In recent years,significant research attention has been directed towards swarm intelligence.The Milling behavior of fish schools,a prime example of swarm intelligence,shows how simple rules followed by individual agen...In recent years,significant research attention has been directed towards swarm intelligence.The Milling behavior of fish schools,a prime example of swarm intelligence,shows how simple rules followed by individual agents lead to complex collective behaviors.This paper studies Multi-Agent Reinforcement Learning to simulate fish schooling behavior,overcoming the challenges of tuning parameters in traditional models and addressing the limitations of single-agent methods in multi-agent environments.Based on this foundation,a novel Graph Convolutional Networks(GCN)-Critic MADDPG algorithm leveraging GCN is proposed to enhance cooperation among agents in a multi-agent system.Simulation experiments demonstrate that,compared to traditional single-agent algorithms,the proposed method not only exhibits significant advantages in terms of convergence speed and stability but also achieves tighter group formations and more naturally aligned Milling behavior.Additionally,a fish school self-organizing behavior research platform based on an event-triggered mechanism has been developed,providing a robust tool for exploring dynamic behavioral changes under various conditions.展开更多
The propulsive performance of an oblique school of fish is numerically studied using an immersed boundary technique. The effect of the spacing and wiggling phase on the hydrodynamics of the system is investigated. The...The propulsive performance of an oblique school of fish is numerically studied using an immersed boundary technique. The effect of the spacing and wiggling phase on the hydrodynamics of the system is investigated. The hydrodynamics of the system is deeply affected by the spacing between each fish in the school. When the horizontal separation is smaller than the length of the fish body, the downstream fish exhibits a larger thrust coefficient and greater propulsive efficiency than the isolated fish. However, the corresponding values for the upstream fish are smaller. The opposite behavior occurs when the horizontal separation increases beyond the length of fish body. The propulsive performance of the entire oblique school of fish can be substantially enhanced when the separations are optimized.展开更多
Numerical simulations of self-propelled swimming of a three dimensional bionic fish and fish school in a viscous fluid are carried out.This is done with the assistance of a parallel software package produced for 3D mo...Numerical simulations of self-propelled swimming of a three dimensional bionic fish and fish school in a viscous fluid are carried out.This is done with the assistance of a parallel software package produced for 3D moving boundary problems.This computational fluid dynamics package combines the adaptive multi-grid finite volume method,the immersed boundary method and VOF(volume of fluid)method.By using the package results of the self-propelled swimming of a 3D bionic fish and fish school in a vis-cous fluid are obtained.With comparison to the existing experimental measurements of living fishes,the predicted structure of vortical wakes is in good agreement with the measurements.展开更多
This paper proposes an improved Gaussian particle filter integratingthe Artificial Fish School Algorithm to optimise the measured values to improve the overall estimation accuracy of the system.Meanwhile,it also solve...This paper proposes an improved Gaussian particle filter integratingthe Artificial Fish School Algorithm to optimise the measured values to improve the overall estimation accuracy of the system.Meanwhile,it also solves the problems of susceptibility to interference and insufficient estimation accuracy in nonlinear systems.Furthermore,since the calculation time of the fusion algorithm increases,in order to ensure the speed of state estimation,the linear transformation of standard particle swarm is used to replace the particle sampling link of Gaussian particle filter.Simulation results show that the calculation speed of a fast Gaussian Particle Filter based on the Artificial Fish School Algorithm is 21.7%faster than the Particle Filter based on the Artificial Fish School Algorithm.Compared with Particle Filter,Gaussian particle filter,and the Artificial Fish School Algorithm,the proposed algorithm has a higher accuracy.展开更多
Aiming at the design problem of aviation swarm combat course of action(COA),considering the influence of stochastic parameters in the causal relationship model and optimization problem model,according to the dynamic i...Aiming at the design problem of aviation swarm combat course of action(COA),considering the influence of stochastic parameters in the causal relationship model and optimization problem model,according to the dynamic influence net(DIN)theory,stochastic simulation technique,feedforward neural network(FNN)function approximation technique and multi-objective artificial fish school algorithm(MOAFSA),this paper proposed a COA optimized method based on DIN and multi-objective stochastic chance constraint optimization for aviation swarm combat.First,on the basis of establishing the overall framework of the model and defining the elements of causal relationship modeling,the static and dynamic causal relationship modeling and optimization problem modeling were carried out respectively.Second,the probability propagation mechanism of DIN was established,which mainly included two aspects,i.e.,the overall process and the specific algorithm.Then,input and output data were generated based on stochastic simulation.According to these data,FNN was adopted for function approximation,and MOAFSA was adopted for iterative optimization.Finally,the rationality of the model,and the effectiveness and superiority of the algorithm were verified through multiple sets of simulation cases.展开更多
基金supported by the National Natural Science Foundation of China under Grant 62273351 and Grant 62303020.
