weight imbalance. This processing method improves the fairness and consistency of weight distribution, provides a stable and unbiased benchmark for the weights of risk factors, sets the risk factors as nodes of the Bayesian network, updates the conditional probability through real-time data, and continuously adjusts the preliminary weight vector of each node, so that the network can dynamically adjust the weights of each risk factor as external data changes.

[0092] It should also be noted that this design can reflect changes in equipment fire risk in real time, significantly improving the flexibility and responsiveness of risk assessment. The dynamic updating of conditional probabilities solves the problem of traditional models' inability to provide real-time feedback, enabling risk assessment to address fire risks in dynamic environments. By decomposing support, negation, and uncertainty probabilities, the model can distinguish between support, opposition, and uncertainty under different risk conditions within a Bayesian network and calculate dynamic weights. This overcomes the binary logic flaw of traditional risk assessment models, which only consider "risk occurrence" or "non-occurrence," enabling the present invention to capture subtle changes in risk trends under complex conditions. For example, even with slight fluctuations in environmental factors, the solution can maintain high response accuracy, avoiding frequent weight adjustments due to minor changes. By dynamically adjusting the weight vector based on real-time data, the present invention can automatically adjust the weights of various risk factors when fire risk changes significantly. For example, if the temperature or current load of a piece of equipment increases significantly, the weight of that factor will automatically increase, highlighting the impact of that risk. Compared to traditional static weight assignment methods, dynamic weight vectors can reflect risk trends in real time, making the solution's fire identification and response more flexible and timely.

[0093] In an embodiment of the present application, calculating the distribution network equipment risk index to identify equipment risk includes: performing dimensionless processing on the pre-processed real-time data of the risk factors, and performing weighted calculation on the dimensionless real-time data of the risk factors according to the adjusted weight values ​​to obtain a weighted value of each risk factor;

[0094] The weighted values ​​of each risk factor are accumulated to generate a comprehensive risk index R for each device. The risk threshold W is set and the comprehensive fire risk index R of each device is compared with the risk threshold W:

[0095] If R≥W, the device is marked as high-risk, otherwise it is low-risk.

[0096] It should be noted that the dimensionless processing significantly enhances the evaluation capability of the present invention, which not only ensures a fair comparison between risk factors, but also improves the accuracy of the overall risk index. By assigning high weights to risk factors such as temperature and current, key risk points can be captured more accurately, thereby improving the accuracy of high-risk equipment identification. By comparing the fire risk index R with the risk threshold W, high-risk equipment can be quickly identified, and higher-priority fire safety management measures can be implemented for these equipment.

[0097] S200: When the distribution network equipment is identified as high-risk equipment, risk simulation is performed in combination with the equipment environment characteristics, and corresponding maintenance measures are implemented based on the dynamic data of the risk simulation;

[0098] In an embodiment of the present application, when the distribution network equipment is identified as high-risk equipment, risk simulation is performed in combination with the equipment environment characteristics, including:

[0099] Collect real-time data from high-risk devices and extract environmental feature data through feature engineering. Set critical thresholds for risk formation based on device safety indicators, including maximum safe temperature, maximum current load, and minimum humidity.

[0100] The critical thresholds of various environmental characteristics are combined into a risk benchmark condition matrix. Based on the benchmark conditions, the risk trigger event of temperature and current load exceeding the critical threshold is selected as the initial event of risk formation, and the initial event is used as the initial event node of the fault tree;

[0101] According to the actual situation of the risk formation of distribution network equipment, select the corresponding logical relationship to link each trigger event, and according to the logical relationship, connect the trigger events step by step to form a risk fault tree;

[0102] For example, assuming that "fire trigger" requires temperature exceeding the limit and current overload, then event A and event B are connected using "AND" logic, indicating that a fire will be triggered only when temperature exceeding the limit and current overload occur at the same time. If insufficient humidity (event C) is an independent fire trigger event, it is connected to the root node "fire trigger" through "OR" logic.

