A method and system for quantitative assessment of fire risk of power distribution network equipment

Abstract

This invention discloses a method and system for quantitative assessment of fire risk in power distribution network equipment, comprising: acquiring power distribution network equipment data; constructing a first quantitative risk assessment model based on the data; performing preliminary risk determination based on the first quantitative risk assessment model, analyzing fault transmission risk, and calculating the overall risk status value; constructing a second quantitative risk assessment model, which is used to predict changes in risk parameters; dynamically updating the overall risk status value, and providing fire risk early warning based on changes in risk parameters. This invention dynamically monitors the transmission risk between equipment risk factors by calculating activation condition values ​​and propagation thresholds based on the fuzzy membership degrees of different risk factor nodes. By using nonlinear functions to calculate risk contribution, nodes with high-risk membership degrees are amplified, making their impact on the overall risk more significant, thus helping to highlight the impact of key nodes when assessing the overall risk of the system.

Description

Technical Field

[0001] This invention relates to the technical field of distribution network risk assessment, and in particular to a method and system for quantitative assessment of fire risk of distribution network equipment. Background Technology

[0002] With the continuous expansion and increasing complexity of power distribution network systems, the safe operation of power distribution equipment faces severe challenges. Fire extinguishing equipment made of perfluorohexanone (PFH) is being used in fire protection equipment. Based on its chemical properties, conductivity, and mechanism of action in inhibiting electrical fire discharge, PFH can be highly compatible with the fire protection operation of power distribution equipment.

[0003] However, in the use of fire extinguishing equipment made of perfluorohexanone, the existing technology for fire risk assessment of power distribution network equipment mainly relies on manual periodic inspections and traditional fault detection methods, such as temperature monitoring and overload protection. However, these methods often suffer from insufficient monitoring timeliness and accuracy, and are mostly focused on the analysis of single data features or states, lacking multi-level and multi-dimensional comprehensive risk assessment methods. In particular, they are still insufficient in terms of fault transmission and dynamic monitoring of fire risks, which reduces the ability to adapt to dynamic changes in risks and reduces the efficiency of fire risk assessment. Summary of the Invention

[0004] The purpose of this section is to outline some aspects of embodiments of the present invention and to briefly describe some preferred embodiments. Simplifications or omissions may be made in this section, as well as in the abstract and title of this application, to avoid obscuring the purpose of these documents; however, such simplifications or omissions should not be construed as limiting the scope of the invention.

[0005] In view of the aforementioned existing problems, the present invention is proposed.

[0006] Therefore, the present invention provides a method and system for quantitative assessment of fire risk of distribution network equipment to solve the problems mentioned in the background art.

[0007] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0008] In a first aspect, embodiments of the present invention provide a method for quantitative assessment of fire risk of distribution network equipment, comprising: acquiring data of distribution network equipment, and constructing a first quantitative risk assessment model based on the data;

[0009] Based on the aforementioned first quantitative risk assessment model, a preliminary risk assessment is conducted, the risk of fault transmission is analyzed, and the overall risk status value is calculated.

[0010] A second quantitative risk assessment model is constructed, which is used to predict changes in risk parameters.

[0011] The overall risk status value is dynamically updated, and fire risk warnings are issued based on changes in the risk parameters.

[0012] As a preferred embodiment of the quantitative assessment method for fire risk of distribution network equipment described in this invention, the acquisition of distribution network equipment data includes: operation data and status data of the distribution network equipment, and operation risk factors and status risk factors are set based on the operation data and status data.

[0013] As a preferred embodiment of the quantitative assessment method for fire risk of distribution network equipment described in this invention, the construction of the first quantitative risk assessment model includes: the first quantitative risk assessment model adopts a fuzzy Petri network structure;

[0014] Each data point of the operational risk factor and the state risk factor is defined as a location node; the triggering conditions of each risk factor are defined as transfer nodes according to the fault propagation path.

[0015] The directed arcs connecting location nodes and transfer nodes represent the relationships between risk factors, and a first quantitative risk assessment model is constructed.

[0016] As a preferred embodiment of the quantitative risk assessment method for distribution network equipment described in this invention, the preliminary risk determination based on the first quantitative risk assessment model includes: calculating the fuzzy membership degree of Petri network location nodes, calculating the corresponding fuzzy membership degree based on the current collected data value of each location node, and setting the fuzzy membership degree range [0,1], as follows:

[0017]

[0018] in, Let Ip,i represent the fuzzy membership degree of the i-th risk factor, Ip,i represent the actual measured value of the i-th risk factor, and Im,i represent the maximum reference value of the i-th risk factor.

