High-rise building layered electrical safety risk assessment method and system based on fuzzy Bayesian network

Abstract

The invention discloses a high-rise building layered electrical safety risk assessment method and system based on a fuzzy Bayesian network. The method comprises the following steps: determining floor function information of each floor in a high-rise building; classifying all floors of the high-rise building according to functions according to the floor function information to obtain a preset number of floor classification sets; according to the function corresponding to each floor classification set, a preset number of first-level electrical risk indexes are selected, and according to the first-level electrical risk indexes, a preset number of second-level electrical risk indexes belonging to the first-level electrical risk indexes are selected; constructing a Bayesian network by taking the risk probability of each floor classification set as a leaf node, the first-level electrical risk index as an intermediate node and the second-level electrical risk index as a root node; the risk probability and consequence loss of each floor classification set are obtained according to the Bayesian network in combination with the fuzzy theory; and obtaining the risk level of each floor classification set according to the risk probability and the consequence loss.

Description

Technical Field

[0001] The present invention relates to the field of electrical safety risk assessment for high-rise buildings, and particularly to a hierarchical electrical safety risk assessment method and system for high-rise buildings based on a fuzzy Bayesian network. Background Art

[0002] With the continuous expansion of the scale of high-rise buildings, their electrical systems face severe safety challenges due to characteristics such as high load density, complex equipment associations, and dense personnel. Old high-rise buildings are more prone to chain accidents such as power outages, electric shocks, and fires caused by local failures due to equipment aging and insufficient maintenance. The electrical risks in different functional floor areas of high-rise buildings have different characteristics, and traditional "one-size-fits-all" risk assessment methods are difficult to accurately reflect their dynamic risk characteristics. Therefore, constructing a hierarchical and quantitative electrical safety risk assessment system has become an urgent need to improve the safety management of high-rise buildings.

[0003] Currently, research on electrical safety issues in high-rise buildings mainly focuses on two directions: electrical facility fault diagnosis and fire risk assessment. The former mainly constructs the association between faults and data characteristics by analyzing the data characteristics of electrical facilities. The latter establishes an assessment framework based on the causal derivation between risk events and fires. However, existing methods have certain limitations. For example, they focus on a single risk dimension such as equipment failures, lacking systematic integration of electrical safety risks; the probabilities and weights of risk indicators rely on expert experience, with strong subjectivity and uncertainty; the impact of risk differences in building floor areas is not fully considered, resulting in insufficient adaptability of the assessment results to the actual scenario.

[0004] Therefore, there is an urgent need for a new technical solution to solve the technical problem of how to comprehensively and accurately assess the electrical safety risks of high-rise buildings. Summary of the Invention

[0005] The present invention provides a hierarchical electrical safety risk assessment method and system for high-rise buildings based on a fuzzy Bayesian network to solve the technical problem of how to comprehensively and accurately assess the electrical safety risks of high-rise buildings.

[0006] To achieve the above object, the present invention provides a hierarchical electrical safety risk assessment method for high-rise buildings based on a fuzzy Bayesian network, including: determining the floor function information of each floor in a high-rise building;

[0007] Classifying each floor of the high-rise building according to function based on the floor function information to obtain a preset number of floor classification sets; the floor function information includes function information considering the height where the floor is located;

[0008] Select a preset number of first-level electrical risk indicators according to the functions corresponding to each floor classification set, and select a preset number of second-level electrical risk indicators subordinate to the first-level electrical risk indicators according to the first-level electrical risk indicators;

[0009] Construct a Bayesian network with the risk probability of each floor classification set as the leaf node, the first-level electrical risk indicators as the intermediate nodes, and the second-level electrical risk indicators as the root nodes;

[0010] Obtain the risk probability and consequence loss of each floor classification set according to the Bayesian network combined with the fuzzy theory;

[0011] Obtain the risk level of each floor classification set according to the risk probability and consequence loss.

[0012] Preferably, the risk probability includes:

[0013] Obtain the risk probability of all second-level electrical risk indicators of a single floor classification set according to the Bayesian network combined with the triangular fuzzy number evaluation; compare all second-level electrical risk indicators of a single floor classification set pairwise to obtain a relative judgment matrix, and obtain the weights of all second-level electrical risk indicators of a single floor classification set according to the relative judgment matrix; obtain the risk probability of the floor classification set according to the weights of all second-level electrical risk indicators of a single floor classification set;

[0014] Calculate the risk probability for each floor classification set respectively, and the risk probability of each floor classification set can be obtained.