[0103] The independent occurrence probability of each event is calculated based on historical data and real-time data, and the risk triggering probability of high-risk equipment is calculated layer by layer through the logical structure of the fault tree.

[0104] Specifically, the logical relationships include:

[0105] If the formation of a risk requires multiple events to occur simultaneously, use "AND" logic; if any one event triggers the risk, use "OR" logic;

[0106] Specifically, based on the combination of "AND" gates and "OR" gates, the fire trigger probability of high-risk equipment is calculated layer by layer:

[0107] For the AND logic gate, the probability of fire triggering is the product of the probability of each event occurring;

[0108] For the OR logic gate, the probability of fire triggering is the complement of the probability of each event not occurring;

[0109] In the embodiment of the present application, it also includes:

[0110] Based on the equipment layout and installation location of the distribution network, collect the physical distance and spatial orientation between high-risk equipment and adjacent equipment, and collect environmental data that affects risk expansion; environmental data includes wind speed and direction;

[0111] In this embodiment of the present application, the probability of a fire on a high-risk device spreading to adjacent devices is calculated based on the neighboring relationship between devices and environmental factors:

[0112]

[0113] Among them, S XJ is the probability of fire spreading from device X to device J, S′ X is the fire triggering probability of device X, d XJ is the physical distance between devices X and J, v is the ventilation velocity, σ is the angle between the fire spread direction and the wind direction, and α is the attenuation coefficient.

[0114] Specifically, the attenuation coefficient is used to adjust the expansion probability as environmental factors change. According to the typical attenuation relationship between devices, α is preliminarily set and obtained based on the fitting of historical fire data.

[0115] In the embodiment of the present application, the probability threshold K of fire spread is set based on the NFPA standard. If the probability S XJ If it is greater than or equal to K, it means that the fire will spread to adjacent devices, otherwise it will not spread. According to the calculation results of the expansion probability, a path diagram is used to mark the direction and path of fire expansion to generate a fire expansion path diagram, and the fire expansion probability, fire trigger probability and affected devices are summarized into a dynamic data set.

[0116] For example, when simulating fire development in high-risk equipment, the present invention combines real-time equipment data with environmental characteristic data to define key fire development conditions, namely critical thresholds, such as maximum safe temperature, maximum current load, and minimum humidity. This enables multi-dimensional monitoring of fire development conditions, significantly improving accuracy. By connecting the initial event nodes of fire development into a hierarchical logical structure, the present invention can clearly demonstrate the multiple conditions required for fire development. This logical relationship ensures that each risk factor has a clear trigger path, demonstrating not only the possibility of fire triggering but also the specific conditions that trigger a fire, facilitating the tracing of key events. The "AND" logic in the fault tree model is used to simulate fire triggering conditions caused by the combined effects of multiple factors, such as when temperature, current load, humidity, and other conditions simultaneously exceed safety thresholds. The "OR" logic, on the other hand, is applicable to the independent fire triggering paths of a single event, such as when the temperature of any device is too high, which may cause a fire. This combined approach offers significant advantages over traditional single-item monitoring systems that cannot identify complex triggering paths. It provides a scientific logical structure and assessment accuracy for fire risk assessment, effectively reducing the rate of missed fire triggers. When calculating the probability of fire triggering step by step, the hierarchical design of the fault tree, combined with a combination of AND and OR gates, provides a detailed hierarchical evaluation mechanism for estimating the probability of fire triggering. In calculating the probability of fire spread, this invention integrates environmental data such as the physical distance between devices, spatial orientation, wind speed, and direction, comprehensively reflecting the spread of the fire. The fire trigger probability, spread probability, and affected device information obtained through these calculations are ultimately aggregated into a dynamic dataset. This dynamic dataset not only provides data storage but also allows for dynamic adjustments as the device's status updates in real time, ensuring that the device's fire risk data remains up to date.

