A commercial building fire coupling risk assessment method and device

Abstract

This invention provides a method and device for coupled risk assessment of commercial building fires. The method includes: establishing a multi-level explanatory structure model based on commercial building fire accident characteristics, historical data, and relevant technical standards; constructing an initial static Bayesian network based on the multi-level explanatory structure model through risk factor mapping; optimizing the initial static Bayesian network using the N-K model based on historical commercial building fire accident data to obtain a dynamic Bayesian network model; and determining the probability of commercial building fire risk based on the dynamic Bayesian network model. This invention can effectively improve the accuracy of commercial building fire risk assessment.

Description

Technical Field

[0001] The present invention relates to the technical field of fire risk assessment, and in particular to a commercial building fire coupling risk assessment method and device. Background Art

[0002] In the process of modern urbanization, commercial buildings, as important carriers of urban economic activities, carry multiple functions such as shopping, catering, entertainment, and office. Their internal structures are complex and changeable, with dense spatial layouts and frequent personnel flow. This high degree of functionality and density makes commercial buildings face more severe challenges in the event of a fire than other types of buildings. Once a fire occurs, due to factors such as the complex internal passages, the large number of combustible materials, and the difficulty of evacuating people, it is very easy for the fire to spread rapidly, causing significant casualties and property losses.

[0003] Given the unique and severe nature of fire risks in commercial buildings, conducting scientific and accurate fire risk assessments is crucial. Fire risk assessments not only identify potential fire hazards in advance, providing a scientific basis for building fire protection design, firefighting facility configuration, and emergency response plan development, but also guide effective rescue operations when a fire occurs, minimizing losses.

[0004] However, the fire risk assessment methods currently used have low accuracy and cannot meet the actual needs of commercial building fire risk management. Summary of the Invention

[0005] The present invention provides a commercial building fire coupling risk assessment method and device, which are used to solve the defect of low accuracy of fire risk assessment in the prior art.

[0006] A coupled risk assessment method for commercial building fires, comprising:

[0007] S1. Establish a multi-level explanatory structural model based on the accident characteristics of commercial building fires, historical data of commercial building fires, and relevant technical standards for commercial building fire risk assessment;

[0008] S2. constructing an initial static Bayesian network based on the multi-level explanatory structural model through risk factor mapping;

[0009] S3. Based on historical data of commercial building fire accidents, the initial static Bayesian network is optimized using the NK model to obtain a dynamic Bayesian network model;

[0010] S4. Determine the probability of occurrence of fire risk in commercial buildings based on the dynamic Bayesian network model.

[0011] According to the commercial building fire coupling risk assessment method provided by the present invention, S1 includes:

[0012] S11. Establish a commercial building fire risk assessment system based on the accident characteristics, historical data, and relevant technical standards for commercial building fire risk assessment;

[0013] S12. establishing a multi-level explanatory structure model based on the commercial building fire risk assessment system;

[0014] The commercial building fire risk assessment system includes: a target layer, a criterion layer, and an indicator layer;

[0015] a plurality of criterion factors corresponding to the target layer, and a plurality of indicator factors corresponding to each criterion factor;

[0016] The target layers include: building fire hazard level;

[0017] The criterion layer includes a plurality of criterion factors corresponding to the fire hazard level of the building, including: electrical factors, fire protection system, building environment and fire protection management;

[0018] The index factors corresponding to the electrical factors include: power transformation and distribution equipment, electrical lines, electrical equipment, grounding system and power protection devices;

[0019] The indicators and factors corresponding to the fire protection system include: automatic fire alarm system, automatic fire extinguishing system, smoke prevention and exhaust system, fire water supply and fire hydrant system, emergency lighting and evacuation signs, fire extinguishing and rescue equipment and fire power supply;

[0020] The index factors corresponding to the building environment include: building layout, fire resistance rating, fire protection, smoke partitioning, fire separation measures and safe evacuation;

[0021] The indicator factors corresponding to the fire protection management include: emergency plans and drills, fire prevention inspections and hidden danger rectification, fire and electricity management systems, fire safety education and training, and fire safety systems.

[0022] According to the commercial building fire coupling risk assessment method provided by the present invention, S12 includes:

[0023] (1) According to whether the indicator factors affect each other, construct a directed adjacency matrix F for the indicator factors, F=[f ij ] n×n ; where f ij Representative risk f i f j The influence relationship of n is the number of indicator factors;

[0024] (2) Perform Boolean operations on the directed adjacency matrix F to obtain the connectivity matrix M, which is calculated as follows:

[0025]

[0026] Where r = 1, 2, 3, ..., m; I is the unit matrix of the same order as F;

[0027] (3) Decompose the connectivity matrix to obtain the reachable set R(f i ) and the preceding set Q(f i ): the reachable set R(f i ) represents the risk index f i Starting from, the set of all risk indicators that can be reached through direct or indirect contact; the preceding set Q(f i ) indicates that the risk index f can be reached directly or indirectly i The set of all risk indicators;

[0028] (4) According to the reachable set R(f i ) and the preceding set Q(f i ) intersection, determine the highest set U(f i );

[0029] (5) Take the highest set U(f i ) as the core risk indicator set, remove the core risk indicator set and its corresponding rows and columns to form a new connectivity matrix, and perform steps (3)-(4) again until all risk indicators are assigned to the corresponding levels, thereby obtaining the hierarchical division result;

[0030] (6) According to the reachable set R(f i ) and the preceding set Q(f i ), the highest set U(f i ), and the hierarchical division results, a multi-level explanatory structural model of commercial building fire risk factors was constructed.

[0031] According to the commercial building fire coupling risk assessment method provided by the present invention, S3 includes:

[0032] S31. Analyze the historical data of commercial building fire accidents using the NK model to determine the coupling risk type between different criterion factors;

[0033] S32. Determine the coupling degree of each coupling risk type;

[0034] S33: Based on the coupling degree of each coupling risk type and the temporal characteristics corresponding to each criterion factor, the initial static Bayesian network is optimized to obtain a dynamic Bayesian network model.