[0019] Define a fuzzy rule that calculates the sum of the mean and standard deviation of the risk factor based on its historical data membership degree. If the calculated membership degree is greater than the risk threshold, it is judged as high risk; if the calculated membership degree is less than or equal to the risk threshold, it is judged as low risk.

[0020] As a preferred embodiment of the quantitative assessment method for fire risk of distribution network equipment described in this invention, the analysis of fault transmission risk and the calculation of the overall risk status value include:

[0021] Based on the fuzzy membership degree of each risk factor node, the activation condition value is calculated and expressed as follows:

[0022]

[0023] Where Θij represents the transmission strength of risk factor node Pi to node Pj. and Let Pi and Pj represent the fuzzy membership degrees of risk factor nodes, respectively.

[0024] Based on historical data, we statistically analyze the fault propagation data between different risk factors, and use the sum of the mean and two standard deviations of the corresponding membership degree as the propagation threshold for the corresponding risk factor node. If the calculated condition value is greater than or equal to the propagation threshold, it indicates that there is a high risk of fault transmission between the two corresponding risk factors. If the calculated condition value is less than the propagation threshold, it indicates that there is a low risk of fault transmission between the two corresponding risk factors.

[0025] Based on the determination that the risk of fault transmission is high, the fuzzy membership degree of the risk factor is updated by risk superposition, as follows:

[0026]

[0027] in, This represents the fuzzy membership degree of the updated risk factor node Pj;

[0028] Risk assessment is re-performed based on the updated fuzzy membership, and the risk contribution of each location node to the overall system risk is calculated, expressed as:

[0029]

[0030] in, This represents the risk contribution of the i-th position node. represents the nonlinear function of the fuzzy membership of the i-th location nodes after the update, and k represents the natural constant for adjusting the nonlinear effect;

[0031] The contribution values ​​are combined into an overall risk status value using a fuzzy overlay method, as follows:

[0032]

[0033] Where Rsy represents the overall risk status value, and n represents the total number of risk factor nodes;

[0034] The overall risk status value is determined by the sum of the mean and three standard deviations of the historical data as the status threshold. If the overall risk status value is greater than or equal to the status threshold, the overall risk is judged to be relatively high.

[0035] As a preferred embodiment of the quantitative assessment method for fire risk of distribution network equipment described in this invention, the method includes: constructing a second quantitative risk assessment model, which is used to predict changes in risk parameters, including: using a Fourier heat conduction model to determine the heat diffusion rate, and combining this with the material combustion heat to calculate the dynamic heat release rate, expressed as:

[0036]

[0037] Where HRR(t) represents the dynamic heat release rate at time t, and ΔH represents the heat release rate constant of the material;

[0038] The rate of change of dynamic heat release rate ΔHRR(t) is calculated based on the time variation.

[0039] A second quantitative risk assessment model is constructed using an LSTM model, which includes an input layer, an LSTM layer, and an output layer.

[0040] The input layer takes the change rate data of heat release rate at different times as input, the LSTM layer extracts the features of the change rate data of heat release rate at different times as input, retains the temporal information, and the output layer outputs the predicted value of the change rate of heat release rate at the next time step.

[0041] The LSTM model is trained using the training set. The cross-entropy loss function is selected to calculate the difference between the predicted and actual results. The Adam optimizer is used for gradient descent optimization to update the model weights. If the model loss no longer decreases significantly during continuous iteration, the iteration is stopped and the model parameters are output to complete the model training.

[0042] Input the real-time heat release rate change data into the LSTM model to predict the heat release rate change value at the next moment.

[0043] The overall risk status is adaptively and dynamically adjusted based on the rate of change of heat release rate, as follows:

[0044] R'sy=Rsy·(1+ΔHRR(t))

[0045] Here, R'sy represents the updated overall risk status value.

[0046] As a preferred embodiment of the quantitative assessment method for fire risk of distribution network equipment described in this invention, the method includes: dynamically updating the overall risk status value and conducting fire risk early warning based on the changes in the risk parameters, which includes: using the sum of the average and standard deviation of the historical heat release rate change rate as the heat release rate threshold.

[0047] If the predicted rate of change of heat release rate at the next moment is greater than or equal to the heat release rate threshold, then the overall risk status value at the current moment is increased to the maximum value, and the overall risk status value is updated.

[0048] If the overall risk status value at the current moment increases to the maximum value, and the change rate of heat release rate at the next moment is less than the heat release rate threshold, the risk status value will recover within the time window of the change rate of heat release rate.

[0049] If the overall risk status is determined to be high based on the updated overall risk status value, an early warning signal will be triggered, and a clear sound and visual alert will be issued through the audible and visual alarm system to remind operators that there is a fire risk to the equipment.

