Hunting stability is an important performance criterion in railway vehicles.This study proposes an incorporation of a bio-inspired limb-like structure(LLS)-based nonlinear damping into the motor suspension system for ...Hunting stability is an important performance criterion in railway vehicles.This study proposes an incorporation of a bio-inspired limb-like structure(LLS)-based nonlinear damping into the motor suspension system for traction units to improve the nonlinear critical speed and hunting stability of high-speed trains(HSTs).Initially,a vibration transmission analysis is conducted on a HST vehicle and a metro vehicle that suffered from hunting motion to explore the effect of different motor suspension systems from on-track tests.Subsequently,a simplified lateral dynamics model of an HST bogie is established to investigate the influence of the motor suspension on the bogie hunting behavior.The bifurcation analysis is applied to optimize the motor suspension parameters for high critical speed.Then,the nonlinear damping of the bio-inspired LLS,which has a positive correlation with the relative displacement,can further improve the modal damping of hunting motion and nonlinear critical speed compared with the linear motor suspension system.Furthermore,a comprehensive numerical model of a high-speed train,considering all nonlinearities,is established to investigate the influence of different types of motor suspension.The simulation results are well consistent with the theoretical analysis.The benefits of employing nonlinear damping of the bio-inspired LLS into the motor suspension of HSTs to enhance bogie hunting stability are thoroughly validated.展开更多
To solve the problem of multi-target hunting by an unmanned surface vehicle(USV)fleet,a hunting algorithm based on multi-agent reinforcement learning is proposed.Firstly,the hunting environment and kinematic model wit...To solve the problem of multi-target hunting by an unmanned surface vehicle(USV)fleet,a hunting algorithm based on multi-agent reinforcement learning is proposed.Firstly,the hunting environment and kinematic model without boundary constraints are built,and the criteria for successful target capture are given.Then,the cooperative hunting problem of a USV fleet is modeled as a decentralized partially observable Markov decision process(Dec-POMDP),and a distributed partially observable multitarget hunting Proximal Policy Optimization(DPOMH-PPO)algorithm applicable to USVs is proposed.In addition,an observation model,a reward function and the action space applicable to multi-target hunting tasks are designed.To deal with the dynamic change of observational feature dimension input by partially observable systems,a feature embedding block is proposed.By combining the two feature compression methods of column-wise max pooling(CMP)and column-wise average-pooling(CAP),observational feature encoding is established.Finally,the centralized training and decentralized execution framework is adopted to complete the training of hunting strategy.Each USV in the fleet shares the same policy and perform actions independently.Simulation experiments have verified the effectiveness of the DPOMH-PPO algorithm in the test scenarios with different numbers of USVs.Moreover,the advantages of the proposed model are comprehensively analyzed from the aspects of algorithm performance,migration effect in task scenarios and self-organization capability after being damaged,the potential deployment and application of DPOMH-PPO in the real environment is verified.展开更多
Bearing-based hunting protocols commonly adopt a leaderless consensus method,which requests an entire state of the target for each agent and ignores the necessity of collision avoidance.We investigate a hunting proble...Bearing-based hunting protocols commonly adopt a leaderless consensus method,which requests an entire state of the target for each agent and ignores the necessity of collision avoidance.We investigate a hunting problem of multi-quadrotor systems with hybrid bearing protocols,where the quadrotor systems are divided into master and slave groups for reducing the onboard loads and collision avoidance.The masters obtain the entire state of the target,whose hybrid protocols are based on the displacement and bearing constraints to maintain formation and to avoid the collision in the hunting process.However,the slaves’protocols merely depend on the part state of the masters to reduce loads of data transmission.We also investigate the feasibility of receiving the bearing state from machine vision.The simulation results are given to illustrate the effectiveness of the proposed hybrid bearing protocols.展开更多
The economy is recovering in most parts of the world, which marks its entering into a post-crisis era. The financial crisis breaking out in the new century gave a heavy blow on the world's employment. As the unemp...The economy is recovering in most parts of the world, which marks its entering into a post-crisis era. The financial crisis breaking out in the new century gave a heavy blow on the world's employment. As the unemployment rate was setting a new record in America, which made Obama's approval ratings plummeting, Chinese textile graduates will make their own career decisions.展开更多
We study the influence of conformity on the evolution of cooperative behavior in games under the learning method of sampling on networks.A strategy update rule based on sampling is introduced into the stag hunt game,w...We study the influence of conformity on the evolution of cooperative behavior in games under the learning method of sampling on networks.A strategy update rule based on sampling is introduced into the stag hunt game,where agents draw samples from their neighbors and then update their strategies based on conformity or inference according to the situation in the sample.Based on these assumptions,we present the state transition equations in the dynamic evolution of population cooperation,conduct simulation analysis on lattice networks and scale-free networks,and discuss how this mechanism affects the evolution of cooperation and how cooperation evolves under different levels of conformity in the network.Our simulation results show that blindly imitating the strategies of neighbors does not necessarily lead to rapid consensus in the population.Instead,rational inference through samples can better promote the evolution of the same strategy among all agents in the population.Moreover,the simulation results also show that a smaller sample size cannot reflect the true situation of the neighbors,which has a large randomness,and the size of the benefits obtained in cooperation determines the direction of the entire population towards cooperation or defection.This work incorporates the conforming behavior of agents into the game,uses the method of sampling for strategy updates and enriches the theory of evolutionary games with a more realistic significance.展开更多
