Juan Wei
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Juan Wei has a total of 39 co-authors. Here are the top co-authors by number of shared publications:
- Jun Hu
Key Laboratory of Interior Layout Optimization and Security, Institutions of Higher Education of Sichuan Province, Chengdu Normal University, Chengdu 611130, P. R. China
2 shared publications - Ling Fan
Key Laboratory of Interior Layout Optimization and Security, Institutions of Higher Education of Sichuan Province, Chengdu Normal University, Chengdu 611130, P. R. China
2 shared publications - Longcheng Yang
Sichuan Key Laboratory of Indoor Space Layout Optimization and Security Guarantee, Chengdu Normal University, Chengdu, China
2 shared publications Xiaofei Wang
School of Computer Science, Chengdu Normal University, Chengdu, China
2 shared publicationsDai-Hui Ni
1 shared publicationFan Ling
Key Laboratory of Interior Layout Optimization and Security, Institutions of Higher Education of Sichuan Province, Chengdu Normal University, Chengdu 611130, People’s Republic of China
1 shared publication
Latest Publications
- 26 April 2025
- Published by World Scientific Pub Co Pte Ltd in International Journal of Modern Physics C
- Vol. 37 (02)
A pedestrian evacuation model with variable neighborhood simulated annealing
In order to further simulate the evacuation process of pedestrians in the indoor space accurately, this paper proposes an evacuation model based on the Moore structure of cellular automata. The proposed model establishes a method to calculate the crowd movement gains by introducing the field gains, waiting gains, conformity gains and guidance gains. The variable neighborhood simulated annealing algorithm is used to optimize the model. Finally, a simulation platform is used to carry out simulation experiments and numerical analysis, and verifies that the model has better adaptability than the traditional field model. At the same time, this paper deeply studies the relationship between parameters such as average velocity, number of pedestrians, evacuation time and weight value distribution. The results of numerical analysis show that in the initial stage of evacuation, the larger the weight value of the field gains and the smaller the waiting gains consideration area, the more pedestrians there are; and in the middle and late stages of evacuation, the smaller the weight value of the field gains and the larger the waiting gains consideration area, the more evacuees there are.
- 26 April 2025
- Published by World Scientific Pub Co Pte Ltd in International Journal of Modern Physics C
- Vol. 37 (02)
A pedestrian evacuation model with variable neighborhood simulated annealing
In order to further simulate the evacuation process of pedestrians in the indoor space accurately, this paper proposes an evacuation model based on the Moore structure of cellular automata. The proposed model establishes a method to calculate the crowd movement gains by introducing the field gains, waiting gains, conformity gains and guidance gains. The variable neighborhood simulated annealing algorithm is used to optimize the model. Finally, a simulation platform is used to carry out simulation experiments and numerical analysis, and verifies that the model has better adaptability than the traditional field model. At the same time, this paper deeply studies the relationship between parameters such as average velocity, number of pedestrians, evacuation time and weight value distribution. The results of numerical analysis show that in the initial stage of evacuation, the larger the weight value of the field gains and the smaller the waiting gains consideration area, the more pedestrians there are; and in the middle and late stages of evacuation, the smaller the weight value of the field gains and the larger the waiting gains consideration area, the more evacuees there are.
- 22 November 2024
- Published by World Scientific Pub Co Pte Ltd in International Journal of Modern Physics C
- Vol. 36 (07)
Study on pedestrian evacuation model based on reinforcement learning
This paper proposed a pedestrian evacuation model combined with reinforcement learning in order to study how to better guide pedestrians to complete evacuation in specific indoor scenes. This model introduced the way of establishing a scene in cellular automata and formulated reward rules according to the characteristics of the scene. It fitted the psychological activities of pedestrians in the actual evacuation process and trained the strategy of pedestrians at the overall level through the Q-learning algorithm from the reinforcement learning area. A speed control mechanism combined with real statistical data was introduced to simulate the speed attenuation. A simulation platform was built to compare the evacuation conditions under different scenarios and the different total numbers of pedestrians. The research showed that the model could automatically realize the exit selection function of pedestrians and part of conformity behavior. In the same evacuation scenario, this model could show adaptability for the different total numbers of pedestrians.