[0035] According to the commercial building fire coupling risk assessment method provided by the present invention, the coupling risk types include: two-factor coupling, three-factor coupling and four-factor coupling;

[0036] The two-factor coupling includes: electrical-system, electrical-building, electrical-management, system-building, system-management, building-management;

[0037] The three-factor coupling includes: electrical-system-building, electrical-system-management, electrical-building-management, and system-building-management;

[0038] The four-factor coupling includes: electrical-system-building-management.

[0039] According to the commercial building fire coupling risk assessment method provided by the present invention, the coupling degree is calculated using the following formula:

[0040]

[0041] Where a, b, c, and d represent electrical factors, fire protection system, building environment, and system management, respectively. h,i,j,k It represents the probability of coupling occurrence of electrical factors in state h, fire protection system in state i, building environment in state j, and fire protection management in state k. The criterion layer risk factor is defined as two states, 0 represents that the risk factor does not occur, and 1 represents that the risk factor occurs.

[0042] According to the commercial building fire coupling risk assessment method provided by the present invention, the dynamic Bayesian network model is as follows:

[0043]

[0044] Where, represents a static Bayesian network, Represents the transfer network of each indicator factor in the time dimension, is the i-th indicator in the initial state, is the i-th indicator at time t, for The parent node of for The parent node of , T represents the entire time span corresponding to the dynamic Bayesian network, t represents a time point in the time span, and N represents the number of indicator factors.

[0045] According to the commercial building fire coupling risk assessment method provided by the present invention, S4 includes:

[0046] S41. Based on the coupling degree and historical data of each coupling risk type, calculate the prior probability of each coupling risk and the prior probability of the indicator layer factors respectively;

[0047] S42. Establish a conditional probability table based on the prior probability of each coupling risk and the prior probability of the indicator layer factors;

[0048] S43. Based on the conditional probability table, use the dynamic Bayesian network model to perform forward reasoning to determine the probability of occurrence of commercial building fire risk;

[0049] The building fire risk level is divided into four levels according to the probability of fire risk occurrence. When 0≤P<0.2, it is risk level one, and normal operation and daily maintenance are allowed; when 0.2≤P<0.4, it is risk level two, and operation needs to be monitored and maintenance needs to be strengthened; when 0.4≤P<0.7, it is risk level three, and use should be controlled and repairs should be carried out within a time limit; when 0.7≤P<1, it is risk level four, and use should be stopped and repairs should be carried out immediately.

[0050] According to the commercial building fire coupling risk assessment method provided by the present invention, the prior probability of the indicator layer factors is determined according to the following method:

[0051] (1) Based on the probability of occurrence of each indicator factor, the LEC evaluation method is used to classify the risk of each event into different risk levels. The levels include: VL level, L level, M level, H level, and VH level. Among them, the risk of each event is determined based on the indicator factor and the criterion factor.

[0052] (2) constructing a corresponding membership function for each risk level;

[0053]

[0054] in, 、 、 、 、 They are the membership degrees corresponding to VL level, L level, M level, H level, and VH level, is a fuzzy number;

[0055] (3) Apply the expert's judgment result on the probability of occurrence of each risk factor to the corresponding membership function to obtain the fuzzy number; and summarize the fuzzy numbers of all experts to obtain the final overall fuzzy number of the factors at the same indicator layer;

[0056] (4) Converting the final overall fuzzy number of the same indicator layer factor into a fuzzy possibility score;

[0057] (5) Convert the fuzzy likelihood scores of the same indicator layer factors into prior probabilities.

[0058] The present invention also provides a commercial building fire coupling risk assessment device, comprising:

[0059] Establishing a unit for establishing a multi-level explanatory structural model based on accident characteristics of commercial building fires, historical data of commercial building fires, and relevant technical standards for commercial building fire risk assessment;

[0060] A construction unit, configured to construct an initial static Bayesian network according to the multi-level explanatory structural model through risk factor mapping;

[0061] An optimization unit is used to optimize the initial static Bayesian network using the NK model based on historical data of commercial building fire accidents to obtain a dynamic Bayesian network model;

[0062] The determination unit is used to determine the probability of occurrence of commercial building fire risk based on the dynamic Bayesian network model.

[0063] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, any of the commercial building fire coupling risk assessment methods described above is implemented.

[0064] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for assessing the coupled fire risk of a commercial building as described above is implemented.

[0065] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements any of the above commercial building fire coupling risk assessment methods.

[0066] The commercial building fire coupling risk assessment method and device provided by the present invention uses the NK model to optimize the initial static Bayesian network to obtain a dynamic Bayesian network model through historical data of commercial building fire accidents, and uses the dynamic Bayesian network model to determine the probability of occurrence of commercial building fire risks, which can effectively improve the accuracy of the fire risk probability. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Figure 1 This is a flow chart of the commercial building fire coupling risk assessment method provided by the present invention;

[0068] Figure 2 This is a schematic diagram of the commercial building fire risk index system provided by the present invention;

[0069] Figure 3 It is a multi-level explanatory structural model provided by the present invention;

[0070] Figure 4 This is a schematic diagram of the static Bayesian network structure of commercial building fire risk provided by the present invention;

[0071] Figure 5 It is a schematic diagram of the coupling risk evolution mechanism provided by the present invention;

[0072] Figure 6 This is a schematic diagram of the dynamic Bayesian network structure of the commercial building fire coupling risk provided by the present invention;

[0073] Figure 7 This is a structural block diagram of the commercial building fire coupling risk assessment device provided by the present invention;

[0074] Figure 8 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0075] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some 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 technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0076] At present, commercial building fire risk assessment technology has the following difficulties: First, in fire risk assessment, electrical factors should be regarded as an important evaluation indicator because it is directly related to the safety and reliability of the building's internal electrical system. The electrical factor indicators in the existing commercial building fire risk assessment system are relatively single, and the risk evaluation indicators of electrical factors should be multiple and complex. It is necessary to comprehensively consider multiple factors to fully evaluate the safety performance of the electrical system; Second, the coupling effect between risks is the main driving force for risk evolution, and the existing fire risk assessment method does not fully consider the interdependence between various risk factors, and cannot identify the dependency between accident sequences and various risk factors and quantitatively evaluate their coupling relationship. In response to the shortcomings of the existing technology, the present invention provides a commercial building fire coupling risk assessment method. Figure 1 The flowchart of the coupled risk assessment method for commercial building fire is shown in Figure 2. Figure 1 As shown, the method includes:

[0077] S1. A multi-level explanatory structural model is established based on the accident characteristics, historical data and relevant technical standards for commercial building fire risk assessment.