[0015] Preferably, obtaining the risk probability of all second-level electrical risk indicators of a single floor classification set according to the Bayesian network combined with the triangular fuzzy number evaluation includes:

[0016] Select a preset number of experts to conduct triangular fuzzy number evaluation on all second-level electrical risk indicators of a single floor classification set according to the floor classification set and the corresponding second-level electrical risk indicators, and obtain the evaluation opinion A of the experts k =(a k , b k , c k );

[0017] Calculate the average fuzzy number A v =(a v , b v , c v ) of all experts' opinions;

[0018] Calculate the distance measure between the average fuzzy number A v of the opinions and the evaluation opinion A k to obtain the similarity between the average expert evaluation opinion and each expert's evaluation opinion:

[0019]

[0020] Among them, d(A k , A v ) represents the distance measure, and s(A k , A v ) represents the similarity between the average evaluation opinion of experts and the evaluation opinion of each expert; m represents the total number of experts;

[0021] Defuzzify the evaluation opinions of experts:

[0022]

[0023] Among them, is the defuzzified evaluation opinion, and a k , b k and c k are the triangular fuzzy numbers of the evaluation opinions;

[0024] Obtain the weights of each expert through the similarity, and then obtain the risk probabilities of all secondary electrical risk indicators of a single - floor classification set:

[0025]

[0026] Among them, w k represents the weight of the k - th expert; A represents the risk probability of the secondary electrical risk indicator.

[0027] Preferably, compare all secondary electrical risk indicators of a single - floor classification set pairwise to obtain a relative judgment matrix, and the weights of all secondary electrical risk indicators of a single - floor classification set obtained from the relative judgment matrix include:

[0028] Compare all secondary electrical risk indicators of a single - floor classification set pairwise to obtain a relative judgment matrix; convert the relative judgment matrix into a triangular fuzzy measure matrix to obtain the first matrix;

[0029] Assume that the element of the first matrix corresponding to the secondary electrical risk indicators X i and X j is u ij =(l ij , m ij , h ij ), then the sum f ij of the triangular fuzzy numbers in the row where u i is located includes:

[0030]

[0031] Among them, n represents the total number of secondary electrical risk indicators in the floor classification set; i and j represent the index numbers;

[0032] Then the relative weight fuzzy number w of the secondary electrical risk indicators i includes:

[0033]

[0034] Dedefuzzify w i to obtain the weights of the secondary electrical risk indicators.

[0035] Preferably, the risk probability of the floor classification set obtained by classifying and aggregating the weights of all secondary electrical risk indicators according to a single floor includes:

[0036] Calculate the risk probability P(E) of the floor classification set through the Bayesian total probability formula:

[0037]

[0038] where P(E|X i ) represents the weight of X i ; P(X i ) represents the risk probability of X i .

[0039] Preferably, the consequence losses include:

[0040] Since the electrical risk focuses of each floor classification set are different and the degrees of consequence losses of accidents vary, a hierarchical influence factor is introduced, and the magnitudes of the hierarchical influence factors of each floor classification set are preset separately;

[0041] Then the consequence loss L of the floor classification set can be expressed as:

[0042]

[0043] where Q represents the hierarchical influence factor, and Y i is the accident loss of the i-th primary electrical risk indicator of the floor classification set; e represents the total number of primary electrical risk indicators;

[0044] The accident loss Y i includes the costs caused by electrical accidents to casualties, including:

[0045] Y i = E × S × W i

[0046] where E represents the personnel exposure rate; S represents the severity value of the accident consequences, in yuan; W i represents the weight of the i-th primary electrical risk indicator, and the calculation method of W i is the same as the calculation method of the weights of the secondary electrical risk indicators.

[0047] Preferably, obtaining the risk levels of each floor classification set according to the risk probability and consequence loss includes:

[0048] Presetting level divisions for the risk probability and consequence loss according to their values, and making a risk level matrix with the risk probability and consequence loss as two dimensions. The combination of the risk probability of each level and the consequence loss of each level is preset with a risk level;

[0049] The risk levels of each floor classification set can be obtained by combining the risk probability and consequence loss of each floor classification set with the risk level matrix.

