Fire risk assessment and personnel evacuation prediction method and device, and storage medium

Abstract

The invention provides a fire risk assessment and personnel evacuation prediction method and device and a storage medium, and belongs to the field of fire risk prediction.The method comprises the steps that firstly, a fire risk assessment model is established, and then an evacuation simulation model is established; key parameters in the evacuation simulation process are determined in the three aspects of the number of evacuated persons, the attributes of the evacuated persons and evacuation time setting, and therefore fire evacuation risk assessment and prediction are carried out. According to the method, a multistage extension evaluation method is applied to carry out fire risk assessment, and Pathfinder evacuation simulation software is adopted to establish a personnel evacuation model. And meanwhile, the CRITIC weighting method is improved, so that the fire evacuation risk assessment is more scientific and accurate. The fire emergency response efficiency can be effectively improved, and the harm of the fire to the life and property of people is reduced.

Description

Technical Field

[0001] The present invention belongs to the field of fire risk prediction, and more specifically relates to a fire risk assessment and personnel evacuation prediction method, device, and storage medium. Background Art

[0002] In modern society, with the acceleration of industrialization and urbanization, there are more and more high-rise buildings and large public places, and the risk of fire is gradually increasing. The occurrence of fire incidents poses a serious threat to the safety of life and property. How to effectively assess fire risks and make reasonable evacuation predictions has become an important research topic. Traditional fire risk assessment and evacuation prediction methods are often based on experience or intuitive judgment, lacking scientificity and objectivity, and cannot accurately predict the process and results of personnel evacuation, which can easily lead to confusion in the evacuation process and further amplify the damage of fire incidents.

[0003] At present, although there are some fire risk assessment and evacuation prediction methods based on mathematical models, these methods have more or less problems such as complex models, cumbersome calculation steps, and difficult operation. They are inconvenient to use and have poor adaptability to some specific scenarios. They are unable to accurately and comprehensively assess fire risks and predict evacuation.

[0004] The life safety and health of employees is undoubtedly one of the most important factors in the workplace. Personnel evacuation prediction is particularly important for fire risk assessment. It can not only enhance employees' awareness of fire safety, but also help employees understand the fire evacuation routes and directions, and can evacuate quickly and orderly in an emergency, greatly reducing the possibility of fire causing harm to people.

[0005] Therefore, how to construct a model that can scientifically and accurately assess fire risks and make effective evacuation predictions, and how to use this model to quantitatively assess fire risks and make evacuation predictions, has become an important research topic in the field of fire protection. Summary of the invention

[0006] The technical problem to be solved by the present invention is how to construct a scientific, accurate and efficient fire risk assessment model and personnel evacuation prediction model to achieve quantitative assessment of fire risks and accurate prediction of personnel evacuation, solve the problems of inconvenience in use and poor prediction effect caused by complex models and difficult operations in the prior art, and at the same time improve the efficiency of fire emergency response and reduce the harm of fire to human life and property.

[0007] In order to achieve the above object, the present invention adopts the following technical solution: the method comprises: Establish a fire risk assessment model to evaluate fire risks; Construct an evacuation simulation model and determine the key parameters in the evacuation simulation process from three aspects: the number of evacuees, the attributes of the evacuees, and the evacuation time setting; Fire evacuation risk assessment; Fire evacuation risk calculation, predicting fire evacuation risk.

[0008] In one embodiment, the fire risk assessment model adopts a multi-level extension assessment method, including: Identify classical and nodal domains; Determine the matter-element to be evaluated; Calculate the correlation; Multi-level extension evaluation.

[0009] In one embodiment, the multi-level extension evaluation includes: (1) Level 1 evaluation; (2) Level 2 evaluation; (3) Determine the risk level.

[0010] In one embodiment, the evacuation simulation model is constructed by using Pathfinder evacuation simulation software to establish a personnel evacuation model; the key parameters of the evacuation simulation model include: The number of people to be evacuated, the use functions, building areas, and personnel composition of different types of buildings, and the number of people to be evacuated are calculated according to the design specifications to be close to the actual situation; Attributes of evacuees: Attributes of evacuees of different ages vary significantly, which will affect the evacuation results. Key parameters of evacuee attributes include height and shoulder width, personnel composition, and evacuation speed. Evacuation time setting: The evacuation time of personnel is mainly composed of fire detection time, pre-action time and evacuation movement time, among which the evacuation time includes the fire detection time and pre-action time.