[0050] Secondly, the present invention provides a quantitative assessment system for fire risk of power distribution network equipment, comprising:

[0051] The first assessment model construction module is used to acquire data from distribution network equipment and construct a first quantitative risk assessment model based on the data.

[0052] The risk status assessment module is used to make a preliminary risk judgment based on the first quantitative risk assessment model, analyze the risk of fault transmission, and calculate the overall risk status value.

[0053] The second assessment model construction module is used to construct a quantitative risk assessment model, which is used to predict changes in risk parameters.

[0054] The risk warning module is used to dynamically update the overall risk status value and provide fire risk warnings based on changes in the risk parameters.

[0055] Thirdly, the present invention provides an electronic device, comprising:

[0056] Memory and processor;

[0057] 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, they implement the steps of the quantitative assessment method for fire risk of distribution network equipment.

[0058] Fourthly, the present invention provides a computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the steps of the method for quantitatively assessing the fire risk of the distribution network equipment.

[0059] Compared with existing technologies, the beneficial effects of this invention are as follows: By defining operational risk factors and state risk factors as location nodes in a fuzzy Petri network structure, this invention can systematically model the relationships between various risk factors. By calculating the activation condition value and propagation threshold based on the fuzzy membership degree of different risk factor nodes, it can dynamically monitor the transmission risk between equipment risk factors. By using nonlinear functions to calculate the risk contribution degree, nodes with high risk membership degrees are amplified, making their impact on the overall risk more significant, which helps to highlight the impact of key nodes when assessing the overall risk of the system. The dynamic heat release rate is calculated by using the thermal diffusion rate, combustion rate, and heat of combustion of materials, so that the heat release rate can reflect the combustion characteristics of the equipment in real time. The time-series prediction of the heat release rate change rate based on the LSTM model can retain the time-series characteristics of the heat release rate and perform a forward-looking analysis of the changing trend of fire risk. Attached Figure Description

[0060] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein:

[0061] Figure 1 This is a schematic diagram of the method and system for quantitative assessment of fire risk of distribution network equipment according to an embodiment of the present invention;

[0062] Figure 2 This is a detailed flowchart illustrating a method and system for quantitative assessment of fire risk in power distribution network equipment according to an embodiment of the present invention.

[0063] Figure 3 This is a schematic diagram illustrating the overall risk status calculation process of a quantitative assessment method and system for fire risk of distribution network equipment according to an embodiment of the present invention. Detailed Implementation

[0064] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0065] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0066] Secondly, the term "one embodiment" or "embodiment" as used 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 different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0067] This invention is described in detail with reference to the schematic diagrams. When detailing the embodiments of this invention, for ease of explanation, the cross-sectional views illustrating the device structure may be partially enlarged, not adhering to the usual scale. Furthermore, the schematic diagrams are merely examples and should not be construed as limiting the scope of protection of this invention. In actual fabrication, the three-dimensional spatial dimensions of length, width, and depth should be included.

[0068] Furthermore, in the description of this invention, it should be noted that the terms "upper," "lower," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. These terms are used solely for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. In addition, the terms "first," "second," or "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0069] Unless otherwise explicitly specified and limited, the terms "installation," "connection," and "joining" in this invention should be interpreted broadly. For example, they can refer to fixed connections, detachable connections, or integral connections; similarly, they can refer to mechanical connections, electrical connections, or direct connections, or indirect connections through an intermediate medium, or internal connections between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0070] Example 1

[0071] Reference Figures 1-3 As one embodiment of the present invention, this embodiment provides a method for quantitatively assessing the fire risk of distribution network equipment, including:

[0072] S100: Acquire data from distribution network equipment and build a primary quantitative risk assessment model based on the data;

[0073] In this embodiment of the application, obtaining data from distribution network equipment includes: operating data and status data of distribution network equipment, and setting operating risk factors and status risk factors based on the operating data and status data.

[0074] Specifically, operational data is collected based on distribution network equipment, including the equipment's operating current, the equipment's corresponding design rated current value, the equipment's current voltage, the equipment's corresponding design rated voltage value, the equipment's operating temperature, and the equipment's corresponding design temperature limit.

[0075] Specifically, status data is collected, including the number of years the equipment has been in use, the design service life of the equipment, the resistance value of the equipment insulation layer and the minimum insulation resistance value of the safety standard, the contact resistance value of the equipment connection points is measured by a contact resistance tester, and the contact resistance value is determined based on the standards of the connection devices.

[0076] Specifically, operational risk factors are set, including current overload rate, voltage deviation rate, and temperature over-limit ratio. The current overload rate is determined based on the ratio of the current current to the rated current, the voltage deviation rate is determined based on the deviation ratio of the current voltage to the rated voltage, and the temperature over-limit ratio is determined based on the proportion of the current operating temperature exceeding the upper limit of the safe temperature.