[0078] Specifically, commercial building fire accident characteristics include: cause of fire, fire development characteristics, fire system response, and building structure. Historical commercial building fire data includes: historical fire accident investigation reports and building fire assessment reports. Historical fire accident investigation reports are documents that provide detailed records and analyses of past commercial building fire accidents. These reports typically include information such as the time, location, cause of fire, fire development, fire system response, casualties, property losses, and post-accident investigation conclusions. By analyzing historical fire accident investigation reports, key risk factors contributing to fires, such as electrical failures, illegal operations, and fire system failures, can be identified. Building fire assessment reports are documents generated after fire safety inspections and assessments of commercial buildings. These reports typically include information on the building's fire system design, the condition of firefighting facilities, the implementation of fire management systems, and the investigation and rectification of fire hazards. Building fire assessment reports provide a comprehensive understanding of the current fire safety status of commercial buildings, including the completeness, effectiveness, and compliance of firefighting facilities. Commercial building fire risk assessment standards refer to a series of specifications, standards, and guidelines developed by authoritative institutions or industry organizations to guide risk assessment practices in this field. These technical standards typically cover aspects such as building fire protection design, fire protection system configuration, fire risk assessment methods, and data collection and analysis.

[0079] Step S1 is explained below, which specifically includes the following two steps:

[0080] S11. Establish a commercial building fire risk assessment system based on the accident characteristics, historical data and relevant technical standards of commercial building fire risk assessment; S12. Establish a multi-level explanatory structure model based on the commercial building fire risk assessment system; among them, the commercial building fire risk assessment system includes: target layer, criterion layer and indicator layer.

[0081] Specifically, the present invention first identifies key risk factors that contribute to fires based on accident characteristics of commercial building fires (e.g., fire cause, fire development characteristics, fire protection system response, building structure, etc.) and historical data (e.g., historical fire accident investigation reports and building fire assessment reports). During this identification process, relevant technical standards, such as building fire protection codes and fire protection system design specifications, are also referenced to ensure that the identified risk factors meet industry standards and practical requirements. The identified risk factors are then classified and organized to construct a commercial building fire risk assessment system consisting of a target layer, a criterion layer, and an indicator layer. Based on the commercial building fire risk system, the evolutionary relationships between the indicator layer factors are analyzed through fire accident case studies to establish a multi-level explanatory structure model.

[0082] This application identifies and sorts out the key fire risk factors of commercial buildings based on accident characteristics and historical data, and then summarizes and classifies these fire risk factors in combination with relevant standards, thereby establishing a commercial building fire risk assessment system. Figure 2 As shown in the figure, the commercial building fire assessment system includes: a first-level risk indicator (i.e., target layer): building fire hazard level; four second-level risk indicators (i.e., criterion layer): electrical factors, fire protection system, building environment and fire management, as well as third-level risk indicators (indicator factors) corresponding to each second-level risk. Among them, the five indicator factors corresponding to electrical factors are power distribution devices, electrical lines, electrical equipment, grounding systems and power protection devices; the seven indicator factors corresponding to fire protection systems are: automatic fire alarm systems, automatic fire extinguishing systems, smoke protection and exhaust systems, fire water supply and fire hydrant systems, emergency lighting and evacuation signs, fire extinguishing and rescue equipment and fire power supply; the five indicator factors corresponding to the building environment are: building layout, fire resistance level, fire protection, smoke protection zoning, fire separation measures and safe evacuation; the five indicator factors corresponding to fire management are: emergency plans and drills, fire inspections and hidden danger rectification, fire and electricity management systems, fire safety education and training and fire safety systems. Based on whether there is a direct impact between all indicator factors, a multi-level explanatory structural model is constructed, as shown in the figure. Figure 3 As shown, the first level {S3, S7, S8, S9, S 11 、S 15 、S 17} is the direct cause of the risk system, levels two to five {S2, S4, S5, S 10 、S 13 、S 14 、S 16 、S 18 、S 20}, {S1, S6, S 12}、{S 19}、{S 21} is the intermediate transition factor of the risk system, level six {S 22} is the fundamental source of the risk system.

[0083] The commercial building fire coupled risk assessment method provided by the present invention establishes a commercial building fire risk assessment system by establishing a multi-level explanatory structural model through the accident characteristics, historical data and commercial building fire risk assessment standards of commercial building fires, making the established assessment system more diverse and complex, so that it can comprehensively consider multiple factors to fully evaluate the safety performance of the electrical system, effectively improving the accuracy of the probability of commercial building fire risk occurrence.

[0084] S2. Based on the multi-level explanatory structural model, an initial static Bayesian network is constructed through risk factor mapping.

[0085] Specifically, each factor in the multi-level explanatory structural model is converted into a node, and the relationship between each factor is converted into a directed edge. The “commercial building fire risk level” is defined as the top risk event I, and the initial static Bayesian network is constructed, as shown in the following example: Figure 4 As shown, Y indicates that the risk occurs and N indicates that the risk does not occur.

[0086] S3. Based on the historical data of commercial building fire accidents, the NK model is used to optimize the initial static Bayesian network to obtain a dynamic Bayesian network model.

