Research On Several Key Technologies Of The Crowd Evacuation In Indoor Scene

The density of crowed is often high in the unexpected crowd incidents. As a result, disaster area will bring huge casualties or economic losses because of continued rescue mismanagement. Besides, it will bring the significant negative political influences to the country. However, we can make the management of public security crisis incident more scientific and effective. Study of the necessary for setting up the disaster prevention space and how to design it is preliminary discussed, for depth study in design, evaluation and optimization of large crowd evacuation plans of public facilities, has great significance.We study large crowd evacuation technology mainly in five parts:(1)、The first part is the crowd evacuation simulation. Its main purpose is to reflect the whole process of evacuation with the analysis of the psychological factors, exercise behavior and compliance with China evacuation standards body. In the process of simulation, it can be render the evacuation situation as possible. According to the sumulation data people study the bottleneck problem of the crowd evacuation simulation to get emergency emergency plan.(2)、The evacuation path finding method is using Dijkstra and A* algorithm, to get escape trajectory with the topology construction of evacuation scene. The topology structure can be abstracted evacuation scenarios, and calculate the shortest path according to the relationship and weights between nodes. This paper proposes an improved node structure based on the(node-relation structure NRS) model of the global and local evacuation routing method. The hierarchical network structure(hierarchical network structure of HNS) builds complex building topological relation to hypergraph structure by the graph theory. Its advantage can simplify the problem and support 3D spatial information query and analysis.(3)、The third part is the presented swam intelligence optimization algorithm that combines the evolutionary method of particle swarm optimization with the filled function method in order to solve the evacuation routing optimization problem. In the proposed algorithm, the whole process is divided into three stages. In the first stage, we make use of global optimization of filled function to obtain optimal solution to set destination of all particles. In the second stage, we make use of the randomicity and rapidity of particle swarm optimization to simulate the crowd evacuation. In the third stage, we propose three methods to manage the competitive behaviors among the particles. This algorithm makes an evacuation plan using the dynamic way finding of particles from both a macroscopic and a microscopic perspective simultaneously. There are three types of experimental scenes to verify the effectiveness and efficiency of the proposed algorithm: a single room, a 4-room/1-corridor layout, and a multi-room multi-floor building layout. The simulation examples demonstrate that the proposed algorithm can greatly improve upon evacuation clear and congestion times. The experimental results demonstrate that this method takes full advantage of multiple exits to maximize the evacuation efficiency.(4)、The fourth part is the risk assessment model to evaluate the risk of crowd evacuation path. According to the length of the evacuation route, evacuation environment, fire source location and evacuees position distribution, the risk assessment model can evaluate risk degree. We establish based on Monte Carlo method of crowd evacuation path quantitative risk evaluation model. The model proposed the degree of path congestion, crossroads congestion and exit congestion as three indicators to fully consider the influence factors of evacuation congestion. The congestion degree of the model regards time as the unit of measurement, a combination of other factors to obtain the total assessment of evacuation time. Then manager can make decisions and analysis with the risk degree.(5)、Evacuation optimization technique is mainly dealing with minimization the evacuation time to achieve the most efficient evacuation. With the increase of the complexity of the building and mass incidents, evacuation path optimization problem has become a very hot research direction in the emergency evacuation field. In an actual emergency, evacuation congestion problem has aroused the interest of some scholars, beacause the crowd congestion is an important factor to influence the evacuation results.We put forward a new model(MEEM) that it gets solution of the Nash equilibrium of game theory by the maximum entropy and it combines with the Monte Carlo algorithm to obtain the optimal evacuation plan under complex scene. We improved game theory methods to obtain the global optimal evacuation plan, according to the the evacuees location distribution to access the risk degrees of evacuation route for managing congestion problem and path selection problem. Compared with other evacuation model, we use evacuation model based on Agent with Newton formula to improve the effect of evacuation under the complex scene. MEEM model can study the evacuation plan that how to affect the evacuation process. Our model regards each exit as a participant in the game theory. Unlike other game theory recognize evacuees as participants, it can deal with more Agents in optimization problem. Finally, we use the maximum entropy to solve the payoff function for calculating Nash equilibrium of game theory. The solution is the optimized plan of evacuation.In conclusion, the evacuation optimization technique has been facing the problem what is to minimize the evacuation time of the plan. In this paper, we have presented a novel model(MEEM) in which game theory and Monte Carlo methods are combined for evacuation routing optimization in complex scenes. The improved game theory method finds the global minimizer for the evacuation time using maximum entropy theory. This model obtains a global optimum agent distribution with estimation of the degree of risk of a route to manage the routing selection problem and the congestion conflict problem. Compared with other evacuation models, we employed a method based on an agent whose motion is governed by Newton’s equations to simulate the effect of complex building architectures during urgent evacuation. MEEM has been established to examine how the rational evacuation planning of the evacuees affects the evacuation process. Our model considers the exits as participants rather than agents, which can deal with more agents in the game optimization problem. Finally, we develop evacuation plans by calculating payoff functions for convergence to Nash equilibria, which are established based on maximum entropy theory.