[0077] Specifically, condition risk factors are set, including aging coefficient, insulation loss rate, and continuous oxidation rate. The aging coefficient is determined based on the ratio of the current service life of the equipment to its expected lifespan. The insulation loss rate is determined based on the ratio of the insulation resistance to the minimum insulation resistance value. The continuous oxidation rate is determined based on the ratio of the contact resistance to the standard contact resistance value.

[0078] By collecting real-time operating data from the equipment, such as current, voltage, and temperature, and combining this data with the equipment's design parameters (rated current, rated voltage, and temperature limits), the system can calculate the equipment's current overload rate, voltage deviation rate, and temperature over-limit ratio in real time. This directly reflects the equipment's current operating status and helps identify key operational risks such as overload, overvoltage, and overheating in real time, making assessments more accurate and avoiding the accumulation of hidden dangers that may result from traditional periodic maintenance.

[0079] In this embodiment of the application, the construction of the first quantitative risk assessment model includes: the first quantitative risk assessment model adopts a fuzzy Petri network structure;

[0080] Each data point of the operational risk factor and the state risk factor is defined as a location node; the triggering conditions of each risk factor are defined as transfer nodes according to the fault propagation path.

[0081] The directed arcs connecting location nodes and transfer nodes represent the relationships between risk factors, and a first quantitative risk assessment model is constructed.

[0082] Specifically, a fuzzy Petri network structure is defined, and each data point of the operational risk factor and state risk factor is defined as a location node, where the location node is labeled as Pi, representing the current risk state of the factor, including current overload risk node P1, voltage deviation risk node P2, temperature over-limit risk node P3, aging coefficient risk node P4, insulation loss risk node P5, and connection oxidation risk node P6.

[0083] Based on the fault propagation path, the triggering conditions of each risk factor are defined as transfer nodes, and the transfer nodes are marked as Tij, where i and j are the numbers of the relevant risk factors, including the transfer node T13 from current overload risk to temperature over-limit risk, the transfer node T25 from voltage deviation risk to insulation loss risk, the transfer node T34 from temperature over-limit risk to aging coefficient risk, the transfer node T45 from aging coefficient risk to insulation loss risk, the transfer node T56 from insulation loss risk to connection oxidation risk, and the transfer node T36 from temperature over-limit risk to connection oxidation risk.

[0084] The directed arcs connecting location nodes and transfer nodes represent the relationship between risk factors, forming a fuzzy Petri network (FPN) model.

[0085] By defining operational and state risk factors as location nodes in the FPN model, and defining the fault propagation path between risk factors as transfer nodes, FPN can systematically model the relationships between various risk factors. Connecting location and transfer nodes with directed arcs visualizes the fault propagation path, allowing risk managers to intuitively observe which risks will trigger subsequent faults. This helps identify critical risk paths and understand their transmission patterns, facilitating targeted protection measures for high-risk paths by equipment managers. Furthermore, fuzzy reasoning can determine the overall risk status of the system even when the risk factor status is not explicitly defined as "high risk" or "low risk." Accurate prediction enhances the flexibility and accuracy of risk assessment. By connecting location nodes into a network structure through transfer nodes, the FPN model can dynamically display multiple stages of fault propagation. For example, when current overload risk leads to temperature over-limit risk, and then further propagates to aging factor risk, FPN can dynamically display this series of fault evolution paths. Equipment managers can clearly observe the gradual development process of the risk, facilitating the formulation of phased intervention measures or early warning mechanisms to prevent small risks from gradually evolving into serious accidents. This achieves the effect of quantitatively outputting the overall risk status and risk propagation probability of the system, enabling managers to conduct detailed risk management and analysis of the system.

[0086] S200: Based on the first quantitative risk assessment model, a preliminary risk assessment is made, the risk of fault transmission is analyzed, and the overall risk status value is calculated.

[0087] The preliminary risk assessment based on the first quantitative risk assessment model includes: calculating the fuzzy membership degree of Petri network location nodes; calculating the corresponding fuzzy membership degree based on the current collected data value of each location node; and setting the fuzzy membership degree range [0,1], as follows:

[0088]

[0089] in, Let Ip,i represent the fuzzy membership degree of the i-th risk factor, where Ip,i represents the actual measured value of the i-th risk factor, including current overload rate, voltage deviation rate, temperature over-limit ratio, aging coefficient, insulation loss ratio, and connection oxidation rate, and Im,i represents the maximum reference value of the i-th risk factor, including the maximum value of current overload rate, maximum deviation of voltage deviation rate, maximum value of temperature over-limit, maximum value of service life, minimum insulation resistance threshold, and maximum value of connection oxidation rate.