[0087] Specifically, during the operation of commercial buildings, adverse effects on electrical factors, fire protection systems, building environment, and fire protection management will impact the risk system. However, a single risk factor is often difficult to break through the safety threshold of the risk system. When multiple factors are coupled together, the risk level increases, causing damage to the risk system and ultimately leading to accidents. Risk coupling types can be divided into three categories: single-factor coupling, dual-factor coupling, and multi-factor coupling. Figure 5 As shown. While the initial static Bayesian network cannot estimate the nonlinear synergistic effects between risk factors, the NK model, as a tool for analyzing the interactions of complex adaptive systems, can use historical data to identify which combinations of risk factors lead to an exponential increase in the probability of a fire accident. For example, the probability of a fire caused by a Level 3 risk indicator electrical wiring is 10%, while the probability of a fire caused by an automatic fire alarm system is 3%. However, when both the electrical wiring and the automatic fire alarm system fail simultaneously, the probability of a fire occurring is 40%, not 13%. Therefore, the NK model can improve the accuracy of fire risk probability predictions.

[0088] In addition, since the static Bayesian network can only analyze the risk relationship at the current moment and cannot predict the probability of fire risk based on real-time data, the probability of fire will be seriously underestimated. However, this application optimizes the initial static Bayesian network by combining historical data of commercial building fire accidents, so that the obtained dynamic Bayesian network model can know the probability of fire risk at each moment and predict the probability of fire risk at a certain moment in the future, thereby improving the accuracy and time range of predicting the probability of fire risk. At the same time, combined with the NK model, the NK model is used to model the interaction between the internal variables of the fire system, revealing the coupling relationship between different risk factors, thereby improving the prediction accuracy of the probability of fire risk.

[0089] S4. Determine the probability of occurrence of fire risk in commercial buildings based on the dynamic Bayesian network model.

[0090] Specifically, the probability of occurrence of fire risks in commercial buildings can be used to determine the building fire risk level, and then corresponding risk management measures can be proposed based on the fire risk level.

[0091] The commercial building fire coupling risk assessment method provided by the present invention uses the NK model to optimize the initial static Bayesian network to obtain a dynamic Bayesian network model through historical data of commercial building fire accidents, and uses the dynamic Bayesian network model to determine the probability of occurrence of commercial building fire risks, which can effectively improve the accuracy of the fire risk probability.

[0092] Furthermore, the following describes how to establish a multi-level explanatory structure model, which specifically includes the following steps:

[0093] (1) According to whether the indicator factors affect each other, construct a directed adjacency matrix F for the indicator factors, that is, F=[f ij ] n×n , where f ij Representative risk f i f j The influence relationship of n is the number of indicator factors.

[0094] Specifically, based on fire accident cases, the evolution relationship of the indicator factors of the fire assessment system is analyzed. During the fire accident, if the risk indicator f i For f j There is a direct impact on the occurrence of ij For example, line aging or short circuit may directly damage electrical equipment. In this case, electrical line S2 has a direct impact on electrical equipment S3. Then f 23 (i≠j) is assigned a value of 1, and the failure of the power distribution device will cause the electrical line to overload, which will in turn cause damage to the electrical equipment. At this time, the power distribution device S1 has no direct impact on the electrical equipment S3, then f 13 Assign 0; the same risk index (i=j) is assigned 0, and the directed adjacency matrix F of the third-level index is constructed, that is, F=[f ij ] n×n .

[0095] (2) Perform Boolean operations on the directed adjacency matrix F to obtain the connectivity matrix M, which is calculated as follows:

[0096]

[0097] Where r = 1, 2, 3, ..., m, m is a non-zero constant; I is the identity matrix of the same order as F;

[0098] (3) Decompose the connectivity matrix to obtain the reachable set R(f i ) and the preceding set Q(fi ); where the reachable set R(f i ) represents the risk index f i Starting from the set of all risk indicators that can be reached through direct or indirect connections, that is, the set of elements containing 1 in the corresponding row of a certain element of the connectivity matrix; the preceding set Q(f i ) indicates that the risk index f can be reached directly or indirectly i The set of all risk indicators, that is, the set of elements containing 1 in the corresponding column of a certain element of the connectivity matrix;

[0099] (4) The reachable set R(f i ) and the preceding set Q(f i ) as the highest set U(f i );

[0100] (5) Take the highest set U(f i ) as the core risk indicator set, remove the core risk indicator set and its corresponding rows and columns to form a new connectivity matrix, and perform steps (3)-(4) again until all risk indicators are assigned to the corresponding levels, thereby obtaining the hierarchical division results, as shown in Table 1:

[0101] Table 1:

[0102] (6) According to the reachable set R(f i ) and the preceding set Q(f i ), the highest set U(f i ), and the hierarchical division results, a multi-level explanatory structural model of commercial building fire risk factors was constructed.

[0103] The method provided by the present invention constructs a directed adjacency matrix F and performs Boolean operations to obtain a connectivity matrix M, then decomposes the connectivity matrix to obtain a reachable set and a precedent set to construct a multi-level explanatory structural model. The constructed multi-level explanatory structural model improves the accuracy and efficiency of commercial building fire risk assessment.

[0104] Furthermore, step S2 is described in detail below:

[0105] First, based on the hierarchical relationships among the target layer, criterion layer, and indicator factors, each risk factor in the multi-level explanatory structural model is mapped as a node in a Bayesian network. Directed edges are then established within the Bayesian network based on the correlations among risk factors within the multi-level explanatory structural model. The direction of the edge represents the causal or conditional dependency relationship between risk factors. Historical data related to each risk factor is collected, including the frequency of occurrence of each factor under different states and the joint frequency of occurrence between factors. Based on this collected data, the conditional probability of each node under different states of its parent node is estimated. These conditional probabilities form a conditional probability table, which is used for inference calculations within the Bayesian network. All nodes, directed edges, and conditional probability tables are integrated to form the structure of a static Bayesian network.

[0106] Further, step S3 is described in detail below, which specifically includes the following scheme:

[0107] Firstly, the NK model is used to analyze the historical data of commercial building fire accidents to determine the coupling risk types between different criterion factors. Secondly, the coupling degree of each coupling risk type is determined. Finally, based on the coupling degree of the coupling risk type, the coupling disaster-causing characteristics of commercial building fire risks, and the temporal characteristics of the indicator factors, the initial static Bayesian network is optimized to obtain a dynamic Bayesian network model.

