Risk perception based exhibition building crowd evacuation simulation method, system, electronic device and medium

Abstract

The application provides a convention and exhibition building crowd evacuation simulation method and system based on risk perception, an electronic device and a medium, and belongs to the technical field of crowd evacuation simulation. First, convention and exhibition building evacuation scene parameters and personnel parameters are acquired, an evacuation scene model is constructed, and personnel is imported into the evacuation model. Then, a risk perception model containing three elements of alarm prompts, danger sources and information transmission is constructed, and the model is coupled with personnel movement. A K-means method is used to divide the personnel to be evacuated in the evacuation scene into a plurality of groups, and an exit is assigned to each group according to the distance. A macroscopic path is planned through an improved artificial bee colony algorithm, and personnel microscopic movement is simulated through a cellular automaton model, so that a personnel evacuation path is obtained. The method can actually reflect the behavior of personnel during evacuation, plan a more reasonable evacuation path, and provide a guidance basis for evacuation under the condition that the convention and exhibition building contains obstacles.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of crowd evacuation simulation, and in particular relates to a risk perception-based crowd evacuation simulation method and system for exhibition buildings, an electronic device, and a medium. BACKGROUND

[0002] With the construction and increasing use of exhibition buildings, due to their large space area and various facility layout, there are problems of long evacuation flow lines and unclear evacuation paths, which bring great challenges to the short-time and rapid gathering and dispersing of large crowds. Especially when an emergency occurs, the safe evacuation of large crowds faces various potential safety risks, and risk perception is the main driving force for emergency evacuation, which is crucial to the safe evacuation of crowds.

[0003] Evacuation simulation is an effective means to study crowd evacuation, and micro-models have attracted the attention of many scholars because they can simulate the interaction between individuals. Gerardo Beni and Jing Wang first proposed the concept of swarm intelligence in 1989 to study group systems composed of a large number of simple individuals. Compared to individual intelligence, the internal design of swarm intelligence is not complex, but based on simple individual rules, they have stronger robustness, stability and adaptability. The application of the widely studied and mature artificial bee colony algorithm in the field of path planning has made continuous progress, providing a new direction for the study of crowd evacuation simulation methods.

[0004] However, the current research on crowd evacuation in complex exhibition building exhibition hall spaces is not deep enough, and no model has considered the role of individual risk perception in the evacuation process. There is still a certain gap in the quantitative study of the influence of risk perception on evacuation. The simulation in this case lacks targeted experiments and guidance. SUMMARY

[0005] In view of the limitations existing in the current crowd evacuation simulation, the present application proposes a risk perception-based crowd evacuation simulation method, system, electronic device and medium for exhibition buildings, which adopts a combination of macro-models and micro-models, introduces risk perception-related elements, and constructs a more accurate model that can reflect the actual evacuation situation, thereby providing suggestions for optimizing evacuation design and improving evacuation efficiency.

[0006] The present application is implemented by the following technical solutions: a risk perception-based crowd evacuation simulation method for exhibition buildings:

[0007] Step one: obtain the evacuation scene parameters and personnel parameters of the exhibition building, construct an evacuation scene model, and import the personnel into the evacuation model;

[0008] Step two: construct a risk perception model containing three elements of alarm prompt, danger source, and information transmission, and couple the model with personnel movement;

[0009] Step three: map the personnel evacuation parameters to the artificial bee colony algorithm, use the K-means method to divide the personnel to be evacuated in the evacuation scene into several groups, and assign an exit to each group according to the distance;

[0010] Step four: use the improved artificial bee colony algorithm to plan the macro evacuation path of the group, and use the cellular automaton model to simulate the movement of personnel;

[0011] Step five: when all the evacuation personnel leave the evacuation scene, determine the end of the evacuation, and export the evacuation path, total evacuation time, and personnel position information at each time step.

[0012] Further, in step one,

[0013] The exhibition building evacuation scene parameters include: exhibition hall size, number of exits, exit width, obstacle layout form, dangerous source setting and emergency broadcasting system setting;

[0014] The personnel parameters include: number of evacuation personnel, personnel type and proportion, movement speed, risk perception adjustment parameter and field of view.

[0015] Further, the step two includes:

[0016] S2-1: Calculate the alarm prompt risk perception factor. Personnel receiving an alarm prompt will assess the danger level of the emergency situation, and then form a risk perception level, which is affected by the sound pressure level, broadcast frequency and time accumulation. The calculation formula is as follows:

[0017]

[0018] Where Lp is the sound pressure level, F is the broadcast frequency, t is the evacuation time, and the time adjustment function η(t) is set as η(t) = 2-e-0.04t;

[0019] S2-2: Calculate the risk perception factor of the dangerous source. The dangerous source is the root cause of the risk perception of personnel, and its size is affected by the straight-line distance between personnel and the dangerous source. The calculation formula is as follows:

[0020]

[0021] Where λ is the distance adjustment parameter, D hazard is the straight-line distance between personnel and the dangerous source;