[0090] Define a fuzzy rule that calculates the sum of the mean and standard deviation of the risk factor based on its historical data membership degree. If the calculated membership degree is greater than the risk threshold, it is judged as high risk; if the calculated membership degree is less than or equal to the risk threshold, it is judged as low risk.

[0091] By converting the collected data into fuzzy membership degrees (range [0,1]), each risk factor of the distribution network equipment can be effectively quantified, making the risk status more intuitive and easy to read. The "IF-THEN" fuzzy rule is defined, and the mean and standard deviation are calculated by combining the historical data of the risk factors and setting the risk threshold. This makes the risk threshold more scientific and dynamic, and can reflect the actual risk level of the equipment at different times and under different conditions. The "high risk" and "low risk" judgment criteria defined by the fuzzy rule provide multi-level risk identification for each risk factor. By calculating the comparison between the fuzzy membership degree and the risk threshold, the system can quickly identify the factors in a high-risk state, thereby prioritizing the handling of the most serious risks. The multi-level identification method greatly improves the sensitivity of the early warning system, ensuring that equipment managers can receive early warning information in a timely manner under high-risk conditions.

[0092] In this embodiment of the application, the analysis of fault propagation risk and the calculation of the overall risk state value include:

[0093] Based on the fuzzy membership degree of each risk factor node, the activation condition value is calculated and expressed as follows:

[0094]

[0095] Where Θij represents the transmission strength of risk factor node Pi to node Pj. and Let Pi and Pj represent the fuzzy membership degrees of risk factor nodes, respectively.

[0096] Based on historical data, we statistically analyze the fault propagation data between different risk factors, and use the sum of the mean and two standard deviations of the corresponding membership degree as the propagation threshold for the corresponding risk factor node. If the calculated condition value is greater than or equal to the propagation threshold, it indicates that there is a high risk of fault transmission between the two corresponding risk factors. If the calculated condition value is less than the propagation threshold, it indicates that there is a low risk of fault transmission between the two corresponding risk factors.

[0097] Based on the determination that the risk of fault transmission is high, the fuzzy membership degree of the risk factor is updated by risk superposition, as follows:

[0098]

[0099] in, This represents the fuzzy membership degree of the updated risk factor node Pj;

[0100] Risk assessment is re-performed based on the updated fuzzy membership, and the risk contribution of each location node to the overall system risk is calculated, expressed as:

[0101]

[0102] Among them, CP i This represents the risk contribution of the i-th position node. represents the nonlinear function of the fuzzy membership of the i-th location nodes after the update, and k represents the natural constant for adjusting the nonlinear effect;

[0103] The contribution values ​​are combined into an overall risk status value using a fuzzy overlay method, as follows:

[0104]

[0105] Where Rsy represents the overall risk status value, and n represents the total number of risk factor nodes;

[0106] The overall risk status value is determined by the sum of the mean and three standard deviations of the historical data as the status threshold. If the overall risk status value is greater than or equal to the status threshold, the overall risk is judged to be relatively high.

[0107] The overall risk status value is determined by the sum of the mean and three standard deviations of the historical data as the status threshold. If the overall risk status value is greater than or equal to the status threshold, the overall risk is judged to be relatively high.

[0108] By calculating activation condition values ​​and propagation thresholds based on the fuzzy membership degrees of different risk factor nodes, the system can dynamically monitor the transmission risk between equipment risk factors. Using the mean and two standard deviations determined from historical data as propagation thresholds, the system can identify risk transmission based on real-time data and historical trends. By updating the risk overlay of fuzzy membership degrees for nodes with high fault transmission risk, the system can more precisely reflect the mutual influence between risk factors. By using nonlinear functions to calculate risk contribution, nodes with high-risk membership degrees are amplified, making their impact on the overall risk more significant. This helps to highlight the impact of key nodes when assessing the overall system risk, ensuring that high-risk nodes are promptly addressed. To enhance the system's early warning sensitivity and prevent significant risks from being underestimated, a fuzzy overlay method is used to combine the risk contribution of each location node into an overall risk status value. This ensures that the risk status of each location node is considered, improving the comprehensiveness of the overall risk status assessment. By calculating the risk contribution and analyzing changes in the overall risk status value, the system can trace back to specific high-risk location nodes when the overall risk status value is high, facilitating the rapid identification of the risk source. Furthermore, the threshold setting combining historical data and standard deviation provides trend analysis of risk changes, offering data support for equipment risk prediction and long-term management. This helps to take preventative measures in advance before risks accumulate or the status deteriorates.