[0050] The present invention also provides a hierarchical electrical safety risk assessment system for high-rise buildings based on a fuzzy Bayesian network, which is used for the method of the present invention. The system includes a first module, a second module, a third module, a fourth module, and a fifth module;

[0051] The first module is used to classify each floor of the high-rise building according to the floor function information to obtain a preset number of floor classification sets; the floor function information includes the function information considering the height where the floor is located;

[0052] The second module is used to respectively select a preset number of first-level electrical risk indicators according to the functions corresponding to each floor classification set, and select a preset number of second-level electrical risk indicators subordinate to the first-level electrical risk indicators according to the first-level electrical risk indicators;

[0053] The third module is used to construct a Bayesian network with the risk probability of each floor classification set as the leaf node, the first-level electrical risk indicator as the intermediate node, and the second-level electrical risk indicator as the root node;

[0054] The fourth module is used to obtain the risk probability and consequence loss of each floor classification set according to the Bayesian network combined with the fuzzy theory;

[0055] The fifth module is used to obtain the risk levels of each floor classification set according to the risk probability and consequence loss.

[0056] The present invention has the following beneficial effects:

[0057] The hierarchical electrical safety risk assessment method for high-rise buildings based on a fuzzy Bayesian network of the present invention classifies each floor of the high-rise building according to the function information considering the height where the floor is located, and selects targeted indicators for the classification results, so that this method can more accurately assess the risks of various categories; a Bayesian network is constructed based on the floor classification results and the selected indicators, and the risk probability and consequence loss of each floor classification set are obtained by combining the fuzzy theory. Furthermore, the risk levels of each floor classification set are obtained according to the risk probability and consequence loss, reducing the fuzziness and subjectivity of the assessment method and providing a comprehensive and accurate data basis for targeted prevention and control strategies.

[0058] The hierarchical electrical safety risk assessment system for high-rise buildings based on the fuzzy Bayesian network of the present invention, which is used for the method of the present invention, has the same beneficial effects as the method of the present invention.

[0059] In addition to the purposes, features and advantages described above, the present invention has other purposes, features and advantages. The present invention will be further described in detail below with reference to the accompanying drawings. Description of the Drawings

[0060] The accompanying drawings constituting a part of the present invention are used to provide a further understanding of the present invention. The schematic embodiments of the present invention and the descriptions thereof are used to explain the present invention and do not constitute an improper limitation to the present invention. In the drawings:

[0061] Figure 1 It is a schematic flow chart of a preferred embodiment of the present invention. Detailed Embodiments

[0062] The embodiments of the present invention will be described in detail below with reference to the accompanying drawings. However, the present invention can be implemented in many different ways defined and covered by the claims.

[0063] Referring to Figure 1 , in a preferred embodiment of the present invention, a hierarchical electrical safety risk assessment method for high-rise buildings based on the fuzzy Bayesian network is provided, including:

[0064] S1. Determine the floor function information of each floor in the high-rise building; classify the floors of the high-rise building according to functions based on the floor function information to obtain a preset number of floor classification sets; the floor function information includes the function information considering the height where the floor is located.

[0065] In a preferred embodiment of the present invention, the floors of a certain high-rise building are classified according to functions to obtain 5 floor classification sets, which are the basement, low floors (shops), mid-high floors (residential and office areas), refuge floors and top floors respectively.

[0066] S2. Select a preset number of first-level electrical risk indicators respectively according to the functions corresponding to each floor classification set, and select a preset number of second-level electrical risk indicators subordinate to the first-level electrical risk indicators according to the first-level electrical risk indicators.

[0067] In a preferred embodiment of the present invention, the selected first-level electrical risk indicators and second-level electrical risk indicators are shown in Table 1.

[0068] Table 1 Electrical Risk Indicator Table

[0069]

[0070]

[0071] S3. Take the risk probabilities of the classified sets of each floor as leaf nodes, the primary electrical risk indicators as intermediate nodes, and the secondary electrical risk indicators as root nodes to construct a Bayesian network.

[0072] S4. Based on the Bayesian network and combined with the fuzzy theory, obtain the risk probabilities and consequence losses of the classified sets of each floor.