[0022]

[0023] Where (x i , y i ) is the distance coordinate of individual i, (x hazard , yhazard ) is the distance coordinate of the center point of the hazard source;

[0024] S2-3: Calculate the information transmission risk perception factor. When an emergency occurs, the personnel located in the influence range of the hazard source are information carriers and generate a risk perception level, which is calculated as follows:

[0025] RP k = Ω · RP0

[0026] Where Ω is the risk perception adjustment parameter, RP0 is the risk perception reference value generated by the hazard information, which conforms to the normal distribution N(0.5, 0.22);

[0027] If there are information carriers in the field of view of the personnel during the evacuation process, the individual becomes an information carrier and generates a corresponding risk perception level, which is affected by the information transmission risk perception level of the surrounding information carriers, the number of information carriers, and the risk perception adjustment parameter. The calculation formula is as follows:

[0028]

[0029] Where Ω is the risk perception adjustment parameter, RP k is the risk perception level of the information carrier, and m' is the number of information carriers in the field of view;

[0030] S2-4: Calculate the risk perception level under the combined influence of alarm prompts, hazard sources, and information transmission, with the formula as follows:

[0031] RP(t) = a · RP alarm + b · RP hazard + c · RP info

[0032] Where a is the weight coefficient of the alarm prompt risk perception level, b is the weight coefficient of the hazard source risk perception level, and c is the weight coefficient of the information transmission risk perception level;

[0033] S2-5: To couple risk perception with personnel movement, the risk perception level of personnel at time t is limited as follows:

[0034]

[0035] S2-6: The higher the risk perception level, the stronger the individual's desire to escape. The movement speed of the individual at time t affected by the risk perception level is calculated as follows:

[0036] v(t) = (1 - RP(t)) · v min + RP(t) · v max

[0037] Where vmin is the minimum movement speed of the individual, v max is the maximum movement speed of the individual;

[0038] S2-7: As the evacuation time increases, the risk perception level of the personnel accumulates, and if the personnel who have not evacuated produce panic and anxiety, it will lead to decision-making errors and the generation of irrational behavior. The performance of the evacuation direction selection is as follows:

[0039] When RP(t) ∈ [0, 1), the personnel move in the best direction at the next time step; when RP(t) = 1, the probability of the personnel moving in the best direction is reduced to 1 / 2, the probability of moving in the adjacent cell in the best direction is 1 / 8, and the probability of moving in the adjacent cell in other directions is 1 / 20.

[0040] Further, step three comprises:

[0041] Mapping the personnel evacuation parameters to the artificial bee colony algorithm: the evacuation exit corresponds to the honey source, the danger source and the obstacle correspond to the abandoned honey source, the leader in the group corresponds to the leading bee, the other personnel in the group correspond to the following bee, and the path quality corresponds to the honey source benefit degree, i.e. the fitness value;

[0042] According to the total number of evacuees, the number of groups is calculated, and it is assumed that there are 100 people in each group, and the value of k is calculated;

[0043] The K-means method is used to cluster the evacuation personnel in the scene, and k groups are obtained;

[0044] The distance of each personnel in the group to each exit is calculated, and the exit selected by the most personnel is the evacuation target exit of the group.

[0045] Further, the K-means method is used to cluster the evacuation personnel in the scene, and k groups are obtained, including the following steps:

[0046] S3-1: Randomly select one from all the evacuation personnel as the initial clustering center c1;

[0047] S3-2: Calculate the distance between each personnel in the data set and the initial clustering center, and select the shortest distance D(x);

[0048] S3-3: Select the personnel with the maximum distance as the new clustering center with a probability, and the probability calculation formula is:

[0049]

[0050] S3-4: Repeat steps S3-2 and S3-3 until all 7 clustering centers are determined;

[0051] S3-5: Calculate the distance between each personnel X and the clustering center ck The distance between them is calculated as follows The personnel are divided into the class corresponding to the cluster center with the minimum distance, where n is the two-dimensional coordinates of the personnel;

[0052] S3-6: The calculation is completed, and the k clusters after clustering are obtained;

[0053] The distance of each personnel in the cluster to each exit is calculated, and the exit selected by the most personnel is the target exit for evacuation of the cluster.

[0054] Further, step four includes:

[0055] S4-1: The fitness values of all personnel in the cluster are improved and calculated as follows:

[0056]

[0057] Where RP i is the risk perception level of personnel i, F(i) is the predicted distance of personnel i to the target exit, D hazard is the distance of personnel i to the nearest danger source, C is the congestion degree of the target exit; α, β, γ are the weight coefficients of the four factors, respectively;

[0058] S4-2: The fitness values of all personnel in the cluster are sorted, and the top 25% of individuals with the highest fitness values are selected as the leading bees, and the remaining personnel are selected as the following bees for evacuation;

[0059] S4-3: The evacuation scene is converted into a two-dimensional grid, and a Moore-type neighborhood is selected so that the cells can move in eight directions around them. The free cells are marked as 0, the cells occupied by personnel are marked as 1, and the cells occupied by obstacles or danger sources are marked as -1;

[0060] S4-4: The cellular automaton model is used to realize the evacuation of personnel to the exit. The target cell at the next time step is determined by the evacuation path calculated by the artificial bee colony algorithm. If the target position cell state is 0, the individual moves to the next time step and updates the state of the two cells. If the target position cell state is 1, the individual waits in place or selects another cell state 0 to move;

[0061] S4-5: Iterative operation is performed once per time step until all personnel in the evacuation scene have left.