[0108] Specifically, historical data on commercial building fire accidents includes information such as the time, location, cause, losses, operational status of firefighting facilities, and building usage. This data is processed to generate encoded historical data. This encoded historical data is then fed into the NK model to create a commercial building fire accident model. All criterion factors (electrical factors, fire protection systems, building environment, and fire management) are then substituted into the commercial building fire accident model to analyze the coupling relationships between these criterion factors, thereby identifying coupling risk types. For example, if lax enforcement of fire and electricity management regulations leads to illegal use of fire within the building, igniting combustibles, and a malfunction in the automatic fire alarm system, the fire spreads and ultimately leads to a fire accident. This accident is caused by the coupling between the fire protection system and fire management. In this case, the failure of the criterion factor (fire protection system) and the lack of the criterion factor (fire protection management) together lead to the fire, resulting in a two-factor coupling (system-management) between the fire protection system and fire management. The coupling degree of each coupling risk type is then calculated. Finally, the calculated coupling degree and the determined disaster-causing characteristics (such as fire spread speed and smoke diffusion characteristics) are integrated into the static Bayesian network to adjust the parameters of the static Bayesian network. Then, based on the temporal characteristics of all indicator factors, the static Bayesian network with adjusted parameters is optimized to obtain a dynamic Bayesian network model. The dynamic Bayesian network model is as follows:

[0109]

[0110] Where B0 represents the initial state of the commercial building fire index factor (i.e., static Bayesian network), B → Represents the transfer network of each indicator factor in the time dimension, is the i-th indicator in the initial state, is the i-th indicator at time t, for The parent node of for The parent node of , T represents the entire time span corresponding to the dynamic Bayesian network, t represents a time point in the time span, and N represents the number of indicator factors.

[0111] In the embodiment of the present invention, the coupling risk types include three categories: two-factor coupling, three-factor coupling, and four-factor coupling.

[0112] Among them, the two-factor coupling includes: electrical-system O 21（a,b） 、Electrical-Building 22（a,c） 、Electrical-Management 23（a,d） 、System-ArchitectureO 24（b,c） , System-Management 25（b,d） 、Construction-Management 26（c,d） ; Three-factor coupling includes: electrical-system-building 31（a,b,c） , Electrical-System-Management 32（a,b,d） 、Electrical-Construction-Management 33（a,c,d） , Systems-Architecture-Management 34（b,c,d） ; Four-factor coupling includes: electrical-system-building-management 4（a,b,c,d） .

[0113] The following uses the four-factor coupling as an example to explain how to obtain the coupling degree of each coupling risk type. For details, please refer to the following formula:

[0114]

[0115] Where a, b, c, and d represent electrical factors, fire protection system, building environment, and fire protection management, respectively. h,i,j,k It represents the probability of the coupling of electrical factors in state h, fire protection system in state i, building environment in state j, and fire protection management in state k. The criterion layer risk factor is defined as two states, that is, 0 represents that the risk factor does not occur, and 1 represents that the risk factor occurs, for example, P .1.. Indicates the risk of fire protection system occurrence. Other factors can occur or not occur. The coupling degree of each coupling risk type is shown in Table 2:

[0116] Table 2

[0117] Furthermore, the following describes how to determine the probability of fire risk in commercial buildings based on a dynamic Bayesian network model, specifically including the following solutions:

[0118] First, based on the coupling degree and historical data of each coupling risk type, the prior probability of each coupling risk and the prior probability of the indicator layer factors are calculated respectively.

[0119] Specifically, based on the coupling degree and historical data for each coupling risk type, we derive the prior probability of each coupling risk type and the prior probability of the indicator-level risk factors. The coupling degree of different coupling risk types is calculated based on the number of risk couplings. A higher coupling degree indicates a greater risk type and a greater probability of simultaneous occurrence. Therefore, the coupling degree can represent the prior probability of different coupling risk types. The prior probability of the indicator-level factors is derived using the LEC evaluation method.

[0120] Secondly, a conditional probability table is established based on the prior probability of each coupling risk and the prior probability of the indicator layer factors.

[0121] Specifically, in a Bayesian network, non-root nodes are nodes that have at least one parent node, meaning they have one or more incoming edges and are not top-level nodes in the network. Non-root nodes represent factors or observations in the network that depend on other variables, and their states are directly affected by their parent nodes. Conditional probabilities can be calculated using the following formula:

[0122]

[0123] Among them, P(S i )、P(S j ) is the prior probability, which represents people’s understanding and estimation based on the existing knowledge and experience system. i |S j ) is the posterior probability, which means that when acquiring new information (knowing S j People's new understanding after the occurrence of

[0124] Taking electrical circuit factors as an example, emergency plans and drills 18 The status of the fire safety system 22 Fire safety education and training 21 Direct impact, emergency plans and drills 18 The expert judgment results of the conditional probability distribution of are shown in Table 3.

[0125] Table 3

[0126]

[0127] Then, the expert judgment results are defuzzified to obtain the emergency plan and drill S 18 The conditional probability values ​​are shown in Table 4. Indicates that the factor occurs, Indicates that the factor does not occur.

[0128] Table 4

[0129]

[0130] Finally, based on the above conditional probability table, the dynamic Bayesian network model is used for forward reasoning to determine the probability of occurrence of commercial building fire risk.