[0109] S300: Construct a second quantitative risk assessment model, which is used to predict changes in risk parameters;

[0110] It should be noted that the Fourier heat conduction model is used to determine the heat diffusion rate, and the dynamic heat release rate is calculated by combining the material's heat of combustion. The rate of change of the dynamic heat release rate at the next moment is then predicted using an LSTM model, including:

[0111] The diffusion characteristics of temperature in the material are calculated using a Fourier heat conduction model based on real-time temperature data, and are expressed as follows:

[0112]

[0113] Where α represents the thermal diffusivity of the equipment material, and T(t) represents the temperature data at the acquisition location. Indicates the thermal diffusion rate;

[0114] The real-time combustion rate is calculated using the thermal diffusion rate and the heat flux of the equipment, and is expressed as:

[0115]

[0116] in, Here, ρ represents the combustion rate, ρ represents the material density, and A represents the surface area of ​​the equipment.

[0117] In this embodiment of the application, a second quantitative risk assessment model is constructed. This model is used to predict changes in risk parameters by: determining the heat diffusion rate using a Fourier heat conduction model, and calculating the dynamic heat release rate by combining the material's combustion heat, expressed as:

[0118]

[0119] Where HRR(t) represents the dynamic heat release rate at time t, and ΔH represents the heat release rate constant of the material;

[0120] The rate of change of dynamic heat release rate ΔHRR(t) is calculated based on the time variation.

[0121] A second quantitative risk assessment model is constructed using an LSTM model, which includes an input layer, an LSTM layer, and an output layer.

[0122] The input layer takes the change rate data of heat release rate at different times as input, the LSTM layer extracts the features of the change rate data of heat release rate at different times as input, retains the temporal information, and the output layer outputs the predicted value of the change rate of heat release rate at the next time step.

[0123] The LSTM model is trained using the training set. The cross-entropy loss function is selected to calculate the difference between the predicted and actual results. The Adam optimizer is used for gradient descent optimization to update the model weights. If the model loss no longer decreases significantly during continuous iteration, the iteration is stopped and the model parameters are output to complete the model training.

[0124] Input the real-time heat release rate change data into the LSTM model to predict the heat release rate change value at the next moment.

[0125] The overall risk status is adaptively and dynamically adjusted based on the rate of change of heat release rate, as follows:

[0126] R'sy=Rsy·(1+ΔHRR(t))

[0127] Here, R'sy represents the updated overall risk status value.

[0128] It should be noted that calculating the temperature diffusion rate using the Fourier heat conduction model allows for precise monitoring of the internal thermal diffusion characteristics of equipment materials based on real-time temperature data. This, combined with the characteristics of material temperature changes, helps identify temperature anomalies and potential combustion risks, enabling risk warnings when early signs of fire appear. The dynamic heat release rate (HRR) is calculated using the thermal diffusion rate, combustion rate, and heat of combustion of the material, allowing the HRR to reflect the combustion characteristics of the equipment in real time. Time-series prediction of the HRR change rate using an LSTM model preserves the temporal characteristics of the HRR, enabling forward-looking analysis of fire risk trends. By predicting the HRR change rate at the next moment, this method can... Issuing early warnings before the peak of fire risk effectively improves the ability to predict fire risks and provides system managers with sufficient reaction time. Based on the HRR change rate prediction results, the overall risk status value is adaptively adjusted, enabling the system to automatically adapt to changes in fire risk. The LSTM model learns from historical HRR change rate data during training, which is not only used for real-time prediction but also for analyzing historical risk data of equipment. This helps equipment managers understand the long-term operating status of equipment. Through the accumulation and trend analysis of historical HRR data, managers can make precise equipment maintenance arrangements, avoid unnecessary downtime and maintenance, and improve equipment operation and maintenance efficiency.

[0129] S400: Dynamically updates the overall risk status value and provides fire risk warnings based on changes in risk parameters;

[0130] In this embodiment of the application, dynamically updating the overall risk status value and combining the changes in risk parameters to conduct fire risk early warning includes: using the sum of the average and standard deviation of the historical heat release rate change rate as the heat release rate threshold;

[0131] If the predicted rate of change of heat release rate at the next moment is greater than or equal to the heat release rate threshold, then the overall risk status value at the current moment is increased to the maximum value, and the overall risk status value is updated.

[0132] If the overall risk status value at the current moment increases to the maximum value, and the change rate of heat release rate at the next moment is less than the heat release rate threshold, the risk status value will recover within the time window of the change rate of heat release rate.

[0133] It should be noted that by setting the heat release rate threshold using the average and standard deviation of historical HRR change rates, the system can identify and respond in advance before the predicted HRR change rate reaches a high-risk moment. When the predicted HRR change rate reaches the threshold, the system automatically increases the overall risk status value to the maximum value, achieving adaptive dynamic adjustment of the risk status. This ensures that the overall risk status can reflect the peak value of fire risk in real time, effectively improving the accuracy and timeliness of the system's risk assessment, avoiding the lag of manual intervention, and ensuring that fire risk is not only based on the current HRR value, but also on dynamic trends and historical patterns, providing more accurate fire precursor monitoring and reducing false alarms and missed alarms.