[0117] In an embodiment of the present application, implementing corresponding maintenance measures based on dynamic data of risk simulation includes: classifying distribution network equipment according to the dynamic data set, marking equipment with a high trigger probability and on the fire expansion path as priority processing equipment, and marking equipment with a high trigger probability but not on the expansion path as second priority processing equipment;

[0118] If the device is a priority device, the sampling frequency of the monitoring data will be increased, and the technical staff will be notified to immediately go to the site to check the status of the relevant distribution network equipment;

[0119] If the equipment is a second-priority processing device, maintain the original data sampling frequency and arrange for technicians to regularly check the status of the distribution network equipment.

[0120] It should be noted that the dynamic dataset records the fire trigger probability and expansion path information of each distribution network equipment. Through the classification strategy, the equipment with high trigger probability is divided into priority or sub-priority, which optimizes resource allocation. The priority and sub-priority hierarchical maintenance method ensures the rational allocation of resources and the timeliness of response. The high-frequency data sampling and timely notification mechanism provide reliable guarantees for early intervention in fire risks.

[0121] S300: Visualize risk simulation data and store assessment process data;

[0122] In an optional embodiment, visually displaying the risk simulation data refers to drawing a two-dimensional risk heat map through a Python data visualization library in combination with the risk trigger probability and the expansion probability, using gradient colors to represent the fire trigger probability, marking low risk to high risk with cold colors to warm colors respectively, adding a legend next to the heat map to indicate the correspondence between color and fire risk degree, and integrating the generated two-dimensional fire risk heat map and fire expansion path map into Power BI for visual display.

[0123] Through the visualization of fire trigger probability and expansion probability, the fire risk level information can be intuitively conveyed to technical personnel, providing support for real-time monitoring and risk warning. Power BI supports real-time data updates and can dynamically adjust the fire trigger probability and expansion path diagram as the data changes. Technical personnel can view the latest risk status of different equipment in real time on a unified interface to ensure the timeliness of risk identification. By combining the two-dimensional heat map and expansion path diagram of the fire trigger probability and expansion probability, a highly targeted visualization method is provided for fire risk assessment. The display results are integrated into Power BI. Through real-time data updates and multi-dimensional data fusion display, the efficiency of fire risk identification and expansion prediction is significantly improved.

[0124] In an embodiment of the present application, storing the data generated during the evaluation process means storing the data collected and analyzed during the evaluation process and the maintenance measures for distribution network equipment at different processing levels in a database, and the database synchronizes the stored data to the cloud for regular backup.

[0125] It should be noted that by centrally storing and synchronizing the data generated during the fire risk assessment process to cloud-based backup, the challenges of dispersed data storage, incomplete information, and data loss risks in traditional fire risk management are effectively addressed. Furthermore, by recording equipment maintenance measures and trend analysis data at different processing levels, precise monitoring and intelligent management of fire risks are achieved, significantly improving the safety and protection capabilities of distribution network equipment, enhancing data traceability, and enhancing the scientific nature of risk assessments.

[0126] Example 2

[0127] Reference Figure 1 , is an embodiment of the present invention. This embodiment is different from the first embodiment in that it provides a distribution network equipment fire risk assessment system.

[0128] It should be noted that the technical solution of this distribution network equipment fire risk assessment system and the technical solution of the above-mentioned distribution network equipment fire risk assessment method belong to the same concept. For details not described in detail in the technical solution of the distribution network equipment fire risk assessment system in this embodiment, please refer to the description of the technical solution of the above-mentioned distribution network equipment fire risk assessment method.

[0129] In this embodiment, a distribution network equipment fire risk assessment system includes:

[0130] A data acquisition and processing module is used to acquire distribution network equipment data and preprocess the data, and calculate the distribution network equipment risk index based on the preprocessing results to identify equipment risks;

[0131] The risk simulation maintenance module is used to perform risk simulation based on the equipment environment characteristics when the distribution network equipment is identified as high-risk equipment, and implement corresponding maintenance measures based on the dynamic data of the risk simulation;

[0132] Presentation module, used to visualize risk simulation data and store assessment process data.