[0062] A convention and exhibition building crowd evacuation simulation system based on risk perception:

[0063] The system includes a evacuation scene modeling module, a risk perception model construction module, a path planning and personnel movement module, and an export and storage module:

[0064] The evacuation scene modeling module is used for obtaining the exhibition building evacuation scene parameters and personnel parameters, constructing an evacuation scene model and importing the personnel into the evacuation model;

[0065] The risk perception model construction module is used for constructing a risk perception model containing three elements of alarm prompt, danger source and information transmission, and coupling the model with personnel movement;

[0066] The path planning and personnel movement module is used for planning a macro evacuation path of a group by using an improved artificial bee colony algorithm, and simulating personnel movement by using a cellular automaton model, so as to realize evacuation model construction by combining the methods;

[0067] The export and storage module is used for exporting the evacuation path, total evacuation time and personnel position information at each time step when all the evacuation personnel leave the evacuation scene and determine that the evacuation is ended.

[0068] Further, the path planning and personnel movement module comprises a macro path planning module and a micro movement simulation module.

[0069] The macro path planning module uses the improved artificial bee colony algorithm to perform macro path planning: the fitness value of an individual is calculated according to four elements of the risk perception level of the personnel, the predicted distance to the exit, the distance to the danger source and the exit congestion degree; the fitness values solved in the group are sorted, and the first 25% of the personnel are selected as leading bees, and the other personnel are selected as following bees.

[0070] The micro movement simulation module uses the cellular automaton model to update the position of the personnel: the macro path planned by the improved artificial bee colony algorithm is used to obtain the best target cell of the personnel at the next time step, if the target cell is marked as 0, the personnel update the position at the next time step, if the target cell is marked as 1 or -1, the personnel select a suboptimal target to update the position or do not update, and the iteration step is repeated until all the personnel leave the evacuation scene, which can be used as a global evacuation path.

[0071] An electronic device comprises a memory and a processor, the memory stores a computer program, and the processor realizes the steps of the above method when executing the computer program.

[0072] A computer readable storage medium is used for storing computer instructions, and the computer instructions realize the steps of the above method when executed by a processor.

[0073] Advantages of the present application

[0074] The application introduces risk perception related elements in the crowd evacuation simulation model, realizes the coupling of macroscopic path planning and microcosmic motion simulation by combining the improved artificial bee colony algorithm with the cellular automaton model, is more suitable for the emergency evacuation of complex scenes containing obstacles such as exhibition buildings, and the results show that the method proposed in the application can effectively complete the emergency evacuation simulation of crowds in exhibition buildings.

[0075] The application constructs a risk perception model, and truly reflects the cognitive ability of different types of personnel to risks in emergency situations and the change of motion behavior in evacuation.

[0076] The application uses the K-means method to group crowds, and more truly reflects the phenomenon of group evacuation of personnel in evacuation.

[0077] The application improves the artificial bee colony algorithm, constructs a fitness function suitable for complex scenes containing obstacles, so that the simulation result is closer to reality.

[0078] The application combines the improved artificial bee colony algorithm with the cellular automaton, the two models complement each other to better simulate crowd motion, and introduces the influence of risk perception in the model, constructs a more realistic evacuation model, and improves the evacuation efficiency.

[0079] The application uses the cellular automaton model to simulate the microcosmic motion of personnel based on the evacuation path planned by the improved artificial bee colony algorithm, reflects the interaction between personnel and the environment, can predict the real evacuation time, and provides suggestions for evacuation design. BRIEF DESCRIPTION OF DRAWINGS

[0080] Figure 1 A flow chart of the crowd evacuation simulation method based on risk perception of the exhibition building according to the application;

[0081] Figure 2 A block diagram of the crowd evacuation simulation system based on risk perception of the exhibition building according to the application;

[0082] Figure 3 A classification diagram of input parameters of the model according to the application;

[0083] Figure 4 A flow chart of the evacuation model combining the improved artificial bee colony algorithm with the cellular automaton model according to the application. DETAILED DESCRIPTION

[0084] Clearly and completely, the technical solutions in the embodiments of the present application will be described below in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of the present application.