The wheel-rail force measurement is of great importance to the condition monitoring and safety evaluation of railway vehicles. In this paper, an improved indirect method for wheel-rail force measurement is proposed to...The wheel-rail force measurement is of great importance to the condition monitoring and safety evaluation of railway vehicles. In this paper, an improved indirect method for wheel-rail force measurement is proposed to evaluate the running safety of railway vehicles. In this method, the equilibrium equations of a suspended wheelset are derived and the wheel-rail forces are then be obtained from measured suspension and inertia forces. This indirect method avoids structural modifications to the wheelset and is applicable to the long-term operation of railway vehicles. As the wheel-rail lateral forces at two sides of the wheelset are difficult to separate, a new derailment criterion by combined use of wheelset derailment coefficient and wheel unloading ratio is proposed. To illustrate its effectiveness, the indirect method is applied to safety evaluation of rail- way vehicles in different scenarios, such as the cross wind safety of a high-speed train and the safety of a metro vehicle with hunting motions. Then, the feasibility of using this method to identify wheel-rail forces for low-floor light rail vehicles with resilient wheels is discussed. The values identified by this method is compared with that by Simpack simulation for the same low-floor vehicle, which shows a good coincidence between them in the time domain of the wheelset lateral force and the wheel-rail vertical force. In addition, use of the method to determine the high-frequency wheel-rail interaction forces reveals that it is possible to identify the high-frequency wheel-rail forces through the accelerations on the axle box.展开更多
基金the National Natural Science Foundation of China (Nos. 52388102, 52072317 and U2268210)the State Key Laboratory of Rail Transit Vehicle System (No. 2024RVL-T12)
文摘Hunting stability is an important performance criterion in railway vehicles.This study proposes an incorporation of a bio-inspired limb-like structure(LLS)-based nonlinear damping into the motor suspension system for traction units to improve the nonlinear critical speed and hunting stability of high-speed trains(HSTs).Initially,a vibration transmission analysis is conducted on a HST vehicle and a metro vehicle that suffered from hunting motion to explore the effect of different motor suspension systems from on-track tests.Subsequently,a simplified lateral dynamics model of an HST bogie is established to investigate the influence of the motor suspension on the bogie hunting behavior.The bifurcation analysis is applied to optimize the motor suspension parameters for high critical speed.Then,the nonlinear damping of the bio-inspired LLS,which has a positive correlation with the relative displacement,can further improve the modal damping of hunting motion and nonlinear critical speed compared with the linear motor suspension system.Furthermore,a comprehensive numerical model of a high-speed train,considering all nonlinearities,is established to investigate the influence of different types of motor suspension.The simulation results are well consistent with the theoretical analysis.The benefits of employing nonlinear damping of the bio-inspired LLS into the motor suspension of HSTs to enhance bogie hunting stability are thoroughly validated.
基金financial support from National Natural Science Foundation of China(Grant No.61601491)Natural Science Foundation of Hubei Province,China(Grant No.2018CFC865)Military Research Project of China(-Grant No.YJ2020B117)。
文摘To solve the problem of multi-target hunting by an unmanned surface vehicle(USV)fleet,a hunting algorithm based on multi-agent reinforcement learning is proposed.Firstly,the hunting environment and kinematic model without boundary constraints are built,and the criteria for successful target capture are given.Then,the cooperative hunting problem of a USV fleet is modeled as a decentralized partially observable Markov decision process(Dec-POMDP),and a distributed partially observable multitarget hunting Proximal Policy Optimization(DPOMH-PPO)algorithm applicable to USVs is proposed.In addition,an observation model,a reward function and the action space applicable to multi-target hunting tasks are designed.To deal with the dynamic change of observational feature dimension input by partially observable systems,a feature embedding block is proposed.By combining the two feature compression methods of column-wise max pooling(CMP)and column-wise average-pooling(CAP),observational feature encoding is established.Finally,the centralized training and decentralized execution framework is adopted to complete the training of hunting strategy.Each USV in the fleet shares the same policy and perform actions independently.Simulation experiments have verified the effectiveness of the DPOMH-PPO algorithm in the test scenarios with different numbers of USVs.Moreover,the advantages of the proposed model are comprehensively analyzed from the aspects of algorithm performance,migration effect in task scenarios and self-organization capability after being damaged,the potential deployment and application of DPOMH-PPO in the real environment is verified.
