An agent-based modeling approach to collaborative classrooms evacuation process

The paper explores the usage of agent-based modeling in the context of large event halls evacuation during music festivals and cultural events. An agent-based model is created in NetLogo 6.2.2 for better representing the human behavior when involved in such situations. A series of characteristics have been set for the agents in order to preserve their heterogeneity in terms of speed, age, locomotion impairment, familiarity with the environment, evacuating with another person, choosing the closest exit or not, selecting the closest path to the exits. An “adapted cone exit” approach has been proposed in the paper in order to facilitate the guidance of the agents in the agent-based model to the closest exit and its advantages have been proved in comparison with the classical “cone exit” approach. Different evacuation scenarios have been simulated and analyzed for better observing the capabilities of evacuation modeling in the case of evacuation emergencies. Besides the overall evacuation time, an average evacuation time has been determined for the agents based on the individual evacuation time, which can be easily connected with a risk indicator associated to each situation. Due to the visual interface offered by the agent-based model, coupled with the evacuation indicators, the proposed model can allow the identification of the main factors that may contribute to a prolonged evacuation process (e.g. overcrowding at one of the exits, not choosing the appropriate door, evacuating with a friend/parent) and the potential measures to be considered for insuring a safe evacuation process.

Evolution of pedestrian evacuation considering different human behaviors

Aim: The main aim of the study was to investigate the possibility to use the Pathfinder simulation software to determine the duration of an evacuation and to plan its course for various scenarios of evacuation organisation, for specific profiles and behaviours of passengers and on-board personnel, and for a specific geometrical arrangement of the passenger cabin of a selected passenger aircraft. In addition, the paper discusses selected factors that affect the evacuation from the passenger aircraft. Project and methods: The Pathfinder software used in the research has the graphical interface to create an evacuation simulation model (2D and 3D) as well as tools to visualise the results. Pathfinder is based on artificial intelligence algorithms, in which each passenger has a number of individual features that can influence his/her movements and decisions during the simulation. The simulation of people's movement is determined by their profiles and behaviours, the parameters of which can be entered by means of probability distributions, which makes it possible to take into account the stochastic nature of the evacuation process. Results: The Boeing 787 Dreamliner was selected for the study, for which six options for simulating the evacuation of 252 passengers and eight members of on-board personnel were conducted. The shortest evacuation time was achieved by changing the even distribution of the number of passengers to the individual emergency exits, thus avoiding congestions in sensitive areas of the passenger cabin. The increase in passengers' maximum speed has paradoxically increased evacuation times, as it has increased the intensity of passenger collisions. It was found that one of the key issues affecting the timing of an evacuation is the proper organisation of the evacuation by on-board personnel, who, by guiding passengers through the geometrically most advantageous passageways, results in the fastest possible evacuation. The simulations in variants five and six have achieved satisfactory evacuation times, which are within the emergency aircraft evacuation time limit required in a certification process. Conclusions: The presented simulation models, the results obtained, and the wide range of possibilities of three-dimensional visualisation of research results give a rational basis for the use of Pathfinder software for testing the evacuation process and thus: for the usage in the aircraft design process, for preparing aircrafts for tests, for shaping evacuation procedures, for on-board personnel training and for air accident investigation.

In order to find out the evacuation process of people when fire occurs in a high-rise building, the evacuation process in a ten-storey telecom office building is simulated under different opening conditions by using FDS+Evac software. The temperature field, smoke layer height and toxic gas index are analysed quantificationally. The results prove that about 70% of time is wasted in the stairs because of the stoppage during people evacuation. The exit numbers have little effect on the evacuation time if the number of people is small and they are familiar with the exits. However, adding another stair case in the building is able to reduce 1/3 time of evacuation.

An Agent-Based Approach to Aircraft Conflict Resolution with Constraints

This study focuses on the safe evacuation strategy and evacuation process in the subway train under the fires. The subway station evacuation mode should be adopted if the power system of a subway train is normal on fire. While, the tunnel evacuation mode should be adopted if the power system of the train fails because of the effects of fire. Under the tunnel evacuation mode, the direction of tunnel smoke should be opposite to that of most passengers, and passengers should be evacuated toward the fresh wind. By using the numerical simulation software Pathfinder and PyroSim, the passenger evacuation time under different conditions is calculated, and the safety of the evacuation process is evaluated. The results show that the evacuation time of the station evacuation mode is obviously shorter than that of the tunnel evacuation mode. With the same conditions, the evacuation time of the tunnel evacuation mode is 2193 s, which is about four times as much as the evacuation time of the station evacuation mode (526 s). The total evacuation time increases with the total number of passengers and the proportion of older people and children. Under an oil pool fire, which is an extreme fire condition, the fire environment inside the train may reach a level threatening the passengers’ safety before the evacuation is complete, even before the door opens; therefore, special attention should be paid to the safety issues in stage from the fire begins to the evacuation complete.