[0085] In the following embodiments, risk perception refers to the perception and subjective evaluation of a person on the short-term threat of a certain specific danger to his own life and health, describes the subjective evaluation of the probability of the impact of an adverse event on himself, and the evaluation of his vulnerability and coping resource measures. Both risk and perception are included, risk refers to the possibility of adverse consequences to human safety, health, property, etc., and "perception" refers to the collection, identification and interpretation of information to understand the environment, which is affected by individual differences and environmental interference. Risk perception is a subjective psychological judgment with individual differences, which emphasizes the influence of individual subjective intuition and personal experience on cognition. Different levels of risk perception as a moderator will have different degrees of influence on individuals, and further change the direction and strength of decision-making and behavior in the evacuation process.

[0086] As Figure 1 , the present application proposes a risk perception-based crowd evacuation simulation method for exhibition buildings:

[0087] The method specifically comprises the following steps:

[0088] Step 1: Obtain the exhibition building evacuation scene parameters and personnel parameters, construct an evacuation scene model and import the personnel into the evacuation model;

[0089] As Figure 3 , the exhibition building evacuation scene parameters include: exhibition hall size, number of exits, exit width, obstacle layout form, dangerous source setting and emergency broadcasting system setting;

[0090] The personnel parameters include: number of evacuees, personnel type and proportion, movement speed, risk perception adjustment parameter and field of view.

[0091] Step 2: Construct a risk perception model containing three elements of alarm prompt, dangerous source and information transmission, and couple the model with personnel movement;

[0092] S2-1: Calculate the alarm prompt risk perception factor. When personnel receive an alarm prompt, they will evaluate the danger level of the emergency situation, and then form a risk perception level, which is affected by sound pressure level, broadcast frequency and time accumulation. The calculation formula is as follows:

[0093]

[0094] wherein Lp is the sound pressure level, F is the broadcast frequency, t is the evacuation time, and the time adjustment function η(t) is set as η(t) = 2 - e-0.04t;

[0095] S2-2: Calculate the risk perception factor of the hazard source, which is the root cause of the risk perception of the personnel, and its size is affected by the straight-line distance between the personnel and the hazard source. The calculation formula is as follows:

[0096]

[0097] wherein λ is the distance adjustment parameter, D hazard is the straight-line distance between the personnel and the hazard source;

[0098]

[0099] wherein (x i ,y i ) is the distance coordinate of the individual i, and (x hazard ,y hazard ) is the distance coordinate of the center point of the hazard source;

[0100] S2-3: Calculate the information transmission risk perception factor. When an emergency occurs, the personnel located within the influence range of the hazard source become information carriers and generate a risk perception level, which is calculated as follows:

[0101] RP k = Ω·RP0

[0102] wherein Ω is the risk perception adjustment parameter, and RP0 is the risk perception reference value generated by the hazard information, which conforms to the normal distribution N(0.5, 0.22);

[0103] If there are information carriers in the visual range of the personnel during the evacuation process, the individual will become an information carrier and generate a corresponding risk perception level, which is affected by the information transmission risk perception level of the surrounding information carriers, the number of information carriers, and the risk perception adjustment parameter. The calculation formula is as follows:

[0104]

[0105] wherein Ω is the risk perception adjustment parameter, and RP k is the risk perception level of the information carrier, and m' is the number of information carriers in the visual range;

[0106] S2-4: Calculate the risk perception level under the comprehensive influence of the alarm prompt, the hazard source, and the information transmission, which is calculated as follows:

[0107] RP(t) = a·RP alarm +b·RP hazard +c·RP info

[0108] wherein a is the weight coefficient of the alarm prompt risk perception level, b is the weight coefficient of the hazard source risk perception level, and c is the weight coefficient of the information transmission risk perception level;

[0109] S2-5: To couple the risk perception with the movement of the personnel, the risk perception level of the personnel at time t is limited as follows:

[0110]

[0111] S2-6: The higher the risk perception level, the stronger the individual's desire to escape, and the movement speed of the individual at time t under the influence of the risk perception level is calculated as follows:

[0112] v(t) = (1 - RP(t)) · v min + RP(t) · v max

[0113] wherein v min is the minimum movement speed of the individual, and v max is the maximum movement speed of the individual;

[0114] S2-7: As the evacuation time increases, the risk perception level of the personnel accumulates, and the unevacuated personnel can produce panic and anxiety, thus leading to decision-making errors and irrational behavior, and the performance of the evacuation direction selection is as follows:

[0115] When RP(t) ∈ [0, 1), the personnel move in the best direction at the next time step; when RP(t) = 1, the probability of the personnel moving in the best direction is reduced to 1 / 2, the probability of moving in the adjacent cell in the best direction is 1 / 8, and the probability of moving in the adjacent cell in other directions is 1 / 20.

[0116] Step three: mapping the personnel evacuation parameters with the artificial bee colony algorithm, using the K-means method to divide the personnel to be evacuated in the evacuation scene into several groups, and assigning an exit to each group according to the distance;

[0117] The artificial bee colony algorithm (ABC algorithm) is an optimization algorithm that simulates the foraging behavior of bees, which divides bees into three categories: scout bees, follower bees, and scout bees, to solve mathematical optimization problems. In path planning applications, the artificial bee colony algorithm has the advantages of fast convergence, few control parameters, easy implementation, simple calculation, and strong robustness. In addition, the global optimization performance of the algorithm is excellent, which can effectively find the optimal path in the search space and improve the efficiency of evacuation. However, as a random algorithm, the local search may be insufficient.