[0073] In the preferred embodiment of the present invention, the risk probabilities include:

[0074] Obtain the risk probabilities of all secondary electrical risk indicators of a single floor classified set according to the Bayesian network combined with the triangular fuzzy number evaluation; compare all secondary electrical risk indicators of a single floor classified set pairwise to obtain a relative judgment matrix, and obtain the weights of all secondary electrical risk indicators of a single floor classified set according to the relative judgment matrix; obtain the risk probability of the floor classified set according to the weights of all secondary electrical risk indicators of a single floor classified set;

[0075] Calculate the risk probabilities for each floor classified set respectively, and the risk probabilities of each floor classified set can be obtained.

[0076] In the preferred embodiment of the present invention, obtaining the risk probabilities of all secondary electrical risk indicators of a single floor classified set according to the Bayesian network combined with the triangular fuzzy number evaluation includes:

[0077] Select a preset number of experts to conduct triangular fuzzy number evaluation on all secondary electrical risk indicators of a single floor classified set according to the floor classified set and the corresponding secondary electrical risk indicators to obtain the evaluation opinions A k =(a k ,b k ,c k );

[0078] See Table 2 for the triangular fuzzy number evaluation form.

[0079] Table 2 Triangular fuzzy numbers corresponding to probability evaluation

[0080]

[0081] Calculate the average fuzzy number A v =(a v ,b v ,c v ) of all experts' opinions;

[0082] Calculate the distance measure between the average fuzzy number A v and the evaluation opinion A k to further obtain the similarity between the average expert evaluation opinion and each expert's evaluation opinion:

[0083]

[0084] Among them, d(A k , A v ) represents the distance measure, and s(A k , A v ) represents the similarity between the average evaluation opinion of experts and the evaluation opinion of each expert; m represents the total number of experts;

[0085] Perform defuzzification processing on the evaluation opinions of experts:

[0086]

[0087] Among them, is the evaluation opinion after defuzzification, and a k , b k , and c k are the triangular fuzzy numbers of the evaluation opinion;

[0088] Obtain the weights of each expert through the similarity, and then obtain the risk probabilities of all secondary electrical risk indicators of a single floor classification set:

[0089]

[0090] Among them, w k represents the weight of the k-th expert; A represents the risk probability of the secondary electrical risk indicator.

[0091] In the preferred embodiment of the present invention, all secondary electrical risk indicators of a single floor classification set are compared pairwise to obtain a relative judgment matrix, and the weights of all secondary electrical risk indicators of a single floor classification set obtained according to the relative judgment matrix include:

[0092] Compare all secondary electrical risk indicators of a single floor classification set pairwise to obtain a relative judgment matrix; convert the relative judgment matrix into a triangular fuzzy measure matrix to obtain the first matrix;

[0093] Assume that the element of the first matrix corresponding to the secondary electrical risk indicators X i and X j is u ij =(l ij , m ij , h ij ), then the sum f i of the triangular fuzzy numbers in the row where u ij is located includes:

[0094]

[0095] Among them, n represents the total number of secondary electrical risk indicators of the floor classification set; i and j represent the index numbers;

[0096] Then the relative weight fuzzy number w of the secondary electrical risk indicators i includes:

[0097]

[0098] Perform defuzzification on w i to obtain the weights of the secondary electrical risk indicators.

[0099] In the preferred embodiment of the present invention, the calculation results of the secondary electrical risk indicators are shown in Table 3:

[0100] Table 3 Risk probabilities and weights of secondary electrical risk indicators

[0101]

[0102] In the preferred embodiment of the present invention, the risk probabilities of the floor classification sets obtained by classifying all the weights of the secondary electrical risk indicators according to individual floors include:

[0103] Calculate the risk probability P(E) of the floor classification set through the Bayesian total probability formula:

[0104]

[0105] where P(E|X i ) represents the weight of X i ; P(X i ) represents the risk probability of X i .

[0106] In the preferred embodiment of the present invention, the method for calculating the weights of the primary electrical risk indicators is the same as that of the secondary electrical risk indicators. The calculation results of the primary electrical risk indicators are shown in Table 4:

[0107] Table 4 Risk probabilities and weights of primary electrical risk indicators

[0108]

[0109] In the preferred embodiment of the present invention, the consequence losses include:

[0110] Since the electrical risks of each floor classification set have different emphases and there are differences in the degree of consequence losses of accidents, a hierarchical influence factor is introduced, and the sizes of the hierarchical influence factors of each floor classification set are preset separately.