- 22 November 2024
- Published by World Scientific Pub Co Pte Ltd in International Journal of Modern Physics C
- Vol. 36 (07)
Study on pedestrian evacuation model based on reinforcement learning
This paper proposed a pedestrian evacuation model combined with reinforcement learning in order to study how to better guide pedestrians to complete evacuation in specific indoor scenes. This model introduced the way of establishing a scene in cellular automata and formulated reward rules according to the characteristics of the scene. It fitted the psychological activities of pedestrians in the actual evacuation process and trained the strategy of pedestrians at the overall level through the Q-learning algorithm from the reinforcement learning area. A speed control mechanism combined with real statistical data was introduced to simulate the speed attenuation. A simulation platform was built to compare the evacuation conditions under different scenarios and the different total numbers of pedestrians. The research showed that the model could automatically realize the exit selection function of pedestrians and part of conformity behavior. In the same evacuation scenario, this model could show adaptability for the different total numbers of pedestrians.
- 21 September 2023
- Published by IOP Publishing in Physica Scripta
- Vol. 98 (10) , 105241
Simulation of a multi-floor evacuation with the extended social force model in a multi-corridor environment
For the stagnation problem that easily occurs in the process of simulating multi-floor and multi-staircase evacuation using a traditional social force model, in this paper, it is proposed to improve the social force model by introducing a moth-flame optimization algorithm, thus to establish a new evacuation model. The model firstly integrates the field model into a social force model as the pedestrian self-driving direction. Meanwhile, an objective optimization function of minimum system evacuation time is established based on the evaluation indexes, such as staircase congestion degree and average velocity, and the moth-flame optimization algorithm is improved by introducing dynamic inertia weight and random reverse learning strategy, thus establishing an evacuation optimization method. Finally, a simulation and numerical analysis is carried out for the multi-floor evacuation process using the experimental simulation platform built, which deeply analyzes the key factors influencing the model, gives the change relationships among the parameters such as evacuation time, initial pedestrian velocity, the number of pedestrians and staircase width, and verifies the effectiveness of the model.
- 21 September 2023
- Published by IOP Publishing in Physica Scripta
- Vol. 98 (10) , 105241
Simulation of a multi-floor evacuation with the extended social force model in a multi-corridor environment
For the stagnation problem that easily occurs in the process of simulating multi-floor and multi-staircase evacuation using a traditional social force model, in this paper, it is proposed to improve the social force model by introducing a moth-flame optimization algorithm, thus to establish a new evacuation model. The model firstly integrates the field model into a social force model as the pedestrian self-driving direction. Meanwhile, an objective optimization function of minimum system evacuation time is established based on the evaluation indexes, such as staircase congestion degree and average velocity, and the moth-flame optimization algorithm is improved by introducing dynamic inertia weight and random reverse learning strategy, thus establishing an evacuation optimization method. Finally, a simulation and numerical analysis is carried out for the multi-floor evacuation process using the experimental simulation platform built, which deeply analyzes the key factors influencing the model, gives the change relationships among the parameters such as evacuation time, initial pedestrian velocity, the number of pedestrians and staircase width, and verifies the effectiveness of the model.
- Open Access
- 1 April 2022
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 2242 (1) , 012006
Influence of Excitation Signal Type and Period Selection on Detection Capability of TEM System
The type and period of excitation signal are the important technical indexes of TEM system detection, which have an important influence on the detection accuracy and detection depth of the system. In this paper, by simulating the magnetic field distribution characteristics and magnetic focusing effects of transmitting coils with different excitation signals at the same depth, the differences of excitation signal types are analyzed and studied. Then, the echo effect diagram of receiving coils and the change curve of magnetic flux at the equivalent depth are simulated under different periods to determine the minimum period of excitation signal by comparative analysis. The simulation results show that the focusing and propagation depth of the magnetic field energy generated by the excitation signal are better when the rectangular pulse is selected and its period is determined to be 500 ms. Experimental tests under different thickness of steel plate show that the induced voltage on the receiving coil is different with different thickness. The thicker the ferromagnetic material is, the smaller the peak value of echo signal is. Moreover, in the case of no ferromagnetic material model, the induced voltage of the receiving coil is the maximum. This provides a theoretical basis for evaluating the corrosion of buried metal pipes by transient electromagnetic detection system.