[0011] In one solution, the fire evacuation risk assessment adopts an improved CRITIC weighting method to assess the fire evacuation risk, and the improved CRITIC weighting method calculates the indicator weights.

[0012] In one embodiment, the steps of improving the CRITIC weighting method are as follows: Data processing: after data processing, the indicators have unified directions and dimensions, which are used to calculate weights and assess risks; Calculate the indicator contrast intensity, conflict and introduce activation entropy; Determine the indicator weights.

[0013] In one embodiment, the fire evacuation risk calculation uses the weight calculation results based on the improved CRITIC weighting method and the data preprocessing results to calculate the risk level of the fire evacuation scenario in a weighted manner.

[0014] On the other hand, an electronic device includes a processor and a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the fire risk assessment and personnel evacuation prediction method is implemented.

[0015] On the other hand, a computer storage medium stores a computer program thereon, and when the computer program is executed by a processor, the fire risk assessment and personnel evacuation prediction method is implemented.

[0016] Beneficial effects of the present invention: 1. The present invention proposes a new method for fire risk assessment and personnel evacuation prediction, which adopts a scientific and accurate model, can quantitatively assess fire risks, accurately predict personnel evacuation, and improve the efficiency of fire prevention and control.

[0017] 2. By constructing an evacuation simulation model, the number, characteristics and evacuation time of personnel are taken into consideration, making the simulation process more realistic and the prediction results more credible.

[0018] 3. The improved CRITIC weighting method is used for fire evacuation risk assessment, which can effectively overcome the shortcomings of traditional methods in dealing with complex systems, such as the difficulty in weight calculation and strong subjectivity. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 is a flow chart of the method of the present invention; Figure 2 Establish a fire risk assessment model flow chart for the present invention; Figure 3 The following are steps for improving the CRITIC weighting method of the present invention. DETAILED DESCRIPTION

[0020] In order to facilitate understanding of the present invention, the present invention will be described more fully below with reference to the relevant drawings. Typical embodiments of the present invention are provided in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described in the present invention. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive.

[0021] Unless otherwise defined, all technical and scientific terms used in the present invention have the same meanings as those understood by those skilled in the art of the present invention. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0022] like Figure 1 As shown, the fire risk assessment and personnel evacuation prediction method comprises: S1. Establish a fire risk assessment model to evaluate fire risks.

[0023] like Figure 2 As shown in the figure, the fire risk assessment model adopts a multi-level extension evaluation method. The core idea of ​​extension evaluation is the matter-element theory. The matter-element is defined as When analyzing a system, N refers to the system security level, C refers to the subsystem, and V refers to the value range of the subsystem security state. The basic theory of multi-level extension evaluation is set theory, which mainly includes classical domain, section domain, correlation degree and correlation function. The calculation steps of the multi-level extension evaluation method are as follows: including: S101, determine the classical domain and the nodal domain; (1); In the formula, It is a classic domain. is the evaluation index set, Is the evaluation index set C about risk level The value range of Parameters or variables related to the j-th level evaluation indicator.

[0024] make: (2); In the formula, is the section domain, is the evaluation index set Regarding the value range of risk level U, Parameters or variables associated with risk level u.

[0025] S102, determining the matter-element to be evaluated; The actual data results of the object to be evaluated are expressed by matter-element Ri: (3); In the formula, is the object to be evaluated, N is the level of influencing factors, For N About The value of , where p is the number of secondary evaluation indicators.

[0026] S103, calculating the correlation degree; For the i-th first-level evaluation index, the correlation between the k second-level indicators and the risk level Uj is: (4); (5); The measured value of the kth secondary indicator under the i-th primary indicator, The classic domain interval corresponding to risk level j is defined as , The section interval (the range of all possible values) is defined as , The lower and upper limits of the section domain for the ith indicator; Measured value To the classical domain The distance (degree of deviation); Measured value To the classical domain The distance (degree of deviation).