[0131] Specifically, since each factor in the risk system has two states, 0 represents that the risk factor does not occur, and 1 represents that the risk factor occurs, the state transition matrix can be obtained:

[0132]

[0133] Where p is the probability that the system factor changes from a normal state to a fault state. When the value of p is equal to When , we can obtain the following conditional probability:

[0134]

[0135] According to the prior probability, conditional probability and transfer network of each risk factor, a dynamic Bayesian network model considering the risk coupling effect is constructed, such as Figure 6 The building fire risk level provided by the embodiment of the present invention is divided into four levels according to the probability of fire risk occurrence: when 0≤P<0.2, it is risk level 1, and normal operation and routine maintenance can be carried out; when 0.2≤P<0.4, it is risk level 2, and operation monitoring and enhanced maintenance are required; when 0.4≤P<0.7, it is risk level 3, and use should be controlled and repairs should be carried out within a specified period; when 0.7≤P<1, it is risk level 4, and use should be stopped and repairs should be carried out immediately.

[0136] Furthermore, the prior probability of the above-mentioned indicator-level risk factors is calculated as follows:

[0137] Since the commercial space fire risk system is a complex network system involving multiple risk factors and is dynamic and fuzzy, the Delphi method is used to select relevant experts in this field to judge the failure possibility of basic events.

[0138] (1) Based on the probability of occurrence of each indicator factor, the LEC evaluation method is used to classify the risk of each event into different risk levels. The levels include: very high (VH), high (H), medium (M), low (L) and very low (VL). Among them, the risk of each event is determined based on the indicator factor and the criterion factor.

[0139] (2) Construct a corresponding membership function for each risk level;

[0140] Specifically, different membership functions are constructed according to the different levels of experts' judgment on basic events. For example, formula (1) corresponds to the VL level, formula (2) corresponds to the L level, formula (3) corresponds to the M level, formula (4) corresponds to the H level, and formula (5) corresponds to the VH level. Through these formulas, the experts' judgment levels on each basic event are fuzzified and converted into corresponding fuzzy numbers.

[0141]

[0142]

[0143]

[0144]

[0145]

[0146] in, 、 、 、 、 They are the membership degrees corresponding to VL level, L level, M level, H level, and VH level, is a fuzzy number.

[0147] (3) Apply the expert's judgment result on the probability of occurrence of each risk factor to the corresponding membership function to obtain the fuzzy number; and summarize the fuzzy numbers of all experts to obtain the final overall fuzzy number of all experts for the same basic event.

[0148] Specifically, the judgments of each expert are aggregated into fuzzy numbers to obtain the final overall fuzzy number of all experts for the same basic event. The calculation formula is as follows:

[0149]

[0150] Among them, is the total fuzzy number of the i-th basic event, is the fuzzy number of the jth expert’s judgment result on the ith basic event, o is the total number of basic events evaluated, and q is the total number of experts participating in the judgment.

[0151] (4) Convert the overall fuzzy number into a fuzzy probability score, where F represents the processed fuzzy probability score:

[0152]

[0153] (5) Convert the fuzzy probability score into an accurate failure probability P F :

[0154]

[0155] For example: The five experts' judgment results on the probability of risk of electrical circuit S2 are H, VH, H, M, and VH respectively. The corresponding fuzzy numbers are (0.6, 0.75, 0.9), (0.8, 0.9, 1), (0.6, 0.75, 0.9), (0.3, 0.5, 0.7), and (0.8, 0.9, 1). The overall fuzzy number is (0.62, 0.76, 0.9). After defuzzifying the overall fuzzy number, it can be obtained that the probability of risk of electrical circuit S2 is 0.0282.

[0156] Finally, the commercial building fire coupling risk assessment method provided by the present invention is generally introduced, which includes the following steps:

[0157] S1. Based on the accident characteristics, historical data and relevant technical standards of commercial building fires, starting from the main disaster-causing factors of commercial buildings, identify the key fire risk factors of commercial buildings and establish a three-level assessment indicator system for commercial building fire risks;

[0158] S2. Based on the commercial building fire risk index system, the evolution relationship between the third-level fire risk index factors is analyzed through fire accident cases, and a multi-level explanatory structural model is established;

[0159] S3. Based on the multi-level explanatory structural model, the initial static Bayesian network is obtained through risk factor mapping;

[0160] S4. Based on historical data of commercial building fire accidents, the NK model is used to analyze the coupling disaster characteristics of the second-level risk indicator factors and obtain the coupling degree of different coupling risk types;

[0161] S5. Based on the characteristics of commercial building fire risk coupling and the temporal characteristics of risk factors, the initial static Bayesian network is improved to establish a dynamic Bayesian network model for commercial building fire coupling risk.

[0162] S6. Based on the coupling degree and historical data of the coupling risk, calculate the prior probabilities of the coupling risk and the third-level risk indicator factors respectively and establish a conditional probability table;

[0163] S7. Based on the conditional probability table, the dynamic Bayesian model is used to forward infer the probability of occurrence of commercial building fire risks, determine the building fire risk level, and propose corresponding risk management measures.

[0164] In summary, the present invention can achieve objective and accurate dynamic assessment of the coupling risk of fire in commercial buildings, identify key factors affecting the occurrence of fire, and propose targeted control measures, effectively improving building safety.

[0165] The commercial building fire coupling risk assessment device provided by the present invention is described below. The commercial building fire coupling risk assessment device described below and the commercial building fire coupling risk assessment method described above can be referenced to each other.

[0166] like Figure 7 As shown, the commercial building fire coupling risk assessment device provided by the embodiment of the present invention includes:

[0167] Establishing unit 701, for establishing a multi-level explanatory structure model based on accident characteristics of commercial building fires, historical data of commercial building fires, and relevant technical standards for commercial building fire risk assessment;

[0168] A construction unit 702 is used to construct an initial static Bayesian network based on the multi-level explanatory structural model through risk factor mapping;

[0169] The optimization unit 703 is configured to optimize the initial static Bayesian network using the NK model based on the historical data of commercial building fire accidents to obtain a dynamic Bayesian network model;

[0170] The determination unit 704 is configured to determine the occurrence probability of the commercial building fire risk based on the dynamic Bayesian network model.