- 1 April 2022
- Published by IOP Publishing in Journal of Physics: Conference Series
- Vol. 2242 (1) , 012006
Open AccessInfluence of Excitation Signal Type and Period Selection on Detection Capability of TEM System
The type and period of excitation signal are the important technical indexes of TEM system detection, which have an important influence on the detection accuracy and detection depth of the system. In this paper, by simulating the magnetic field distribution characteristics and magnetic focusing effects of transmitting coils with different excitation signals at the same depth, the differences of excitation signal types are analyzed and studied. Then, the echo effect diagram of receiving coils and the change curve of magnetic flux at the equivalent depth are simulated under different periods to determine the minimum period of excitation signal by comparative analysis. The simulation results show that the focusing and propagation depth of the magnetic field energy generated by the excitation signal are better when the rectangular pulse is selected and its period is determined to be 500 ms. Experimental tests under different thickness of steel plate show that the induced voltage on the receiving coil is different with different thickness. The thicker the ferromagnetic material is, the smaller the peak value of echo signal is. Moreover, in the case of no ferromagnetic material model, the induced voltage of the receiving coil is the maximum. This provides a theoretical basis for evaluating the corrosion of buried metal pipes by transient electromagnetic detection system.
- Open Access
- 1 August 2020
- Published by Wiley in Journal of Advanced Transportation
- Vol. 2020, 1-7
Simulating Crowd Evacuation in a Social Force Model with Iterative Extended State Observer
Due to the interaction and external interference, the crowds will constantly and dynamically adjust their evacuation path in the evacuation process to achieve the purpose of rapid evacuation. The information from previous process can be used to modify the current evacuation control information to achieve a better evacuation effect, and iterative learning control can achieve an effective prediction of the expected path within a limited running time. In order to depict this process, the social force model is improved based on an iterative extended state observer so that the crowds can move along the optimal evacuation path. First, the objective function of the optimal evacuation path is established in the improved model, and an iterative extended state observer is designed to get the estimated value. Second, the above model is verified through simulation experiments. The results show that, as the number of iterations increases, the evacuation time shows a trend of first decreasing and then increasing.
- 1 August 2020
- Published by Wiley in Journal of Advanced Transportation
- Vol. 2020, 1-7
Open AccessSimulating Crowd Evacuation in a Social Force Model with Iterative Extended State Observer
Due to the interaction and external interference, the crowds will constantly and dynamically adjust their evacuation path in the evacuation process to achieve the purpose of rapid evacuation. The information from previous process can be used to modify the current evacuation control information to achieve a better evacuation effect, and iterative learning control can achieve an effective prediction of the expected path within a limited running time. In order to depict this process, the social force model is improved based on an iterative extended state observer so that the crowds can move along the optimal evacuation path. First, the objective function of the optimal evacuation path is established in the improved model, and an iterative extended state observer is designed to get the estimated value. Second, the above model is verified through simulation experiments. The results show that, as the number of iterations increases, the evacuation time shows a trend of first decreasing and then increasing.
- 1 December 2017
- Published by World Scientific Pub Co Pte Ltd in International Journal of Modern Physics C
- Vol. 28 (12)
Modeling and simulation of group formation and crowd dynamics with smoke effect
In order to depict crowd dynamics in the case of smoke effect, a novel evacuation model is presented based on the extended cellular automaton. In the model, the moving probability of the target position in the next time step is given by combining distance gain and smoke gain at first. Through considering individual kinship and group effect, group disbanding and regrouping rules are defined, and the optimal evacuation route planning is determined. At last, the simulation was conducted to study the key factors influencing evacuation efficiency. The results showed that when the group size was small and the smoke spreading velocity was slow, priority selection of the shortest route strategy was good for reducing evacuation time, and large-scale group should be avoided as much as possible in evacuation process.