[0111] In the preferred embodiment of the present invention, the hierarchical influence factors are shown in Table 5.

[0112] Table 5 Hierarchical influence factors

[0113]

[0114] Then the consequence loss L of the floor classification set can be expressed as:

[0115]

[0116] Among them, Q represents the hierarchical influence factor, and Y i is the accident loss of the i-th primary electrical risk index of the floor classification set; e represents the total number of primary electrical risk indexes;

[0117] The accident loss Y i includes the costs caused by electrical accidents to casualties, including:

[0118] Y i = E × S × W i

[0119] Among them, E represents the personnel exposure rate; S represents the severity value of the accident consequences, in yuan; W i represents the weight of the i-th primary electrical risk index, and W i is calculated in the same way as the weight calculation method of the secondary electrical risk index.

[0120] In the preferred embodiment of the present invention, for the specific descriptions of the personnel exposure rate and the severity value of the accident consequences, refer to Table 6.

[0121] Table 6 Accident Loss Level Descriptions

[0122]

[0123]

[0124] In the preferred embodiment of the present invention, for the accident loss Y i refer to Table 7:

[0125] Table 7 Accident Loss Table of Primary Electrical Risk Indexes

[0126]

[0127] S5. Obtain the risk levels of each floor classification set according to the risk probability and the consequence loss. S5 specifically includes:

[0128] Refer to Table 5, make a preset level division for the risk probability and the consequence loss according to the values, and make a risk level matrix with the risk probability and the consequence loss as two dimensions. The risk level matrix is shown in Table 6, and the combination of the risk probability of each level and the consequence loss of each level is preset with a risk level;

[0129] According to the risk probability and the consequence loss of each floor classification set and in combination with the risk level matrix, the risk levels of each floor classification set can be obtained and used as a reference for professionals to formulate corresponding countermeasures.

[0130] Table 8 Risk Probability and Consequence Loss Level Classification Table

[0131]

[0132] Table 9 Risk Level Matrix

[0133]

[0134] In the preferred embodiment of the present invention, the calculated values of the risk probability and consequence loss of each floor classification set are shown in Table 10; the risk levels of each floor classification set are shown in Table 11:

[0135] Table 10 Risk Probability and Consequence Loss of Floor Classification Set

[0136]

[0137] Table 11 Risk Level Results of Each Floor Classification Set

[0138]

[0139] From the risk classification results, it can be seen that the basement, low floors, and mid-high floors of this high-rise building are at medium risk levels, and the refuge floor and the top floor are at low risk, which is roughly consistent with the actual situation. Since there are power distribution rooms, high-voltage rooms, etc. in the basement, which contain key electrical facilities such as transformers and various load power supplies, a power outage of the whole building may occur in case of a failure. The low floors and mid-high floors are mainly commercial shops, office areas, and residential houses, where people are active frequently and the electrical load is large, making it extremely easy to have risks such as short circuits and overloads, which may cause fires. A large number of electrical fire cases are also often located in this area. The risks of the refuge floor and the top floor are relatively low. The design of the refuge floor usually meets high-standard fire prevention requirements, and there is no personnel activity during normal times. Since the top floor is open-air and has good ventilation, electrical fires can be detected in time, and the "chimney effect" of the fire is difficult to affect the residents because the top floor is the highest part of the building. However, due to the influence of rainy days, electrical lines are prone to corrosion and aging, and are also vulnerable to lightning strikes, so close attention is needed.

[0140] In summary, according to the characteristics and risk levels of different floors of this high-rise building, targeted measures can be taken to enhance the overall electrical safety level. The inspection density should be increased in the basement and the top floor to reduce potential safety hazards, and monitoring devices should be deployed in key areas to give early warnings of abnormal electrical line parameters. The low floors and mid-high floors should maintain regular management, but the fire prevention and electrical safety awareness of personnel need to be strengthened. The refuge floor needs to regularly check the status of fire-fighting facilities, standby power supplies, and emergency lighting systems to ensure normal operation.

[0141] The hierarchical electrical safety risk assessment method for high-rise buildings based on fuzzy Bayesian network of the present invention classifies each floor of a high-rise building according to function considering the functional information of the floor height, and selects targeted indicators for the classification results, enabling the method to more accurately evaluate the risks of various categories; a Bayesian network is constructed based on the floor classification results and the selected indicators, and the risk probability and consequence loss of each floor classification set are obtained by combining fuzzy theory. Furthermore, the risk level of each floor classification set is obtained based on the risk probability and consequence loss, reducing the fuzziness and subjectivity of the assessment method and providing a comprehensive and accurate data basis for targeted prevention and control strategies.