[0027] S104, multi-level extension evaluation. Before conducting each level evaluation, other evaluation methods such as fuzzy hierarchical analysis method should be used to obtain the weights of each secondary indicator and the weights of the primary indicator, and form the weight vector of the secondary indicator. and the first-level indicator weight vector .

[0028] The multi-level extension evaluation includes: (1) First-level evaluation: The weight vector of the secondary index Multiply the correlation matrix of each security level of the secondary indicator , calculate the correlation matrix of each first-level indicator for the security level: (6);

[0029] The i-th first-level evaluation index; The weight vector of each secondary indicator under the i-th primary indicator (determined by fuzzy analytic hierarchy process, etc.); p is the total number of secondary indicators (the number of secondary indicators under each primary indicator); m is the total number of safety levels (such as high risk, medium risk, low risk, etc.).

[0030] (2) Secondary evaluation: The weight vector of the first-level index Multiply by the correlation of the first-level indicator for each security level , calculate the correlation matrix of the overall target safety level: (7); The correlation matrix of the overall target safety level (the final correlation after integrating all first-level indicators); The weight vector of the first-level indicators (determined by fuzzy analytic hierarchy process, etc.); n The total number of safety levels is the same as m in formula 6.

[0031] (3) Determine the risk level: If satisfied: , then the object to be evaluated belongs to level j: (8); (9); Total correlation Normalized value of (map the correlation degree to the interval 0,1); The original correlation of the total target to the safety level j (calculated from formula 7); The maximum correlation value among all security levels; The minimum correlation value among all security levels. The final safety level (comprehensive level calculated by weighted average); j Safety level number (e.g. j=1 for low risk, j=2 for medium risk, etc.); The relevance of the total goal to security level j (from Formula 7), and m is the total number of security levels.

[0032] S2. Construct an evacuation simulation model and determine the key parameters in the evacuation simulation process from three aspects: the number of evacuees, the attributes of evacuees, and the evacuation time setting.

[0033] The evacuation simulation model described herein is constructed by using Pathfinder evacuation simulation software to establish a personnel evacuation model; since Pathfinder supports model files in multiple formats such as DXF, IFC, PSM, etc., the physical model in PyroSim can be directly exported as a file in ".psm" format, or the Revit model can be saved as an interactive file in IFC format, loaded into the Pathfinder software, and the measurement unit of the model size can be set, the angle deviation can be automatically corrected, the model reference point can be set, and a three-dimensional evacuation physical model can be established.

[0034] The values ​​of the key parameters of evacuation simulation directly affect the accuracy of evacuation simulation results. Therefore, the values ​​of the evacuation simulation parameters of commercial complexes should be analyzed in combination with existing domestic and foreign research results and relevant specifications. The key parameters of the evacuation simulation model include: When determining the number of evacuees, various factors such as the use function, building area, and personnel composition of different types of buildings should be considered. According to the specifications or relevant survey and research results, the number of personnel that is as close to the actual situation as possible should be calculated. At present, the number of evacuees in commercial complexes is mostly calculated based on the "Building Design Fire Protection Code" and is determined by formula (10). First, determine the population density of each floor in the building, then the area ratio, calculate the area of ​​each floor, and finally calculate the number of evacuees by multiplying the population density and area of ​​each floor; (10); Where: is the total number of evacuees from the commercial complex, persons; is the number of people evacuated from the i-th layer, people; is the building area of ​​the i-th floor of the commercial complex; a is the ratio of the business hall area to the building area in the commercial complex. The "Code for Fire Protection Design of Buildings" stipulates that the ratio of the business hall area to the building area of ​​a store is (0.5~0.7):1; is the personnel density coefficient in the business area of ​​the i-th floor of the commercial complex.