基金Project supported by the National Natural Science Foundation of China(Grant Nos.61673217 and 61673214)the National Defense Basic Scientific Research Program of China(Grant No.JCKY2019606D001)the China Scholarship Council.
文摘Bearing-based hunting protocols commonly adopt a leaderless consensus method,which requests an entire state of the target for each agent and ignores the necessity of collision avoidance.We investigate a hunting problem of multi-quadrotor systems with hybrid bearing protocols,where the quadrotor systems are divided into master and slave groups for reducing the onboard loads and collision avoidance.The masters obtain the entire state of the target,whose hybrid protocols are based on the displacement and bearing constraints to maintain formation and to avoid the collision in the hunting process.However,the slaves’protocols merely depend on the part state of the masters to reduce loads of data transmission.We also investigate the feasibility of receiving the bearing state from machine vision.The simulation results are given to illustrate the effectiveness of the proposed hybrid bearing protocols.
文摘The economy is recovering in most parts of the world, which marks its entering into a post-crisis era. The financial crisis breaking out in the new century gave a heavy blow on the world's employment. As the unemployment rate was setting a new record in America, which made Obama's approval ratings plummeting, Chinese textile graduates will make their own career decisions.
基金Project supported by the National Natural Science Foundation of China(Grant No.72031009)the National Social Science Foundation of China(Grant No.20&ZD058)。
文摘We study the influence of conformity on the evolution of cooperative behavior in games under the learning method of sampling on networks.A strategy update rule based on sampling is introduced into the stag hunt game,where agents draw samples from their neighbors and then update their strategies based on conformity or inference according to the situation in the sample.Based on these assumptions,we present the state transition equations in the dynamic evolution of population cooperation,conduct simulation analysis on lattice networks and scale-free networks,and discuss how this mechanism affects the evolution of cooperation and how cooperation evolves under different levels of conformity in the network.Our simulation results show that blindly imitating the strategies of neighbors does not necessarily lead to rapid consensus in the population.Instead,rational inference through samples can better promote the evolution of the same strategy among all agents in the population.Moreover,the simulation results also show that a smaller sample size cannot reflect the true situation of the neighbors,which has a large randomness,and the size of the benefits obtained in cooperation determines the direction of the entire population towards cooperation or defection.This work incorporates the conforming behavior of agents into the game,uses the method of sampling for strategy updates and enriches the theory of evolutionary games with a more realistic significance.
基金supported by the National Natural Science Foundation of China (Grant No. U1334206 and No. 51475388)Science & Technology Development Project of China Railway Corporation (Grant No. J012-C)
文摘The wheel-rail force measurement is of great importance to the condition monitoring and safety evaluation of railway vehicles. In this paper, an improved indirect method for wheel-rail force measurement is proposed to evaluate the running safety of railway vehicles. In this method, the equilibrium equations of a suspended wheelset are derived and the wheel-rail forces are then be obtained from measured suspension and inertia forces. This indirect method avoids structural modifications to the wheelset and is applicable to the long-term operation of railway vehicles. As the wheel-rail lateral forces at two sides of the wheelset are difficult to separate, a new derailment criterion by combined use of wheelset derailment coefficient and wheel unloading ratio is proposed. To illustrate its effectiveness, the indirect method is applied to safety evaluation of rail- way vehicles in different scenarios, such as the cross wind safety of a high-speed train and the safety of a metro vehicle with hunting motions. Then, the feasibility of using this method to identify wheel-rail forces for low-floor light rail vehicles with resilient wheels is discussed. The values identified by this method is compared with that by Simpack simulation for the same low-floor vehicle, which shows a good coincidence between them in the time domain of the wheelset lateral force and the wheel-rail vertical force. In addition, use of the method to determine the high-frequency wheel-rail interaction forces reveals that it is possible to identify the high-frequency wheel-rail forces through the accelerations on the axle box.
