Different from the organization structure of complex projects in Western countries, the Liang Zong hierarchical organization structure of complex projects in China has two different chains, the chief-engineer chain an...Different from the organization structure of complex projects in Western countries, the Liang Zong hierarchical organization structure of complex projects in China has two different chains, the chief-engineer chain and the general-director chain,to handle the trade-off between technical and management decisions. However, previous works on organization search have mainly focused on the single-chain hierarchical organization in which all decisions are regarded as homogeneous. The heterogeneity and the interdependency between technical decisions and management decisions have been neglected. A two-chain hierarchical organization structure mapped from a real complex project is constructed. Then, a discrete decision model for a Liang Zong two-chain hierarchical organization in an NK model framework is proposed. This model proves that this kind of organization structure can reduce the search space by a large amount and that the search process should reach a final stable state more quickly. For a more complicated decision mechanism, a multi-agent simulation based on the above NK model is used to explore the effect of the two-chain organization structure on the speed, stability, and performance of the search process. The results provide three insights into how, compared with the single-chain hierarchical organization, the two-chain organization can improve the search process: it can reduce the number of iterations efficiently; the search is more stable because the search space is a smoother hill-like fitness landscape; in general, the search performance can be improved.However, when the organization structure is very complicated, the performance of a two-chain organization is inferior to that of a single-chain organization. These findings about the efficiency of the unique Chinese-style organization structure can be used to guide organization design for complex projects.展开更多
In this study, we develop a mixed reality game system to investigate characteristics ofjudgrnents of individual players in an evacuation process. The characteristics of judgments of the players that are inferred from ...In this study, we develop a mixed reality game system to investigate characteristics ofjudgrnents of individual players in an evacuation process. The characteristics of judgments of the players that are inferred from the performance of the game are then incorporated into a multi-agent simulation as rules. The behavior of evacuees is evaluated in approximations of real situations, by using the agent simulation including different judgments of evacuees. Using the results of the simulation, effective methods are discussed for achieving the escape of the evacuees within a short time.展开更多
The prediction of the behavior of people in a disaster has a useful role to play in the design of urban structures such as department stores, schools, and office buildings. We focus on using emergency exit signs to ef...The prediction of the behavior of people in a disaster has a useful role to play in the design of urban structures such as department stores, schools, and office buildings. We focus on using emergency exit signs to effectively guide the evacuation of people on a floor with a dynamically changing layout. A multi-agent simulation is developed to simulate the behavior of evacuees on a floor. A mathematical model is constructed to obtain optimal sign locations to efficiently assist evacuation under the condition that obstacles are dynamically generated on the floor. The optimal sign locations are calculated by the mathematical model. Then, the developed simulation is performed to evaluate the effectiveness of the emergency exit signs and the behavior of evacuees on simple layout models using the calculated optimal sign locations.展开更多
When arranging the pedestrian infrastructure,one of the most important components that make a tangible contribution to the safety of pedestrians is to organize the safe road crossing.In cities,pedestrians often cross ...When arranging the pedestrian infrastructure,one of the most important components that make a tangible contribution to the safety of pedestrians is to organize the safe road crossing.In cities,pedestrians often cross a road in the wrong place due to established routes or inadequate location of crosswalks.Accidents with the participation of pedestrians who crossed the road neglecting the traffic rules,make up a significant part of the total amount of road accidents.In this paper,we propose a method that allows us,on the basis of the results of a computer simulation of pedestrian traffic,to obtain predicted routes for road crossing and to indicate optimal locations for crosswalks that take into account established pedestrian routes and increase their safety.The work describes an extension for the existing AntRoadPlanner simulation algorithm,which searches for and clusters points where pedestrians cross the roadway and suggests locations for new crosswalks.This method was tested on the basis of a comparative simulation of several territories before and after its application,as well as on the basis of a field study of the territories.The developed algorithm can also be used to search for other potentially dangerous places for pedestrians on plans of districts,for example,crossings in places with limited visibility.展开更多