[0171] Figure 8 An example of a physical structure diagram of an electronic device is shown below. Figure 8 As shown, the electronic device may include: a processor 810, a communications interface 820, a memory 830, and a communication bus 840, wherein the processor 810, the communications interface 820, and the memory 830 communicate with each other via the communication bus 840. The processor 810 may call the logic instructions in the memory 830 to execute the commercial building fire coupling risk assessment method, which includes:

[0172] S1. Establish a multi-level explanatory structural model based on the accident characteristics of commercial building fires, historical data of commercial building fires, and relevant technical standards for commercial building fire risk assessment;

[0173] S2. Based on the multi-level explanatory structural model, an initial static Bayesian network is constructed through risk factor mapping;

[0174] S3. Based on the historical data of commercial building fire accidents, the NK model is used to optimize the initial static Bayesian network to obtain a dynamic Bayesian network model;

[0175] S4. Determine the probability of occurrence of fire risk in commercial buildings based on the dynamic Bayesian network model.

[0176] Furthermore, the logic instructions in the aforementioned memory 830 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the various embodiments of the method of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0177] In another aspect, the present invention further provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can perform the commercial building fire coupling risk assessment method provided by the above methods, which includes:

[0178] S1. Establish a multi-level explanatory structural model based on the accident characteristics of commercial building fires, historical data of commercial building fires, and relevant technical standards for commercial building fire risk assessment;

[0179] S2. Based on the multi-level explanatory structural model, an initial static Bayesian network is constructed through risk factor mapping;

[0180] S3. Based on the historical data of commercial building fire accidents, the NK model is used to optimize the initial static Bayesian network to obtain a dynamic Bayesian network model;

[0181] S4. Determine the probability of occurrence of fire risk in commercial buildings based on the dynamic Bayesian network model.

[0182] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for assessing the coupled fire risk of commercial buildings provided by the above methods is implemented. The method comprises:

[0183] S1. Establish a multi-level explanatory structural model based on the accident characteristics of commercial building fires, historical data of commercial building fires, and relevant technical standards for commercial building fire risk assessment;

[0184] S2. Based on the multi-level explanatory structural model, an initial static Bayesian network is constructed through risk factor mapping;

[0185] S3. Based on the historical data of commercial building fire accidents, the NK model is used to optimize the initial static Bayesian network to obtain a dynamic Bayesian network model;

[0186] S4. Determine the probability of occurrence of fire risk in commercial buildings based on the dynamic Bayesian network model.

[0187] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units. That is, they may be located in one place or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0188] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion 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 ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0189] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A commercial building fire coupling risk assessment method, characterized in that: include: S1. Establish a multi-level explanatory structural model based on the accident characteristics of commercial building fires, historical data of commercial building fires, and relevant technical standards for commercial building fire risk assessment; S2. constructing an initial static Bayesian network based on the multi-level explanatory structural model through risk factor mapping; S3. Based on historical data of commercial building fire accidents, the initial static Bayesian network is optimized using the NK model to obtain a dynamic Bayesian network model; S4. Determine the probability of occurrence of commercial building fire risk based on the dynamic Bayesian network model; The S3 includes: S31. Analyze the historical data of commercial building fire accidents using the NK model to determine the coupling risk type between different criterion factors; S32. Determine the coupling degree of each coupling risk type; S33, based on the coupling degree of each coupling risk type and the temporal characteristics corresponding to each criterion factor, optimizing the initial static Bayesian network to obtain a dynamic Bayesian network model; Said S1 comprises: S11. Establish a commercial building fire risk assessment system based on the accident characteristics, historical data, and relevant technical standards for commercial building fire risk assessment; S12. establishing a multi-level explanatory structure model based on the commercial building fire risk assessment system; The commercial building fire risk assessment system includes: a target layer, a criterion layer, and an indicator layer; a plurality of criterion factors corresponding to the target layer, and a plurality of indicator factors corresponding to each criterion factor; The target layers include: building fire risk level; The criterion layer includes a plurality of criterion factors corresponding to the building fire risk level, including: electrical factors, fire protection system, building environment and fire protection management; The index factors corresponding to the electrical factors include: power transformation and distribution equipment, electrical lines, electrical equipment, grounding system and power protection devices; The indicators and factors corresponding to the fire protection system include: automatic fire alarm system, automatic fire extinguishing system, smoke prevention and exhaust system, fire water supply and fire hydrant system, emergency lighting and evacuation signs, fire extinguishing and rescue equipment and fire power supply; The index factors corresponding to the building environment include: building layout, fire resistance level, smoke partition, fire separation measures and safe evacuation; The indicators and factors corresponding to the fire management mentioned above include: emergency plans and drills, fire inspections and hidden danger rectification, fire and electricity management systems, fire safety education and training, and fire safety systems; The S4 includes: S41. Based on the coupling degree and historical data of each coupling risk type, calculate the prior probability of each coupling risk and the prior probability of the indicator layer factors respectively; S42. Establish a conditional probability table based on the prior probability of each coupling risk and the prior probability of the indicator layer factors; S43. Based on the conditional probability table, forward reasoning is performed using the dynamic Bayesian network model to determine the probability of occurrence of fire risk in commercial buildings.

2. The commercial building fire coupling risk assessment method according to claim 1, characterized in that: The S12 includes: (1) According to whether the index factors affect each other, construct a directed adjacency matrix F for the index factors, F = [f ij ] n×n ; where f ij Representative risk f i f j The influence relationship of n is the number of indicator factors; (2) Perform Boolean operations on the directed adjacency matrix F to obtain the connectivity matrix M, which is calculated as follows: M=(F+I) r+1 =(F+l) r ≠(F+I) r-1 Where r = 1, 2, 3, ..., m; I is the unit matrix of the same order as F; (3) Decompose the connectivity matrix to obtain the reachable set R(f i ) and the preceding set Q(f i ): the reachable set R(f i ) represents the risk index f i Starting from, the set of all risk indicators that can be reached through direct or indirect contact; the preceding set Q(f i ) indicates that the risk index f can be reached directly or indirectly i The set of all risk indicators; (4) According to the reachable set R(f i ) and the preceding set Q(f i ) intersection, determine the highest set U(f i ); (5) With the highest set U(f i ) as the core risk indicator set, remove the core risk indicator set and its corresponding rows and columns to form a new connectivity matrix, and perform steps (3)-(4) again until all risk indicators are assigned to the corresponding levels, thereby obtaining the hierarchical division result; (6) According to the reachable set R(f i ) and the preceding set Q(f i ), the highest set U(f i ), and the hierarchical division results, a multi-level explanatory structural model of commercial building fire risk factors was constructed.