- 1 December 2017
- Published by World Scientific Pub Co Pte Ltd in International Journal of Modern Physics C
- Vol. 28 (12)
Modeling and simulation of group formation and crowd dynamics with smoke effect
In order to depict crowd dynamics in the case of smoke effect, a novel evacuation model is presented based on the extended cellular automaton. In the model, the moving probability of the target position in the next time step is given by combining distance gain and smoke gain at first. Through considering individual kinship and group effect, group disbanding and regrouping rules are defined, and the optimal evacuation route planning is determined. At last, the simulation was conducted to study the key factors influencing evacuation efficiency. The results showed that when the group size was small and the smoke spreading velocity was slow, priority selection of the shortest route strategy was good for reducing evacuation time, and large-scale group should be avoided as much as possible in evacuation process.
- Open Access
- 1 January 2014
- Published by Wiley in Mathematical Problems in Engineering
- Vol. 2014 (1)
The Group Evacuation Behavior Based on Fire Effect in the Complicated Three‐Dimensional Space
In order to effectively depict the group evacuation behavior in the complicated three‐dimensional space, a novel pedestrian flow model is proposed with three‐dimensional cellular automata. In this model the calculation methods of floor field and fire gain are elaborated at first, and the transition gain of target position at the next moment is defined. Then, in consideration of pedestrian intimacy and velocity change, the group evacuation strategy and evolution rules are given. Finally, the experiments were conducted with the simulation platform to study the relationships of evacuation time, pedestrian density, average system velocity, and smoke spreading velocity. The results had shown that large‐scale group evacuation should be avoided, and in case of large pedestrian density, the shortest route of evacuation strategy would extend system evacuation time.
- 1 January 2014
- Published by Wiley in Mathematical Problems in Engineering
- Vol. 2014 (1)
Open AccessThe Group Evacuation Behavior Based on Fire Effect in the Complicated Three‐Dimensional Space
In order to effectively depict the group evacuation behavior in the complicated three‐dimensional space, a novel pedestrian flow model is proposed with three‐dimensional cellular automata. In this model the calculation methods of floor field and fire gain are elaborated at first, and the transition gain of target position at the next moment is defined. Then, in consideration of pedestrian intimacy and velocity change, the group evacuation strategy and evolution rules are given. Finally, the experiments were conducted with the simulation platform to study the relationships of evacuation time, pedestrian density, average system velocity, and smoke spreading velocity. The results had shown that large‐scale group evacuation should be avoided, and in case of large pedestrian density, the shortest route of evacuation strategy would extend system evacuation time.
- 1 April 2004
- Vol. 23 (4)
[Effects of intermittent and continuous thermochemotherapeutic intra artery infusion on adriamycin concentration in rabbit VX-2 tumor].
It has been proved that vital signs of organism can be influenced by heat infusion and the thermochemotherapy with Adriamycin (ADM) is more effective than the general chemotherapy in inhibiting extraneous rabbit VX-2 cells. Intermittent thermochemotherapeutic infusion and continuous thermochemotherapeutic infusion with ADM were performed respectively on the rabbits to evaluate the effectiveness and safety of intermittent thermochemotherapeutic intra artery infusion by comparing their respiration rate, heart rate, body temperature, and the ADM concentration in VX-2 carcinoma.
- 1 April 2004
- Vol. 23 (4)
[Effects of intermittent and continuous thermochemotherapeutic intra artery infusion on adriamycin concentration in rabbit VX-2 tumor].
It has been proved that vital signs of organism can be influenced by heat infusion and the thermochemotherapy with Adriamycin (ADM) is more effective than the general chemotherapy in inhibiting extraneous rabbit VX-2 cells. Intermittent thermochemotherapeutic infusion and continuous thermochemotherapeutic infusion with ADM were performed respectively on the rabbits to evaluate the effectiveness and safety of intermittent thermochemotherapeutic intra artery infusion by comparing their respiration rate, heart rate, body temperature, and the ADM concentration in VX-2 carcinoma.