With the aid of multi-agent based modeling approach to complex systems, the hierarchy simulation models of carrier-based aircraft catapult launch are developed. Ocean, carrier, aircraft, and atmosphere are treated as ...With the aid of multi-agent based modeling approach to complex systems, the hierarchy simulation models of carrier-based aircraft catapult launch are developed. Ocean, carrier, aircraft, and atmosphere are treated as aggregation agents, the detailed components like catapult, landing gears, and disturbances are considered as meta-agents, which belong to their aggregation agent. Thus, the model with two layers is formed i.e. the aggregation agent layer and the meta-agent layer. The information communication among all agents is described. The meta-agents within one aggregation agent communicate with each other directly by information sharing, but the meta-agents, which belong to different aggregation agents exchange their information through the aggregation layer first, and then perceive it from the sharing environment, that is the aggregation agent. Thus, not only the hierarchy model is built, but also the environment perceived by each agent is specified. Meanwhile, the problem of balancing the independency of agent and the resource consumption brought by real-time communication within multi-agent system （MAS） is resolved. Each agent involved in carrier-based aircraft catapult launch is depicted, with considering the interaction within disturbed atmospheric environment and multiple motion bodies including carrier, aircraft, and landing gears. The models of reactive agents among them are derived based on tensors, and the perceived messages and inner frameworks of each agent are characterized. Finally, some results of a simulation instance are given. The simulation and modeling of dynamic system based on multi-agent system is of benefit to express physical concepts and logical hierarchy clearly and precisely. The system model can easily draw in kinds of other agents to achieve a precise simulation of more complex system. This modeling technique makes the complex integral dynamic equations of multibodies decompose into parallel operations of single agent, and it is convenient to expand, maintain, and reuse the program codes.展开更多
In this paper,a theoretical framework of Multiagent Simulation(MAS)is proposed for strategic bidding in electricity markets using reinforcement learning,which consists of two parts:one is a MAS system used to simulate...In this paper,a theoretical framework of Multiagent Simulation(MAS)is proposed for strategic bidding in electricity markets using reinforcement learning,which consists of two parts:one is a MAS system used to simulate the competitive bidding of the actual electricity market;the other is an adaptive learning strategy bidding system used to provide agents with more intelligent bidding strategies.An ExperienceWeighted Attraction(EWA)reinforcement learning algorithm(RLA)is applied to the MAS model and a new MAS method is presented for strategic bidding in electricity markets using a new Improved EWA(IEWA).From both qualitative and quantitative perspectives,it is compared with three other MAS methods using the Roth-Erev(RE),Q-learning and EWA.The results show that the performance of the MAS method using IEWA is proved to be better than the others.The four MAS models using four RLAs are built for strategic bidding in electricity markets.Through running the four MAS models,the rationality and correctness of the four MAS methods are verified for strategic bidding in electricity markets using reinforcement learning.展开更多
Wire arc additive manufacturing(WAAM)has emerged as a promising approach for fabricating large-scale components.However,conventional WAAM still faces challenges in optimizing microstructural evolution,minimizing addit...Wire arc additive manufacturing(WAAM)has emerged as a promising approach for fabricating large-scale components.However,conventional WAAM still faces challenges in optimizing microstructural evolution,minimizing additive-induced defects,and alleviating residual stress and deformation,all of which are critical for enhancing the mechanical performance of the manufactured parts.Integrating interlayer friction stir processing(FSP)into WAAM significantly enhances the quality of deposited materials.However,numerical simulation research focusing on elucidating the associated thermomechanical coupling mechanisms remains insufficient.A comprehensive numerical model was developed to simulate the thermomechanical coupling behavior in friction stir-assisted WAAM.The influence of post-deposition FSP on the coupled thermomechanical response of the WAAM process was analyzed quantitatively.Moreover,the residual stress distribution and deformation behavior under both single-layer and multilayer deposition conditions were investigated.Thermal analysis of different deposition layers in WAAM and friction stir-assisted WAAM was conducted.Results show that subsequent layer deposition induces partial remelting of the previously solidified layer,whereas FSP does not cause such remelting.Furthermore,thermal stress and deformation analysis confirm that interlayer FSP effectively mitigates residual stresses and distortion in WAAM components,thereby improving their structural integrity and mechanical properties.展开更多
War rehearsals have become increasingly important in national security due to the growing complexity of international affairs.However,traditional rehearsal methods,such as military chess simulations,are inefficient an...War rehearsals have become increasingly important in national security due to the growing complexity of international affairs.However,traditional rehearsal methods,such as military chess simulations,are inefficient and inflexible,with particularly pronounced limitations in command and decision-making.The overwhelming volume of information and high decision complexity hinder the realization of autonomous and agile command and control.To address this challenge,an intelligent warfare simulation framework named Command-Agent is proposed,which deeply integrates large language models(LLMs)with digital twin battlefields.By constructing a highly realistic battlefield environment through real-time simulation and multi-source data fusion,the natural language interaction capabilities of LLMs are leveraged to lower the command threshold and to enable autonomous command through the Observe-Orient-Decide-Act(OODA)feedback loop.Within the Command-Agent framework,a multimodel collaborative architecture is further adopted to decouple the decision-generation and command-execution functions of LLMs.By combining specialized models such as Deep Seek-R1 and MCTool,the limitations of single-model capabilities are overcome.MCTool is a lightweight execution model fine-tuned for military Function Calling tasks.The framework also introduces a Vector Knowledge Base to mitigate hallucinations commonly exhibited by LLMs.Experimental results demonstrate that Command-Agent not only enables natural language-driven simulation and control but also deeply understands commander intent.Leveraging the multi-model collaborative architecture,during red-blue UAV confrontations involving 2 to 8 UAVs,the integrated score is improved by an average of 41.8%compared to the single-agent system(MCTool),accompanied by a 161.8%optimization in the battle loss ratio.Furthermore,when compared with multi-agent systems lacking the knowledge base,the inclusion of the Vector Knowledge Base further improves overall performance by 16.8%.In comparison with the general model(Qwen2.5-7B),the fine-tuned MCTool leads by 5%in execution efficiency.Therefore,the proposed Command-Agent introduces a novel perspective to the military command system and offers a feasible solution for intelligent battlefield decision-making.展开更多