CellEVAC: An adaptive guidance system for crowd evacuation through behavioral optimization

Modeling and safety strategy of passenger evacuation in a metro station in China

The use of ships as a transportation is growing rapidly, of course, this is also related to transportation safety related including ship accidents. The National Transportation Accident Commission (KNKT) recorded 86 accidents in the sea transportation sector from 2010 to 2019. In 2018, the KMP Trisna Dwitya ferry ran aground, which resulted in 28 passengers having to be evacuated. Safety on ships must be optimized by minimizing casualties. The determining factor in evacuation is the time it takes for passengers to get out of the waiting room on the ship. Hence, it is necessary to calculate the time for the evacuation process. The purpose of this study is to obtain results in the form of evacuation time during a fire and evaluate the simulation of passenger evacuation in the fastest time. The method used is modeling and simulation, where modeling is used to simulate and analyze the time required for evacuation with the Pathfinder software. The results of the analysis and simulation yielded 3 different scenarios. Scenario 1: When the fire point is on the main deck where the motorized vehicle with evacuation time reaches 20 minutes 21 seconds. Scenario 2, when the fire point is in the left side engine room, reaches 20 minutes 57 seconds. Scenario 3, when the fire point is in the right-side engine room, the time obtained is 21 minutes 1 second. So that the 3 scenarios have met the requirements of the IMO, which is less than 60 minutes during the evacuation process on a passenger ship.

Evacuation time prediction method for large cruise ships based on a deep extreme learning machine

Human behaviour and evacuation time for large underground comprehensive buildings during fire risk process

Cel: The article presents the results of research on the evacuation process of people from the building of the Faculty of Environmental and Power Engineering of the Silesian University of Technology, including the evacuation of people with a temporary limitation of independent movement, who are evacuated using an evacuation chair. The travel times and the time needed to prepare an evacuation chair were examined. Based on the research, the average speeds of movement of the studied populations were determined. Projekt i metody: Twelve evacuation experiments were carried out in three different user populations of the building. The experiments included the analysis of the times of movement of people without disabilities; people with temporary disabilities who move independently on crutches and a population in which there was one person with temporary reduced mobility, who was evacuated using an evacuation chair. Six of the experiments concerned the evacuation from the fourth floor of the building, three of which were proceeded through the main staircase and the remaining three through the side staircase. The next six experiments were carried out from the second floor, also split into two different staircases. Each experiment ended when all people reached the meeting point near the building. Wyniki: The lowest values of the average total travel time were recorded for the population without disabilities. The shortest average travel time was 83 seconds and concerned the evacuation of the population without disabilities from the second floor, evacuating through a side staircase (K1). In all the experiments, the person on crutches was the slowest to move, for whom the evacuation times were the longest. The maximum average time for a person on crutches was 342 seconds to evacuate from the fourth floor via the main staircase. Evacuation with an emergency chair improved the process by 10.47% for the evacuation from the second floor using K1 staircase, and for the evacuation with this staircase from the 4th floor by 28.71%. For the main staircase (K2), the experiments conducted from the second floor using an evacuation chair took 40.02% less time than an independent evacuation of a person with crutches and 47.07% less time when evacuating from the fourth floor. Wnioski: Interpreting the results obtained in the experiments, it can be stated that the evacuation using an evacuation chair improved the evacuation process compared to the experiments in which a person temporarily disabled was walking independently on crutches. People without disabilities evacuate the fastest. The analysis of the time of travel made it possible to determine the average speed of movement of the analyzed populations, which can be used as a model value to perform an evacuation simulation. Słowa kluczowe: evacuation, evacuation time, people with disabilities, evacuation chair

Computer simulations on the evacuation process in a story are launched with cellular automaton in this article. The story is composed of five rooms and one corridor. Influence of various parameters on the evacuation process is investigated. It shows that the width of the door of rooms has little influence but the width of the corridor and the maximum velocity of the pedestrian have great influence on the time for evacuation. The relation between evacuation time and the width of corridor is found as tc ∝ W−0.84. It is also found that appropriate shape of the room is helpful to evacuation.

During mass evacuations, many psychological and physical factors are responsible for stampedes and other life threatening situations. Quantitative and qualitative analyses of these factors are of high importance while devising optimal strategies for evacuations. In this paper, we present an agent-based model that considers psychological and physical factors that cause panic in such situations. We have also simulated some simple evacuation scenarios and presented a method to identify possible bottlenecks and shortcomings in the environments during emergency evacuations. Our method also helps in evaluation and analysis of different evacuation strategies. To enable this analysis, we have used a rule-based roadmap approach, where critical nodes in the environment are identified by the evacuation planner and each node has a special rule according to the strategy of the planner. We evaluate different strategies on parameters, such as evacuation time and physical discomfort caused to the agents.

Integration of cumulative prospect theory in cellular automata model for building evacuation