[0118] First, the personnel evacuation parameters are mapped with the artificial bee colony algorithm: the evacuation exit corresponds to the honey source, the hazard source and the obstacle correspond to the abandoned honey source, the leader in the group corresponds to the leading bee, the other personnel in the group correspond to the following bee, and the path quality corresponds to the honey source benefit degree, that is, the fitness value;

[0119] Then, the number of groups is calculated according to the total number of evacuees, each group has about 100 people, and the k value is calculated;

[0120] The K-means method is used to cluster the evacuation personnel in the scene to obtain k groups; the specific steps are as follows:

[0121] S3-1: randomly select one from all the evacuation personnel as the initial clustering center c1;

[0122] S3-2: calculate the distance between each personnel in the data set and the initial clustering center, and select the shortest distance D(x);

[0123] S3-3: select the personnel with the maximum distance as the new clustering center with a probability, and the probability calculation formula is:

[0124]

[0125] S3-4: repeat steps S3-2 and S3-3 until all 7 clustering centers are determined;

[0126] S3-5: calculate the distance between each personnel X and the clustering center c k , and the formula is as follows The personnel is divided into the class corresponding to the clustering center with the minimum distance, wherein n is the horizontal and vertical coordinates of the personnel;

[0127] S3-6: the calculation is completed, and k groups after clustering are obtained.

[0128] The distance of each personnel in the group to each exit is calculated, and the exit selected by the most personnel is the evacuation target exit of the group.

[0129] Step four: use the improved artificial bee colony algorithm to plan the macro evacuation path of the group, and use the cellular automaton model to simulate the movement of personnel;

[0130] As Figure 4 shown is the evacuation model flow chart of the improved artificial bee colony algorithm combined with the cellular automaton model.

[0131] Cellular automata is a dynamic system evolving in discrete time, space and state dimensions. The model is built by summarizing the rules of cells, which can simulate and reproduce various self-organizing phenomena with high complexity. In the field of crowd evacuation, cellular automata model has strong local search ability and good visualization effect, which can depict individual interaction and group behavior in detail and intuitively show the trajectory of crowd movement.

[0132] S4-1: Improve and calculate the fitness value of all personnel in the group as follows:

[0133]

[0134] Where RP i is the risk perception level of personnel i, and the calculation formula is:

[0135] RP(t)=a·RP alarm +b·RP hazard +c·RP info

[0136] F(i) is the predicted distance of personnel i to the target exit, which is calculated by using a heuristic method,

[0137] The specific steps of the heuristic method are as follows:

[0138] Initialize two lists, open_list and closed_list, to store the grids to be checked and the grids that have been checked, respectively;

[0139] Add the starting point to open_list and check its adjacent grids. Add the passable grids (grids that are not obstacles and danger sources) to open_list. Move the starting point to closed_list and set it as the parent node of these grids;

[0140] Calculate the F(n) value of these grids, select the grid with the smallest value as the parent node, and move it to closed_list;

[0141] Check the adjacent grids of the grid, ① if the grid is an obstacle or in closed_list, ignore it, ② if it is not in open_list, add it to open_list and calculate the F(n), G(n) and H(n) values, ③ if it is in open_list, but the new path provides a smaller G(n) value, update the G(n) and F(n) values.

[0142] If the exit grid is reached, calculate the final actual distance F(n); otherwise, perform step 3 to continue calculation until the exit grid is reached.

[0143] F(n)=G(n)+H(n)

[0144]

[0145] H(n) = |x exit -x n |+|y exit -y n |

[0146] F(n) represents the actual distance from the starting position to the exit position of the individual; G(n) is the actual distance from the starting position to the grid n, which is the sum of the Euclidean distances between the two grids passed; H(n) represents the estimated distance from the grid n to the exit position, which is calculated by Manhattan distance. Since there may be obstacles in the path, H(n) is not accurate enough to represent the estimated distance.

[0147] D hazard is the distance from personnel i to the nearest hazard source, and the calculation formula is:

[0148]

[0149] C is the congestion degree of the target exit, and the calculation formula is as follows:

[0150]

[0151] where N(t) is the number of individuals waiting for evacuation at the exit at time t, W e is the exit width, and S is the number of individuals passing through the exit per time step;

[0152] α, β, γ are the weight coefficients of the four factors, respectively;

[0153] S4-2: At the initial stage of evacuation, the congestion degrees of each exit are equivalent, and the evacuees evacuate according to the original target exit. After a period of evacuation, due to various factors, the use of the exit may be unbalanced. When the congestion degree of the exit reaches the threshold X, the last 25% of the individuals in each group recompute the fitness value for each exit. If there is a better choice, the individual will leave the current group and evacuate to the new exit.