[0035] The attributes of evacuees are significantly different for people of different age groups, which will affect the evacuation results. The key parameters of evacuees’ attributes include height and shoulder width, personnel composition and evacuation speed. This formula takes into account the impact of personnel density and path setting on the evacuation speed. It is suitable for calculating the evacuation speed when the personnel density is less than 23.8 / m and greater than 20.5 / m. When the personnel density is greater than 23.8 / m, the personnel in the commercial complex are very crowded and basically unable to move, resulting in a stagnant state. When the personnel density is less than 20.5 / m, the personnel density is greater than 23.8 / m. At that time, there was basically no congestion in the commercial complex and people could be evacuated normally.

[0036] (11); Where: is the personnel evacuation speed m / s; is the evacuation path coefficient, which is related to the setting of evacuation paths such as corridors and doors. The density of people.

[0037] Evacuation time setting The evacuation time is mainly determined by the fire detection time. , Pre-action time (Including recognition time , reaction time ) and evacuation movement time Composition, where evacuation time includes fire detection time and pre-action time .

[0038] When setting the fire detection time When , it can be considered that it approximately obeys the maximum value of 112.2s and the minimum value of 29.1s.

[0039] In a real fire scene, the personnel pre-action time It often obeys a certain probability distribution, which means that people who are closer to the fire source can quickly discover the fire and take evacuation actions. Short, while people who are far away from the fire source need a certain reaction time and pre-action time my country's performance-based design standards and related research give the probability distribution of pre-action time and its parameters, which are approximately 53.7s for the maximum value and 10s for the minimum value.

[0040] S3. Fire evacuation risk assessment.

[0041] The fire evacuation risk assessment adopts the improved CRITIC weighting method to evaluate the fire evacuation risk, and improves the calculation index weight of the CRITIC weighting method. On the basis of the traditional CRITIC weighting method, the information entropy is introduced into the CRITIC multiplication model, and the exponential state variable weight vector in the variable weight theory is introduced in the final calculation of the weight, which comprehensively reflects the correlation, independence, data chaos and subjective factors of the decision maker of the index.

[0042] Compared with the existing CRITIC weighting method: the existing CRITIC weighting method calculates the indicator weight based on the comparative strength of the indicator and the conflict between the indicators. The comparative strength is the standard deviation of the indicator, which is positively correlated with the weight allocation; the conflict is the correlation between the indicators, expressed by the Pearson coefficient, which is negatively correlated with the weight allocation. The existing CRITIC weighting method can measure the correlation of each indicator in the risk assessment indicator system by conflict, and reflect the information difference between indicators by comparative strength, but it does not consider the degree of data confusion within the same indicator, and there are problems such as incomplete information and imbalance between subjective and objective.

[0043] This application introduces the calculation of indicator comparison intensity, which can better measure the contribution of each indicator to the risk assessment results, thereby optimizing the weight distribution and ensuring the fairness and rationality of the assessment results.

[0044] Considering that the conflict between indicators is also a major factor affecting the accuracy of the evaluation results, the improved CRITIC weighting method uniquely incorporates this factor into the weight calculation, effectively avoiding the evaluation bias caused by indicator conflicts. The simple objective weighting method ignores the subjective will of the decision maker, and the calculated indicator weights may deviate from the actual situation. Therefore, on the basis of objective weighting, the decision maker's emphasis on different indicators should be reflected. At the same time, in order to avoid the complexity of the weight calculation process, the selected subjective weighting method should be easy to operate.

[0045] Introducing the calculation of activation entropy will help reduce the interference of noise on the evaluation results and improve the stability of the evaluation when there is strong diversity and uncertainty and complex data intersection. Generally speaking, if the information entropy of an indicator is smaller, it means that the discreteness of the indicator is greater, the degree of data chaos within the indicator is higher, the information contained is more sufficient, and the weight of the indicator will be greater when weighting; on the contrary, the larger the information entropy, the smaller the discreteness of the indicator, the more concentrated the data, the lower the degree of chaos, and the smaller the weight of the indicator when weighting. Activation entropy can reflect the degree of chaos of the data and better reflect the information differences within the indicator, effectively making up for the problem of incomplete information in the CRITIC weighting method. Therefore, combining the CRITIC weighting method with activation entropy can more reasonably calculate the objective weight of the indicator.