[0134] In this embodiment of the application, if the overall risk status value is determined to be high based on the updated overall risk status value, an early warning signal is triggered, and a clear sound and visual prompt is issued through the sound and light alarm system to remind the operator that there is a fire risk to the equipment.

[0135] It should also be noted that the system automatically records the time, location, and key risk parameters that trigger a high-risk state, including the current HRR value, temperature, and membership values ​​of each risk factor.

[0136] The warning information is sent to the control center, and a "High Risk Warning" dialog box pops up on the monitoring interface. The corresponding fire warning measures are then implemented according to the fire protection standards of the distribution network equipment.

[0137] Through the sound and visual cues of the audible and visual alarm system, the system can immediately alert operators when a high-risk condition is detected. The automatic recording method ensures the objectivity and completeness of the data, avoiding data omissions or inaccuracies that may be caused by manual recording, and providing a reliable basis for subsequent analysis. By sending the warning information to the control center and popping up a "High-Risk Warning" dialog box on the monitoring interface, the system ensures that management and relevant personnel can be informed of the high-risk status of the equipment in a timely manner.

[0138] Example 2

[0139] Reference Figures 1-3 This is one embodiment of the present invention, which differs from the first embodiment in that it provides a quantitative assessment system for fire risk of distribution network equipment.

[0140] It should be noted that the technical solution of the quantitative fire risk assessment system for distribution network equipment is based on the same concept as the technical solution of the quantitative fire risk assessment method for distribution network equipment described above. For details not described in detail in the technical solution of the quantitative fire risk assessment system for distribution network equipment in this embodiment, please refer to the description of the technical solution of the quantitative fire risk assessment method for distribution network equipment described above.

[0141] This embodiment provides a quantitative assessment system for fire risk of power distribution network equipment, comprising:

[0142] The first assessment model construction module is used to acquire data from distribution network equipment and construct a quantitative risk assessment model based on the data.

[0143] The risk status assessment module is used to make preliminary risk judgments based on the first quantitative risk assessment model, analyze the risk of fault transmission, and calculate the overall risk status value.

[0144] The second assessment model construction module is used to construct a quantitative risk assessment model, which is used to predict changes in risk parameters.

[0145] The risk warning module is used to dynamically update the overall risk status value and provide fire risk warnings based on changes in risk parameters.

[0146] This embodiment also provides an electronic device applicable to the quantitative assessment method of fire risk of distribution network equipment, including:

[0147] The system includes a memory and a processor. The memory stores computer-executable instructions, and the processor executes these instructions to implement the quantitative assessment method for fire risk of distribution network equipment as proposed in the above embodiments.

[0148] This embodiment also provides a storage medium storing a computer program that, when executed by a processor, implements the quantitative assessment method for fire risk of distribution network equipment as proposed in the above embodiments.

[0149] The storage medium proposed in this embodiment and the method for quantitative assessment of fire risk of distribution network equipment proposed in the above embodiments belong to the same inventive concept. Technical details not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0150] Based on the above description of the implementation methods, those skilled in the art can clearly understand that the present invention can be implemented using software and necessary general-purpose hardware, and of course, it can also be implemented using 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. This 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), flash memory, hard disk, or optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of the various embodiments of the present invention.