[0154] Sort the fitness values of all individuals in the group, and select the top 25% of the individuals as the leading bees, and the remaining individuals as the following bees for evacuation;

[0155] S4-3: The evacuation scene is converted into a two-dimensional grid, and a Moore-type neighborhood is selected so that the cell can move in eight directions. The free cell is marked as 0, the cell occupied by personnel is marked as 1, and the cell occupied by obstacles or hazards is marked as -1;

[0156] S4-4: the personnel evacuation to the exit is realized using the cellular automaton model, the target cell of the next time step is determined by the evacuation path calculated by the artificial bee colony algorithm, if the state of the target position cell is 0, the movement is performed in the next time step and the states of the two cells are updated, if the state of the target position cell is 1, the individual waits in place or selects other cells with a state of 0 to move;

[0157] S4-5: the iteration operation is performed once per time step until all the personnel in the evacuation scene leave.

[0158] Step five: when all the evacuation personnel leave the evacuation scene, it is determined that the evacuation is completed, the evacuation path, the total evacuation time and the position information of the personnel at each time step are derived and stored.

[0159] A convention and exhibition building crowd evacuation simulation system based on risk perception, as shown in Figure 2

[0160] The system comprises a evacuation scene modeling module, a risk perception model construction module, a path planning and personnel movement module and a derivation and storage module.

[0161] The evacuation scene modeling module is used for acquiring convention and exhibition building evacuation scene parameters and personnel parameters, constructing an evacuation scene model and importing the personnel into the evacuation model.

[0162] The risk perception model construction module is used for constructing a risk perception model comprising three elements of alarm prompt, danger source and information transmission, and coupling the model with personnel movement.

[0163] The path planning and personnel movement module is used for planning a macro evacuation path of a group using an improved artificial bee colony algorithm and simulating personnel movement using a cellular automaton model, so as to realize the construction of an evacuation model combining the methods.

[0164] The path planning and personnel movement module comprises a macro path planning module and a micro movement simulation module.

[0165] The macro path planning module uses the improved artificial bee colony algorithm to perform macro path planning: the fitness value of an individual is calculated according to four elements of the risk perception level of the personnel, the predicted distance to the exit, the distance to the danger source and the exit congestion degree; the fitness values solved in the group are sorted, and the first 25% of the personnel are selected as leading bees and the other personnel are selected as following bees.

[0166] ​The micro-motion simulation module updates the position of the personnel using a cellular automaton model: using the macro-path planned by the improved artificial bee colony algorithm, the best target cell of the personnel at the next time step is obtained, if the target cell is marked as 0, the personnel updates the position to the target cell at the next time step, if the target cell is marked as 1 or -1, the personnel selects a suboptimal target to update the position or does not update, and the iteration step is repeated until all the personnel leave the evacuation scene, that is, the global evacuation path is obtained.

[0167] The export and storage module: when all the evacuation personnel leave the evacuation scene to determine that the evacuation is completed, the evacuation path, the total evacuation time and the position information of the personnel at each time step are exported.

[0168] An electronic device, comprising a memory and a processor, the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0169] A computer readable storage medium for storing computer instructions, the computer instructions are executed by a processor to implement the steps of the above method.

[0170] The memory in the embodiments of the present application can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read only memory (ROM), a programmable ROM (PROM), an erasable programmable ROM (EPROM), an electrically EPROM (EEPROM) or a flash memory. The volatile memory can be a random access memory (RAM) used as an external cache. By way of example, but not limitation, many forms of RAM can be used, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchlink DRAM (SLDRAM) and direct rambus RAM (DR RAM). It should be noted that the memory of the method described in the present application is intended to include but not limited to these and any other suitable types of memory.

[0171] In the above embodiments, all or part of the methods can be implemented by software, hardware, firmware, or any combination thereof. When implemented by software, all or part of the methods can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transferred from one website, computer, server, or data center to another website, computer, server, or data center through a wired manner such as a coaxial cable, an optical fiber, a digital subscriber line (DSL), or a wireless manner such as infrared, wireless, microwave, etc. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. integrated with one or more available media. The available medium can be a magnetic medium such as a floppy disk, a hard disk, a magnetic tape, an optical medium such as a digital video disc (DVD), or a semiconductor medium such as a solid state disc (SSD), etc.

[0172] In the implementation process, each step of the above method can be completed by the integrated logic circuit of hardware in the processor or the instruction in the form of software. The steps of the method disclosed in the embodiments of the present application can be directly embodied as hardware processor execution or executed by a combination of hardware and software modules in the processor. The software module can be located in a random access memory, a flash memory, a read-only memory, a programmable read-only memory, an electrically erasable programmable memory, a register, or other mature storage media in the art. The storage medium is located in the memory, and the processor reads the information in the memory and combines the hardware to complete the steps of the above method. To avoid repetition, it will not be described in detail here.