[0046] like Figure 3 As shown, the steps of the improved CRITIC weighting method are as follows: S301. Data processing: To facilitate the calculation of weights and risk assessment, data preprocessing and data expression conversion are required before applying the improved CRITIC weighting method. This includes unifying the indicator direction and dimensionless processing of the data. The noise-reduced data of m scenarios are constructed into a matrix ; (12); matrix The positive and negative indicators in are processed using formula (13) and formula (14) respectively.

[0047] (13); (14); Where: is the normalized result of the jth index under the i-th fire evacuation scenario; is the jth indicator under the i-th fire evacuation scenario; , is the minimum and maximum value of the jth indicator.

[0048] The processed indicators have unified direction and dimension, and can be used to calculate weights and assess risks.

[0049] S302. Calculate the comparison strength of indicators , conflict And introduce activation entropy .

[0050] Reflect the comparative strength of indicators in the form of standard deviation , calculated by formula (15): (15); Where: is the mean value of the jth indicator; is the standard deviation of the jth indicator. The larger the standard deviation of indicator j, the greater the difference in its internal information. The standardized value of the jth indicator in the i-th scenario, at which time the weight distribution of this indicator is appropriately increased.

[0051] The conflict between indicators is calculated by formula (16): (16); Where: is the correlation coefficient between the i-th indicator and the j-th indicator. The larger the correlation coefficient of indicator j, The conflict of the jth indicator; The standardized value of the jth indicator in the kth scenario; the greater the amount of information duplication, the more appropriate it is to reduce the weight of the indicator.

[0052] According to the entropy weight method, the proportion of indicators corresponding to the i-th scenario under the j-th indicator is calculated. : (17); The indicator proportion of the i-th scenario under the j-th indicator; The standardized value of the jth indicator in the i-th scenario; Calculate the information entropy of the jth indicator : (18); Natural logarithm function, used to standardize entropy values; After the data is preprocessed, The situation is defined as In order to prevent the influence of data mutation on indicator weights and consider the relationship between information entropy and weight distribution, activation entropy is introduced : (19); S303: Determine indicator weights.

[0053] By contrast intensity , conflict and discreteness , the multiplication model in the CRITIC weighting method is used to calculate the information content of index j .

[0054] (20); Calculate the initial weight of indicator j : (twenty one); In order to reflect the subjective will of decision makers on the indicator weights, the exponential state variable weight vector in the variable weight theory is introduced to calculate the comprehensive weight of indicator j : (twenty two); The comprehensive weight of the jth indicator (the weight adjusted considering the subjective will of the decision maker); Penalty factor; The original weight of the jth indicator Negative factor, a threshold set by the decision maker to determine whether the weight needs to be adjusted; The final weight after normalization; The adjusted comprehensive weights of all indicators.

[0055] Where: is the penalty factor, which takes values ​​within (0,1); It is a negation factor and its value can be determined according to the actual situation.

[0056] S4. Calculate fire evacuation risk and predict fire evacuation risk.

[0057] The weight calculation results based on the improved CRITIC weighting method and the data preprocessing results are used to weight the The risk level of the fire evacuation scenario is calculated by the formula. The comprehensive risk level of the scenario is determined by the safety index S. The larger the S is, the safer the scenario is and the smaller the corresponding fire evacuation risk is. Its calculation method is shown in formula (23).

[0058] (twenty three); Where: They are , , , , , The comprehensive weight value of the indicator is calculated and determined by the improved CRITIC weighting method; PAe is the evaluation indicator Ae value after data conversion, and the rest are similar.

[0059] After calculating the safety index S of each fire evacuation scenario, the risk size of each scenario can be determined in an intuitive way based on the safety index S, and the risks can be ranked, thereby determining the dangerous scenarios and key indicators that affect the risk level.

[0060] Embodiment 1: First, a fire risk assessment model is established. A multi-level extension evaluation method is used to determine the classic domain as [0,1] and the section domain as [0.3,0.7]. The object elements to be evaluated are various fire sources in the building, with key monitoring equipment and fire use. According to the national fire protection regulations, their correlations are calculated to obtain the risk level of each risk source.