[0151] 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 it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for quantitatively assessing the fire risk of power distribution network equipment, characterized in that, include: The process involves acquiring data from distribution network equipment and constructing a first quantitative risk assessment model based on that data. The acquired data includes operational and status data of the distribution network equipment. Operational and status risk factors are then defined based on the operational and status data. The construction of the first quantitative risk assessment model utilizes a fuzzy Petri network structure. Each data point of the operational risk factor and the state risk factor is defined as a location node; the triggering conditions of each risk factor are defined as transfer nodes according to the fault propagation path. Directed arcs connecting location nodes and transfer nodes represent the relationships between risk factors, thus constructing a first quantitative risk assessment model; Preliminary risk assessment is performed based on the first quantitative risk assessment model, analyzing the risk of fault transmission and calculating the overall risk status value. The preliminary risk assessment based on the first quantitative risk assessment model includes: calculating the fuzzy membership degree of Petri network location nodes; calculating the corresponding fuzzy membership degree based on the current collected data value of each location node; setting the fuzzy membership degree range to [0,1], as follows: , in, Represents risk factor nodes Fuzzy membership degree, Indicates the first The actual measured value of each risk factor, Indicates the first The maximum reference value for each risk factor; Define fuzzy rules, and calculate the sum of the mean and standard deviation of the risk factors based on the membership degree of the historical data of the risk factors as the risk threshold. If the calculated membership degree is greater than the risk threshold, it is judged as high risk, and if the calculated membership degree is less than or equal to the risk threshold, it is judged as low risk. Analyzing the risk of fault propagation and calculating the overall risk state value includes: Based on the fuzzy membership degree of each risk factor node, the activation condition value is calculated and expressed as follows: , in, Represents risk factor nodes To the node The transmission intensity, Represents risk factor nodes Fuzzy membership degree; Based on historical data, we statistically analyze the fault propagation data between different risk factors, and use the sum of the mean and two standard deviations of the corresponding membership degree as the propagation threshold for the corresponding risk factor node. If the activation condition value is greater than or equal to the propagation threshold, it indicates that there is a high risk of fault propagation between the two corresponding risk factors. If the activation condition value is less than the propagation threshold, it indicates that there is a low risk of fault propagation between the two corresponding risk factors. Based on the determination that the risk of fault transmission is high, the fuzzy membership degree of the risk factor is updated by risk superposition, as follows: , in, This indicates the updated risk factor node. Fuzzy membership degree; Risk assessment is re-performed based on the updated fuzzy membership, and the risk contribution of each location node to the overall system risk is calculated, expressed as: , , in, Represents risk factor nodes Risk contribution Indicates the updated risk factor node The nonlinear function of fuzzy membership degree, This represents the natural constant used to adjust for nonlinear effects; The contribution values ​​are combined into an overall risk status value using a fuzzy overlay method, as follows: , in, Indicates the overall risk status value. Indicates the total number of risk factor nodes; The overall risk status value is determined by the sum of the mean and three standard deviations of the historical data as the status threshold. If the overall risk status value is greater than or equal to the status threshold, the overall risk is judged to be relatively high. A second quantitative risk assessment model is constructed to predict changes in risk parameters. This includes: determining the heat diffusion rate using a Fourier heat conduction model and calculating the dynamic heat release rate based on the material's heat of combustion, expressed as: , in, Indicates time Dynamic heat release rate, This represents the heat release rate constant of the material; The rate of change of dynamic heat release rate is calculated based on time variation. ; A second quantitative risk assessment model is constructed using an LSTM model, which includes an input layer, an LSTM layer, and an output layer. The input layer takes the change rate data of heat release rate at different times as input, the LSTM layer extracts the features of the change rate data of heat release rate at different times as input, retains the temporal information, and the output layer outputs the predicted value of the change rate of heat release rate at the next time step. The LSTM model is trained using the training set. The cross-entropy loss function is selected to calculate the difference between the predicted and actual results. The Adam optimizer is used for gradient descent optimization to update the model weights. If the model loss no longer decreases significantly during continuous iteration, the iteration is stopped and the model parameters are output to complete the model training. Input the real-time heat release rate change data into the LSTM model to predict the heat release rate change value at the next moment. The overall risk status is adaptively and dynamically adjusted based on the rate of change of heat release rate, as follows: , in, This represents the updated overall risk status value; The overall risk status value is dynamically updated, and fire risk warnings are issued in combination with changes in risk parameters, including: using the sum of the average and standard deviation of the historical heat release rate change rate as the heat release rate threshold; If the predicted rate of change of heat release rate at the next moment is greater than or equal to the heat release rate threshold, then the overall risk status value at the current moment is increased to the maximum value, and the overall risk status value is updated. If the overall risk status value increases to its maximum value at the current moment, and the change rate of heat release rate is less than the heat release rate threshold at the next moment, the overall risk status value will recover within the time window of the change rate of heat release rate. If the overall risk status is determined to be high based on the updated overall risk status value, an early warning signal will be triggered, and a clear sound and visual alert will be issued through the audible and visual alarm system to remind operators that there is a fire risk to the equipment.

2. A quantitative assessment system for fire risk of power distribution network equipment, applied to the method described in claim 1, characterized in that, include: The first assessment model construction module is used to acquire data from distribution network equipment and construct a first quantitative risk assessment model based on the data. The risk status assessment module is used to make a preliminary risk judgment based on the first quantitative risk assessment model, analyze the risk of fault transmission, and calculate the overall risk status value. The second assessment model construction module is used to construct a quantitative risk assessment model, which is used to predict changes in risk parameters. The risk warning module is used to dynamically update the overall risk status value and provide fire risk warnings based on changes in the risk parameters.

3. 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, they implement the steps of the quantitative assessment method for fire risk of distribution network equipment as described in claim 1.

4. A computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the steps of the quantitative assessment method for fire risk of distribution network equipment as described in claim 1.

Images