文摘In recent years,significant research attention has been directed towards swarm intelligence.The Milling behavior of fish schools,a prime example of swarm intelligence,shows how simple rules followed by individual agents lead to complex collective behaviors.This paper studies Multi-Agent Reinforcement Learning to simulate fish schooling behavior,overcoming the challenges of tuning parameters in traditional models and addressing the limitations of single-agent methods in multi-agent environments.Based on this foundation,a novel Graph Convolutional Networks(GCN)-Critic MADDPG algorithm leveraging GCN is proposed to enhance cooperation among agents in a multi-agent system.Simulation experiments demonstrate that,compared to traditional single-agent algorithms,the proposed method not only exhibits significant advantages in terms of convergence speed and stability but also achieves tighter group formations and more naturally aligned Milling behavior.Additionally,a fish school self-organizing behavior research platform based on an event-triggered mechanism has been developed,providing a robust tool for exploring dynamic behavioral changes under various conditions.
基金supported by the National Natural Science Foundation of China (Grant 11462015)
文摘The propulsive performance of an oblique school of fish is numerically studied using an immersed boundary technique. The effect of the spacing and wiggling phase on the hydrodynamics of the system is investigated. The hydrodynamics of the system is deeply affected by the spacing between each fish in the school. When the horizontal separation is smaller than the length of the fish body, the downstream fish exhibits a larger thrust coefficient and greater propulsive efficiency than the isolated fish. However, the corresponding values for the upstream fish are smaller. The opposite behavior occurs when the horizontal separation increases beyond the length of fish body. The propulsive performance of the entire oblique school of fish can be substantially enhanced when the separations are optimized.
基金Supported by the Key Project of National Natural Science Foundation of China(Grant No.10532040)
文摘Numerical simulations of self-propelled swimming of a three dimensional bionic fish and fish school in a viscous fluid are carried out.This is done with the assistance of a parallel software package produced for 3D moving boundary problems.This computational fluid dynamics package combines the adaptive multi-grid finite volume method,the immersed boundary method and VOF(volume of fluid)method.By using the package results of the self-propelled swimming of a 3D bionic fish and fish school in a vis-cous fluid are obtained.With comparison to the existing experimental measurements of living fishes,the predicted structure of vortical wakes is in good agreement with the measurements.
基金supported by Aeronautical Science Founda-tion of China[grant numbers 2018ZC52037,2017ZC52017]and National Natural Science Foundation of China[grant number 51505221].
文摘This paper proposes an improved Gaussian particle filter integratingthe Artificial Fish School Algorithm to optimise the measured values to improve the overall estimation accuracy of the system.Meanwhile,it also solves the problems of susceptibility to interference and insufficient estimation accuracy in nonlinear systems.Furthermore,since the calculation time of the fusion algorithm increases,in order to ensure the speed of state estimation,the linear transformation of standard particle swarm is used to replace the particle sampling link of Gaussian particle filter.Simulation results show that the calculation speed of a fast Gaussian Particle Filter based on the Artificial Fish School Algorithm is 21.7%faster than the Particle Filter based on the Artificial Fish School Algorithm.Compared with Particle Filter,Gaussian particle filter,and the Artificial Fish School Algorithm,the proposed algorithm has a higher accuracy.
基金co-supported by Natural Science Foundation of Shaanxi(2023-JC-QN-0728)Postdoctoral Science Foundation of China(2021M693942)。
文摘Aiming at the design problem of aviation swarm combat course of action(COA),considering the influence of stochastic parameters in the causal relationship model and optimization problem model,according to the dynamic influence net(DIN)theory,stochastic simulation technique,feedforward neural network(FNN)function approximation technique and multi-objective artificial fish school algorithm(MOAFSA),this paper proposed a COA optimized method based on DIN and multi-objective stochastic chance constraint optimization for aviation swarm combat.First,on the basis of establishing the overall framework of the model and defining the elements of causal relationship modeling,the static and dynamic causal relationship modeling and optimization problem modeling were carried out respectively.Second,the probability propagation mechanism of DIN was established,which mainly included two aspects,i.e.,the overall process and the specific algorithm.Then,input and output data were generated based on stochastic simulation.According to these data,FNN was adopted for function approximation,and MOAFSA was adopted for iterative optimization.Finally,the rationality of the model,and the effectiveness and superiority of the algorithm were verified through multiple sets of simulation cases.