[0173] It should be noted that the processor in the embodiments of the present application can be an integrated circuit chip with signal processing capability. In the implementation process, each step of the method embodiments can be completed by the integrated logic circuit of hardware in the processor or the instructions in the form of software. The processor mentioned above can be a general processor, a digital signal processor DSP, an application specific integrated circuit ASIC, a field programmable gate array FPGA or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The disclosed methods, steps and logic block diagrams in the embodiments of the present application can be implemented or executed. The general processor can be a microprocessor or the processor can be any conventional processor. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as hardware code processor execution completion, or executed by hardware and software module combination in the code processor. The software module can be located in the random access memory, the flash memory, the read only memory, the programmable read only memory or the electrically erasable programmable memory, the register or other mature storage medium in the art. The storage medium is located in the memory, and the processor reads the information in the memory, and combines the hardware to complete the steps of the above method.

[0174] The risk-aware crowd evacuation simulation method, system, electronic device and medium for exhibition buildings proposed in the present application are described in detail, the principles and implementation modes of the present application are described, and the above embodiment description is only used to help understand the method of the present application and its core idea; at the same time, for those skilled in the art, according to the idea of the present application, the specific implementation mode and application range will be changed, and the above description should not be understood as a limitation of the present application.

Claims

1. A risk perception-based crowd evacuation simulation method for exhibition buildings, characterized in that: The method specifically comprises the following steps: Step one: Obtain the evacuation scene parameters and personnel evacuation parameters of the exhibition building, construct the evacuation scene model and import the personnel into the evacuation model; Step two: Construct a risk perception model containing three elements: alarm prompt, hazard source and information transmission, and couple the model with personnel movement; Step three: Map the personnel evacuation parameters to the artificial bee colony algorithm, use the K-means method to divide the personnel to be evacuated in the evacuation scene into several groups, and assign an exit to each group according to the distance; Step four: Use the improved artificial bee colony algorithm to plan the macro evacuation path of the group, and use the cellular automaton model to simulate the movement of personnel; S4-1: Improve and calculate the fitness value of all personnel in the group as follows: wherein RP i is the risk perception level of the person i , F ( i ) is the predicted distance of the person i to the target exit, D hazard is the distance of the person i to the nearest hazard source, C is the crowding level of the target exit; , , , are the weight coefficients of the four factors, respectively. S4-2: Sort the fitness values of all personnel in the group, and select the top 25% individuals as leader bees and the remaining personnel as follower bees for evacuation; S4-3: Convert the evacuation scene into a two-dimensional grid, select a Moore neighborhood so that the cell can move in eight directions, mark the idle cell as 0, mark the cell occupied by personnel as 1, and mark the cell occupied by obstacles or hazards as -1; S4-4: Use the cellular automaton model to realize personnel evacuation to the exit, the target cell of the next time step is determined by the evacuation path calculated by the artificial bee colony algorithm, if the target position cell state is 0, then move and update the state of the two cells in the next time step, if the target position cell state is 1, then the individual waits in place or selects another cell state 0 to move; S4-5: Perform an iteration operation once per time step until all personnel in the evacuation scene have left; Step five: When all evacuated personnel leave the evacuation scene, determine that the evacuation is complete, and export the evacuation path, total evacuation time, and personnel position information at each time step.

2. The method of claim 1, wherein: In step one, The exhibition building evacuation scene parameters include: exhibition hall size, number of exits, exit width, obstacle layout form, hazard source setting and emergency broadcasting system setting; The personnel evacuation parameters include: number of evacuees, personnel type and proportion, movement speed, risk perception adjustment parameters and field of view.

3. The method of claim 2, wherein: The step two includes: S2-1: Calculate the alarm prompt risk perception factor. When personnel receive an alarm prompt, they will assess the danger level of the emergency situation, thereby forming a risk perception level, which is influenced by sound pressure level, broadcast frequency and time accumulation. The calculation formula is as follows: wherein Lp is the sound pressure level, F is the announcement frequency, t is the evacuation time, the adjustment function of time η ( t ) is set to η ( t )=2-e-0.04t; S2-2: Calculate the hazard source risk perception factor. Hazard source is the root cause of personnel risk perception, which is influenced by the straight-line distance between personnel and hazard source. The calculation formula is as follows: wherein λ is a distance adjustment parameter, Dhazard is the straight-line distance between the person and the hazard. in( xi, yi (is an individual) i Distance coordinates, ( xhazard, yhazard () represents the distance coordinates of the center point of the hazard source; S2-3: Calculate the information transmission risk perception factor. When an emergency occurs, personnel located within the influence range of the hazard source become information carriers and generate a risk perception level, which is calculated as follows: where Ω is a risk perception adjustment parameter, RP 0 is a risk perception baseline value for the hazard information generation, conforming to a normal distribution N(0.5, 0.2 2 ); If there is an information carrier in the field of view of the evacuation personnel, the individual will become an information carrier and generate a corresponding risk perception level, which is influenced by the information transmission risk perception level of the surrounding information carriers, the number of information carriers, and the risk perception adjustment parameter, and is calculated as follows: where Ω is a risk perception adjustment parameter, RP k is the level of risk perception of the information carrier, is the number of information carriers within the field of view; S2-4: Calculate the risk perception level under the combined influence of alarm prompts, hazards, and information transmission, as follows: wherein a is a weight coefficient of the alerting risk perception level, b is a weight coefficient of the hazard source risk perception level, c is a weight coefficient of the information transfer risk perception level; S2-5: To couple risk perception with personnel movement, the risk perception level of personnel at time t is limited as follows: S2-6: The higher the risk perception level, the stronger the individual's desire to escape, and the movement speed of the individual at time t is calculated as follows: wherein v min is the minimum movement speed of the individual, v max is the maximum movement speed of the individual; S2-7: As the evacuation time increases, the risk perception level of the personnel accumulates, and if the unevacuated personnel experience panic and anxiety, it will lead to decision-making errors and irrational behavior, and the evacuation direction selection is as follows: When RP(t) ∈ [0, 1), the personnel move in the best direction at the next time step; when RP(t) = 1, the probability of the personnel moving in the best direction decreases to 1 / 2, the probability of moving to the adjacent cell in the best direction is 1 / 8, and the probability of moving to the adjacent cell in other directions is 1 / 20.