[0142] In a preferred embodiment of the present invention, there is also provided a hierarchical electrical safety risk assessment system for high-rise buildings based on fuzzy Bayesian network for the method of the present invention. The system includes a first module, a second module, a third module, a fourth module, and a fifth module;

[0143] The first module is used to classify each floor of a high-rise building according to function based on the floor functional information to obtain a preset number of floor classification sets; the floor functional information includes the functional information considering the floor height.

[0144] The second module is used to respectively select a preset number of primary electrical risk indicators according to the functions corresponding to each floor classification set, and select a preset number of secondary electrical risk indicators subordinate to the primary electrical risk indicators according to the primary electrical risk indicators.

[0145] The third module is used to construct a Bayesian network with the risk probability of each floor classification set as the leaf node, the primary electrical risk indicator as the intermediate node, and the secondary electrical risk indicator as the root node.

[0146] The fourth module is used to obtain the risk probability and consequence loss of each floor classification set according to the Bayesian network combined with fuzzy theory.

[0147] The fifth module is used to obtain the risk level of each floor classification set according to the risk probability and consequence loss.

[0148] The hierarchical electrical safety risk assessment system for high-rise buildings based on fuzzy Bayesian network of the present invention, for the method of the present invention, has the same beneficial effects as the method of the present invention.

[0149] The above are only preferred embodiments of the present invention and are not used to limit the present invention. For those skilled in the art, the present invention can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A hierarchical electrical safety risk assessment method for high-rise buildings based on a fuzzy Bayesian network, characterized in that, Including: Determine the floor function information of each floor in the high-rise building; Classify each floor of the high-rise building according to the floor function information to obtain a preset number of floor classification sets; the floor function information includes the function information considering the height where the floor is located; Select a preset number of first-level electrical risk indicators according to the functions corresponding to each floor classification set, and select a preset number of second-level electrical risk indicators subordinate to the first-level electrical risk indicators according to the first-level electrical risk indicators; Construct a Bayesian network with the risk probability of each floor classification set as the leaf node, the first-level electrical risk indicator as the intermediate node, and the second-level electrical risk indicator as the root node; Obtain the risk probability and consequence loss of each floor classification set according to the Bayesian network combined with the fuzzy theory; Obtain the risk level of each floor classification set according to the risk probability and consequence loss.

2. The method for hierarchical electrical safety risk assessment of high-rise buildings based on the fuzzy Bayesian network according to claim 1, wherein The risk probability includes: Obtain the risk probability of all second-level electrical risk indicators of a single floor classification set according to the Bayesian network combined with the triangular fuzzy number evaluation; compare all second-level electrical risk indicators of a single floor classification set pairwise to obtain a relative judgment matrix, and obtain the weights of all second-level electrical risk indicators of a single floor classification set according to the relative judgment matrix; obtain the risk probability of the floor classification set according to the weights of all second-level electrical risk indicators of the single floor classification set; Calculate the risk probability for each floor classification set respectively, and the risk probability of each floor classification set can be obtained.

3. The hierarchical electrical safety risk assessment method for high-rise buildings based on the fuzzy Bayesian network according to claim 2, characterized in that Obtaining the risk probability of all second-level electrical risk indicators of a single floor classification set according to the Bayesian network combined with the triangular fuzzy number evaluation includes: Select a preset number of experts to conduct a triangular fuzzy number evaluation on all secondary electrical risk indicators of a single floor classification set according to the floor classification set and the corresponding secondary electrical risk indicators, and obtain the evaluation opinions A of the experts k =(a k ,b k ,c k ); Calculate the average value A of the opinion fuzzy numbers of all experts v =(a v , b v , c v ); Calculate the average value A of the fuzzy numbers of the opinions v and the evaluation opinion A k of the distance measure, and then obtain the similarity between the average evaluation opinion of the experts and the evaluation opinions of each expert: Among them, d(A k , A v ) represents the distance measure, and s(A k , A v ) represents the similarity between the average evaluation opinion of experts and the evaluation opinions of each expert; m represents the total number of experts; Defuzzify the evaluation opinions of experts: Among them, is the evaluation opinion after deblurring, a k , b k and c k are the triangular fuzzy values of the evaluation opinion; Obtain the weights of each expert through similarity, and then obtain the risk probability of all second-level electrical risk indicators of a single floor classification set: Among them, w k represents the weight of the k-th expert; A represents the risk probability of the secondary electrical risk index.