[0133] This embodiment further provides an electronic device applicable to the fire risk assessment method for distribution network equipment, including:

[0134] Memory and processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement the fire risk assessment method for distribution network equipment proposed in the above embodiment.

[0135] This embodiment further provides a storage medium having a computer program stored thereon. When the program is executed by a processor, the method for fire risk assessment of distribution network equipment proposed in the above embodiment is implemented.

[0136] The storage medium proposed in this embodiment and the method for implementing fire risk assessment of distribution network equipment proposed in the above embodiment belong to the same inventive concept. For technical details not described in detail in this embodiment, please refer to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0137] Through the above description of the embodiments, those skilled in the art can clearly understand that the present invention can be implemented with the help of software and necessary general-purpose hardware. Of course, it can also be implemented with hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), magnetic disk, optical disk, or other medium that can store program code.

[0138] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing the 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 (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0139] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0140] It should be understood that various parts of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used to implement: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0141] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for fire risk assessment of distribution network equipment, characterized in that: include: Acquiring distribution network equipment data and preprocessing the data, and calculating a distribution network equipment risk index based on the preprocessing results to identify equipment risks; Before calculating the distribution network equipment risk index based on the preprocessing results, the method further includes: using the preprocessing results as risk factors and assigning weights to different risk factors; Establishing spherical fuzzy judgment matrix r=(o ij ), where element o ij It is expressed as a triple: (a ij1 , a ij2 , a ij3 ), where a ij1 is the membership degree, a ij2 Non-membership degree, a ij3 It is the degree of hesitation; Calculate the triplet data of each row in the matrix r to generate the preliminary weight value of each risk factor: Among them, g i is the initial weight of risk factor i, T i is the temperature data corresponding to risk factor i, I j is the current load corresponding to risk factor j, H j is the humidity corresponding to risk factor j, U is the external ambient temperature of the entire device, I is the internal current load of the device, θ ij is the temperature interaction coefficient, δ ij is the current load interaction coefficient, a ij1 , a ij2 and a ij3 is the degree of membership, non-membership and hesitation between risk factor i and risk factor j, and n represents the total number of risk factors; The risk factors are used as nodes of the Bayesian network, and the weight value corresponding to each risk factor is used as the initial probability value of each node; Dynamically update the conditional probability P(B|A) in the Bayesian network based on real-time collected data: P(B|A)=(a′ ij1 ,a′ ij2 ,a′ ij3 ) Among them, a′ ij1 It represents the support probability of risk factor B for the overall risk under given condition A, a′ ij2 Indicates the probability of negation of risk factor B on the overall risk under condition A, a′ ij3 It represents the uncertainty probability of risk factor B to the overall risk under condition A; Based on the updated conditional probability value, the preliminary weight vector of each node is dynamically adjusted. The dynamic weight value calculation formula of each risk factor is: g′ i =g i ·a′ ij1 +(1-g i )·(1-a′ ij2 )+a′ ij3 ·g i ·(1-g i ) Among them, g′i is the adjusted weight value, g i is the preliminary weight, a′ij1 is the support probability, a′ij2 is the negation probability, and a′ij3 is the uncertainty probability; Traverse and calculate the dynamically updated weights of the risk factors, normalize the dynamically updated weights, and generate an updated weight vector based on the adjusted weight values; Calculating the distribution network equipment risk index to identify equipment risks includes: performing dimensionless processing on the pre-processed real-time data of the risk factors, and performing weighted calculation on the dimensionless real-time data of the risk factors according to the adjusted weight values ​​to obtain weighted values ​​of each risk factor; The weighted values ​​of each risk factor are accumulated to generate a comprehensive risk index R for each device. The risk threshold W is set and the comprehensive fire risk index R of each device is compared with the risk threshold W: If R ≥ W, the device is marked as high-risk, otherwise it is low-risk; When distribution network equipment is identified as high-risk equipment, risk simulation of fire triggering probability and expansion path is performed using fault tree and Bayesian networks, combined with equipment environment characteristics. Corresponding maintenance measures are implemented based on the dynamic data of risk simulation; dynamic data includes fire expansion probability, fire trigger probability, and affected equipment. Visualize risk simulation data and store assessment process data.