[0061] Secondly, an evacuation simulation model was constructed. The Pathfinder evacuation simulation software was used to build a personnel evacuation model. The number of evacuees was set to about 200 per floor, mainly adults, with a small number of elderly people and children. After simulation calculations, it was found that the evacuation time for all personnel in the building was about 6 minutes.

[0062] Then, the fire evacuation risk assessment was carried out. The improved CRITIC weighting method was used to calculate the index weights, where the weight of the fire source risk was 0.5, the weight of the evacuation channel condition was 0.3, and the weight of the personnel evacuation time was 0.2. After data processing, the index comparison intensity, conflict, and activation entropy were calculated to obtain the weights of each index.

[0063] Finally, the fire evacuation risk is calculated. Using the weight calculation results based on the improved CRITIC weighting method and the data preprocessing results, the risk level of the fire evacuation scenario is calculated in a weighted manner, and the fire risk level of the building is obtained as level 4, indicating that the fire risk is high. We should be vigilant, do a good job in fire prevention, and conduct evacuation drills for employees.

[0064] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM).

[0065] It should be understood that the detailed description of the technical solutions of the present invention by means of the preferred embodiments is illustrative rather than restrictive. A person skilled in the art may modify the technical solutions described in the embodiments, or replace some of the technical features by equivalents, based on reading the specification of the present invention; and 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 embodiments of the present invention.

Claims

1. A method for fire risk assessment and personnel evacuation prediction, characterized in that: The method includes: Establish a fire risk assessment model to evaluate fire risks; Construct an evacuation simulation model and determine the key parameters in the evacuation simulation process from three aspects: the number of evacuees, the attributes of evacuees and the evacuation time; Fire evacuation risk assessment; Fire evacuation risk calculation, predicting fire evacuation risk.

2. A fire risk assessment and personnel evacuation prediction method according to claim 1, characterized in that: The fire risk assessment model adopts a multi-level extension assessment method, including: Identify classical and nodal domains; Determine the matter-element to be evaluated; Calculate the correlation; Multi-level extension evaluation.

3. A method for fire risk assessment and personnel evacuation prediction according to claim 2, characterized in that: The multi-level extension evaluation includes: (1) Level 1 evaluation; (2) Level 2 evaluation; (3) Determine the risk level.

4. A fire risk assessment and personnel evacuation prediction method according to claim 1, characterized in that: The evacuation simulation model described above uses Pathfinder evacuation simulation software to establish a personnel evacuation model; the key parameters of the evacuation simulation model include: The number of people to be evacuated, the use functions, building areas, and personnel composition of different types of buildings, and the number of people to be evacuated are calculated according to the design specifications to be close to the actual situation; Attributes of evacuees: Attributes of evacuees of different ages vary significantly, which will affect the evacuation results. Key parameters of evacuee attributes include height and shoulder width, personnel composition, and evacuation speed. Evacuation time setting: The evacuation time of personnel is mainly composed of fire detection time, pre-action time and evacuation movement time, among which the evacuation time includes the fire detection time and pre-action time.

5. A fire risk assessment and personnel evacuation prediction method according to claim 1, characterized in that: The fire evacuation risk assessment adopts the improved CRITIC weighting method to assess the fire evacuation risk, and the improved CRITIC weighting method calculates the indicator weights.

6. A method for fire risk assessment and personnel evacuation prediction according to claim 5, characterized in that: The steps of improving the CRITIC weighting method are as follows: Data processing: after data processing, the indicators have unified directions and dimensions, which are used to calculate weights and assess risks; Calculate the indicator contrast intensity, conflict and introduce activation entropy; Determine the indicator weights.

7. A method for fire risk assessment and personnel evacuation prediction according to claim 1, characterized in that: The fire evacuation risk calculation uses the weight calculation results based on the improved CRITIC weighting method and the data preprocessing results to calculate the risk level of the fire evacuation scenario in a weighted manner.

8. An electronic device, characterized in that: It comprises a processor and a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, a fire risk assessment and personnel evacuation prediction method according to any one of claims 1 to 7 is implemented.

9. A computer storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, a fire risk assessment and personnel evacuation prediction method as described in any one of claims 1 to 7 is implemented.

Images