4. The method for hierarchical electrical safety risk assessment of high-rise buildings based on the fuzzy Bayesian network according to claim 3, characterized in that, Comparing all second-level electrical risk indicators of a single floor classification set pairwise to obtain a relative judgment matrix, and obtaining the weights of all second-level electrical risk indicators of a single floor classification set according to the relative judgment matrix includes: Compare all second-level electrical risk indicators of a single floor classification set pairwise to obtain a relative judgment matrix; convert the relative judgment matrix into a triangular fuzzy measure matrix to obtain a first matrix; Suppose the secondary electrical risk index is X i and X j The corresponding first matrix element between them is u ij =(l ij , m ij , h ij ), then the sum f ij of the triangular fuzzy numbers in the row where u i is located includes: Where n represents the total number of second-level electrical risk indicators of the floor classification set; i and j represent the index numbers; Then the relative weight fuzzy number \(w\) of the secondary electrical risk index i includes: Perform defuzzification on w i to obtain the weight of the secondary electrical risk indicator.

5. The method for hierarchical electrical safety risk assessment of high-rise buildings based on a fuzzy Bayesian network according to claim 4, characterized in that, Obtaining the risk probability of the floor classification set according to the weights of all second-level electrical risk indicators of the single floor classification set includes: Calculate the risk probability P(E) of the floor classification set through the Bayesian total probability formula: Among them, P(E|X i ) represents the weight of X i ; P(X i ) represents the risk probability of X i .

6. The hierarchical electrical safety risk assessment method for high-rise buildings based on the fuzzy Bayesian network according to claim 5, wherein The consequence loss includes: Since the electrical risks of each floor classification set have different emphases and the degree of consequence loss of accidents varies, a hierarchical influence factor is introduced, and the size of the hierarchical influence factor of each floor classification set is preset separately; Then the consequence loss L of the floor classification set can be expressed as: Among them, Q represents the hierarchical influence factor, and Y i is the accident loss of the i-th primary electrical risk indicator in the floor classification set; e represents the total number of primary electrical risk indicators; Accident loss Y i Including the costs caused by electrical accidents to casualties, including: Y i = E × S × W i Among them, E represents the personnel exposure rate; S represents the severity value of the accident consequence, with the unit of yuan; W i represents the weight of the i-th primary electrical risk index, and W i is calculated in the same way as the weight calculation method of the secondary electrical risk index.

7. The hierarchical electrical safety risk assessment method for high-rise buildings based on the fuzzy Bayesian network according to claim 6, characterized in that Obtaining the risk level of each floor classification set according to the risk probability and consequence loss includes: The risk probability and the consequential loss are divided into preset levels according to their values, and a risk level matrix is created with the risk probability and the consequential loss as two dimensions. Each level of risk probability and each level of consequential loss is given a preset risk level; The risk level of each floor classification set can be obtained by combining the risk probability and consequence loss of each floor classification set with the risk level matrix.

8. A hierarchical electrical safety risk assessment system for high-rise buildings based on a fuzzy Bayesian network, for use in the method according to any one of claims 1 to 7, characterized in that, The system includes a first module, a second module, a third module, a fourth module and a fifth module; The first module is used to classify the floors of the high-rise building according to their functions based on the floor function information to obtain a preset number of floor classification sets; the floor function information includes functional information considering the height of the floor; The second module is used to select a preset number of first-level electrical risk indicators according to the functions corresponding to the classification sets of each floor, and select a preset number of second-level electrical risk indicators subordinate to the first-level electrical risk indicators according to the first-level electrical risk indicators; The third module is used to construct a Bayesian network by taking the risk probability of each floor classification set as a leaf node, the first-level electrical risk index as an intermediate node, and the second-level electrical risk index as a root node; The fourth module is used to obtain the risk probability and consequential loss of each floor classification set based on the Bayesian network combined with fuzzy theory; The fifth module is used to obtain the risk level of each floor classification set according to the risk probability and consequence loss.

Images