4. The method of claim 3, wherein: In step three, the following steps are included: Map the personnel evacuation parameters to the artificial bee colony algorithm: map the evacuation exit to the honey source, the hazard and obstacle to the abandoned honey source, the leader in the group to the leading bee, the other personnel in the group to the following bee, and the path quality to the honey source benefit degree, i.e., the fitness value; Calculate the number of groups based on the total number of evacuees, and set 100 people per group to calculate the k value; Use the K-means method to cluster the evacuation personnel in the scene to obtain k groups; Calculate the distance from each personnel in the group to each exit, and the exit selected by the most personnel is the evacuation target exit for the group.

5. The crowd evacuation simulation method of claim 4, wherein: The K-means method is used to cluster the evacuation personnel in the scene to obtain k groups, including the following steps: S3-1 : Randomly select one from all evacuees as initial cluster center c 1; S3-2: Calculate the distance between each person in the data set and the initial cluster center, and select the shortest distance among them D ( x ) S3-3: Select the personnel with the maximum distance as the new clustering center with a probability, and the probability calculation formula is: S3-4: Repeat steps S3-2 and S3-3 until all 7 clustering centers are determined; S3-5: Calculate the distance between each person and the cluster center, formula as follows X with the cluster center c k between them, formula as follows , and put the person into the class corresponding to the cluster center with the minimum distance, where n is the two dimensions of the horizontal and vertical coordinates of the person; S3-6: The calculation is completed, and k groups after clustering are obtained; Calculate the distance from each personnel in the group to each exit, and the exit selected by the most personnel is the evacuation target exit for the group.

6. A simulation system for performing the risk perception-based crowd evacuation simulation method of any one of claims 1 to 5, wherein: The system includes a evacuation scene modeling module, a risk perception model construction module, a path planning and personnel movement module, and an export and storage module: The evacuation scene modeling module is used to obtain the exhibition building evacuation scene parameters and personnel evacuation parameters, construct an evacuation scene model, and import the personnel into the evacuation model; The risk perception model construction module: constructs a risk perception model containing three elements of alarm prompts, hazards, and information transmission, and couples the model with personnel movement; The path planning and personnel motion module: uses an improved artificial bee colony algorithm to plan a macroscopic evacuation path for a group, and uses a cellular automaton model to simulate personnel motion, thereby realizing an evacuation model construction combining methods; The export and storage module: when all evacuees leave the evacuation scene, determines that the evacuation is over, and exports the evacuation path, total evacuation time, and personnel position information at each time step.

7. The crowd evacuation simulation system according to claim 6, characterized in that: The path planning and personnel motion module comprises a macroscopic path planning module and a microscopic motion simulation module; The macroscopic path planning module uses an improved artificial bee colony algorithm to perform macroscopic path planning: calculates an individual fitness value according to four elements of a personnel risk perception level, a predicted distance to an exit, a distance to a hazard source, and an exit congestion degree; sorts the fitness values solved within a group, selects the top 25% of personnel as leading bees, and selects the other personnel as following bees; The microscopic motion simulation module uses a cellular automaton model to update personnel positions: uses the macroscopic path planned by the improved artificial bee colony algorithm to obtain a best target cell of personnel at a next time step, if the target cell is marked as 0, the personnel updates a position to the target cell at the next time step, if the target cell is marked as 1 or -1, the personnel selects a suboptimal target to update a position or does not update, and repeats the iteration steps until the personnel all leave the evacuation scene, which can be used as a global evacuation path. 8.An electronic device comprising a memory and a processor, the memory storing a computer program, wherein, The processor executes the computer program to realize the steps of the method in any one of claims 1 to 5.

9. A computer readable storage medium for storing computer instructions, characterized in that, The computer instructions are executed by the processor to realize the steps of the method in any one of claims 1 to 5.

Images