2. The fire risk assessment method for distribution network equipment according to claim 1, characterized in that: When the distribution network equipment is identified as high-risk equipment, the risk simulation is performed in combination with the equipment environment characteristics, including: Collect real-time data from high-risk devices and extract environmental feature data through feature engineering. Set critical thresholds for risk formation based on device safety indicators, including maximum safe temperature, maximum current load, and minimum humidity. The critical thresholds of various environmental characteristics are combined into a risk benchmark condition matrix. Based on the benchmark conditions, the risk trigger event of temperature and current load exceeding the critical threshold is selected as the initial event of risk formation, and the initial event is used as the initial event node of the fault tree; According to the actual situation of the risk formation of distribution network equipment, select the corresponding logical relationship to link each trigger event, and according to the logical relationship, connect the trigger events step by step to form a risk fault tree; The independent occurrence probability of each event is calculated based on historical data and real-time data, and the fire triggering probability of high-risk equipment is calculated layer by layer through the logical structure of the fault tree.

3. The fire risk assessment method for distribution network equipment according to claim 2, characterized in that: Also includes: Based on the equipment layout and installation location of the distribution network, collect the physical distance and spatial orientation between high-risk equipment and adjacent equipment, and collect environmental data that affects risk expansion. Calculate the probability of a fire on high-risk equipment spreading to adjacent equipment based on the adjacent relationship between equipment and environmental factors: Among them, S XJ is the probability of fire spreading from device X to device J, S′ X is the fire triggering probability of device X, d XJ is the physical distance between devices X and J, v is the ventilation velocity, σ is the angle between the fire spread direction and the wind direction, and α is the attenuation coefficient; Set the probability threshold K of fire expansion, if the probability S XJ If it is greater than or equal to K, it means that the fire will spread to adjacent devices, otherwise it will not spread. According to the calculation results of the expansion probability, a path diagram is used to mark the direction and path of fire expansion to generate a fire expansion path diagram, and the fire expansion probability, fire trigger probability and affected devices are summarized into a dynamic data set.

4. The fire risk assessment method for distribution network equipment according to claim 3, characterized in that: Implementing corresponding maintenance measures based on dynamic data from risk simulation includes: classifying distribution network equipment according to the dynamic data set, marking equipment with a high trigger probability and on the fire expansion path as priority equipment, and marking equipment with a high trigger probability but not on the expansion path as second priority equipment; If the device is a priority device, the sampling frequency of the monitoring data will be increased, and the technical staff will be notified to immediately go to the site to check the status of the relevant distribution network equipment; If the equipment is a second-priority processing device, maintain the original data sampling frequency and arrange for technicians to regularly check the status of the distribution network equipment.

5. A fire risk assessment system for distribution network equipment, applied to the method according to any one of claims 1 to 4, characterized in that: include: A data acquisition and processing module is used to acquire distribution network equipment data and preprocess the data, and calculate the distribution network equipment risk index based on the preprocessing results to identify equipment risks; The risk simulation maintenance module is used to perform risk simulation based on the equipment environment characteristics when the distribution network equipment is identified as high-risk equipment, and implement corresponding maintenance measures based on the dynamic data of the risk simulation; Presentation module, used to visualize risk simulation data and store assessment process data.

6. An electronic device comprising: memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the distribution network equipment fire risk assessment method described in any one of claims 1 to 4 are implemented.

7. A computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the distribution network equipment fire risk assessment method according to any one of claims 1 to 4.

Images