3. The commercial building fire coupling risk assessment method according to claim 1, characterized in that: The coupling risk types include: two-factor coupling, three-factor coupling and four-factor coupling; The two-factor coupling includes: electrical-system, electrical-building, electrical-management, system-building, system-management, building-management; The three-factor coupling includes: electrical-system-building, electrical-system-management, electrical-building-management, and system-building-management; The four-factor coupling includes: electrical-system-building-management.

4. The commercial building fire coupling risk assessment method according to claim 1, characterized in that: The coupling degree is calculated using the following formula: Where a, b, c, and d represent electrical factors, fire protection system, building environment, and fire protection management, respectively. h,i,j,k It represents the probability of coupling occurrence of electrical factors in state h, fire protection system in state i, building environment in state j, and fire protection management in state k. The criterion layer risk factor is defined as two states, 0 represents that the risk factor does not occur, and 1 represents that the risk factor occurs.

5. The commercial building fire coupling risk assessment method according to claim 1, characterized in that: The dynamic Bayesian network model is as follows: Where, represents a static Bayesian network, Represents the transfer network of each indicator factor in the time dimension, is the i-th indicator in the initial state, is the i-th indicator at time t, for The parent node of for The parent node of , T represents the entire time span corresponding to the dynamic Bayesian network, t represents a time point in the time span, and N represents the number of indicator factors.

6. The commercial building fire coupling risk assessment method according to claim 1, characterized in that: The building fire risk level is divided into four levels according to the probability of fire risk. When 0≤P<0.2, it is risk level 1, and normal operation and routine maintenance can be carried out; when 0.2≤P<0.4, it is risk level 2, and monitoring operation and enhanced maintenance are required; When 0.4≤P<0.7, it is the third risk level, and its use should be controlled and repaired within a time limit; when 0.7≤P<1, it is the fourth risk level, and its use should be stopped and repaired immediately.

7. The commercial building fire coupling risk assessment method according to claim 1, characterized in that: The prior probability of the indicator layer factors is determined as follows: (1) Based on the probability of occurrence of each indicator factor, the LEC evaluation method is used to classify the risk of each event into different risk levels; The levels include: VL level, L level, M level, H level, and VH level; the risk of each event is determined based on both indicator factors and criterion factors; (2) constructing a corresponding membership function for each risk level; Among them, β VL (ω), β L (ω), β M (ω), β H (ω), β VH (ω) are the membership degrees corresponding to VL level, L level, M level, H level, and VH level, respectively, and ω is a fuzzy number; (3) Apply the expert's judgment result on the probability of occurrence of each risk factor to the corresponding membership function to obtain the fuzzy number; and summarize the fuzzy numbers of all experts to obtain the final overall fuzzy number of the factors at the same indicator layer; (4) converting the final overall fuzzy number of the same indicator layer factor into a fuzzy possibility score; (5) Convert the fuzzy possibility scores of the same indicator layer factors into prior probabilities.

8. A commercial building fire coupling risk assessment device, characterized in that: include: Establishing a unit for establishing a multi-level explanatory structure model based on accident characteristics of commercial building fires, historical data on commercial building fires, and relevant technical standards for commercial building fire risk assessment; A construction unit, configured to construct an initial static Bayesian network according to the multi-level explanatory structural model through risk factor mapping; An optimization unit is used to optimize the initial static Bayesian network using the NK model based on historical data of commercial building fire accidents to obtain a dynamic Bayesian network model; a determination unit, configured to determine the probability of occurrence of a commercial building fire risk based on the dynamic Bayesian network model; Wherein, the establishing unit is further used for: Establish a commercial building fire risk assessment system based on accident characteristics, historical data, and relevant technical standards for commercial building fire risk assessment; and establish a multi-level explanatory structure model based on the commercial building fire risk assessment system. The commercial building fire risk assessment system includes: a target layer, a criterion layer, and an indicator layer; a plurality of criterion factors corresponding to the target layer, and a plurality of indicator factors corresponding to each criterion factor; The target layers include: building fire risk level; The criterion layer includes a plurality of criterion factors corresponding to the building fire risk level, including: electrical factors, fire protection system, building environment and fire protection management; The index factors corresponding to the electrical factors include: power transformation and distribution equipment, electrical lines, electrical equipment, grounding system and power protection devices; The indicators and factors corresponding to the fire protection system include: automatic fire alarm system, automatic fire extinguishing system, smoke prevention and exhaust system, fire water supply and fire hydrant system, emergency lighting and evacuation signs, fire extinguishing and rescue equipment and fire power supply; The index factors corresponding to the building environment include: building layout, fire resistance level, smoke partition, fire separation measures and safe evacuation; The indicators and factors corresponding to the fire management mentioned above include: emergency plans and drills, fire inspections and hidden danger rectification, fire and electricity management systems, fire safety education and training, and fire safety systems; The optimization unit is further configured to: Analyzing the historical data of commercial building fire accidents using the NK model to determine the coupling risk types between different criterion factors; determining the coupling degree of each coupling risk type; and optimizing the initial static Bayesian network based on the coupling degree of each coupling risk type and the time series characteristics corresponding to each criterion factor to obtain a dynamic Bayesian network model. The determining unit is further configured to: Based on the coupling degree and historical data of each coupling risk type, the prior probability of each coupling risk and the prior probability of the indicator layer factors are calculated respectively; Establish a conditional probability table based on the prior probability of each coupling risk and the prior probability of the indicator layer factors; Based on the conditional probability table, the dynamic Bayesian network model is used to perform forward reasoning to determine the probability of occurrence of commercial building fire risks.

Images