This paper focuses on the leader-following positive consensus problems of heterogeneous switched multi-agent systems.First,a state-feedback controller with dynamic compensation is introduced to achieve positive consen...This paper focuses on the leader-following positive consensus problems of heterogeneous switched multi-agent systems.First,a state-feedback controller with dynamic compensation is introduced to achieve positive consensus under average dwell time switching.Then sufficient conditions are derived to guarantee the positive consensus.The gain matrices of the control protocol are described using a matrix decomposition approach and the corresponding computational complexity is reduced by resorting to linear programming and co-positive Lyapunov functions.Finally,two numerical examples are provided to illustrate the results obtained.展开更多
With the advent of sixth-generation mobile communications(6G),space-air-ground integrated networks have become mainstream.This paper focuses on collaborative scheduling for mobile edge computing(MEC)under a three-tier...With the advent of sixth-generation mobile communications(6G),space-air-ground integrated networks have become mainstream.This paper focuses on collaborative scheduling for mobile edge computing(MEC)under a three-tier heterogeneous architecture composed of mobile devices,unmanned aerial vehicles(UAVs),and macro base stations(BSs).This scenario typically faces fast channel fading,dynamic computational loads,and energy constraints,whereas classical queuing-theoretic or convex-optimization approaches struggle to yield robust solutions in highly dynamic settings.To address this issue,we formulate a multi-agent Markov decision process(MDP)for an air-ground-fused MEC system,unify link selection,bandwidth/power allocation,and task offloading into a continuous action space and propose a joint scheduling strategy that is based on an improved MATD3 algorithm.The improvements include Alternating Layer Normalization(ALN)in the actor to suppress gradient variance,Residual Orthogonalization(RO)in the critic to reduce the correlation between the twin Q-value estimates,and a dynamic-temperature reward to enable adaptive trade-offs during training.On a multi-user,dual-link simulation platform,we conduct ablation and baseline comparisons.The results reveal that the proposed method has better convergence and stability.Compared with MADDPG,TD3,and DSAC,our algorithm achieves more robust performance across key metrics.展开更多
This paper investigates the consensus tracking control problem for high order nonlinear multi-agent systems subject to non-affine faults,partial measurable states,uncertain control coefficients,and unknown external di...This paper investigates the consensus tracking control problem for high order nonlinear multi-agent systems subject to non-affine faults,partial measurable states,uncertain control coefficients,and unknown external disturbances.Under the directed topology conditions,an observer-based finite-time control strategy based on adaptive backstepping and is proposed,in which a neural network-based state observer is employed to approximate the unmeasurable system state variables.To address the complexity explosion problem associated with the backstepping method,a finite-time command filter is incorporated,with error compensation signals designed to mitigate the filter-induced errors.Additionally,the Butterworth low-pass filter is introduced to avoid the algebraic ring problem in the design of the controller.The finite-time stability of the closed-loop system is rigorously analyzed with the finite-time Lyapunov stability criterion,validating that all closed-loop signals of the system remain bounded within a finite time.Finally,the effectiveness of the proposed control strategy is verified through a simulation example.展开更多
Addressing optimal confrontation methods in multi-agent attack-defense scenarios is a complex challenge.Multi-Agent Reinforcement Learning(MARL)provides an effective framework for tackling sequential decision-making p...Addressing optimal confrontation methods in multi-agent attack-defense scenarios is a complex challenge.Multi-Agent Reinforcement Learning(MARL)provides an effective framework for tackling sequential decision-making problems,significantly enhancing swarm intelligence in maneuvering.However,applying MARL to unmanned swarms presents two primary challenges.First,defensive agents must balance autonomy with collaboration under limited perception while coordinating against adversaries.Second,current algorithms aim to maximize global or individual rewards,making them sensitive to fluctuations in enemy strategies and environmental changes,especially when rewards are sparse.To tackle these issues,we propose an algorithm of MultiAgent Reinforcement Learning with Layered Autonomy and Collaboration(MARL-LAC)for collaborative confrontations.This algorithm integrates dual twin Critics to mitigate the high variance associated with policy gradients.Furthermore,MARL-LAC employs layered autonomy and collaboration to address multi-objective problems,specifically learning a global reward function for the swarm alongside local reward functions for individual defensive agents.Experimental results demonstrate that MARL-LAC enhances decision-making and collaborative behaviors among agents,outperforming the existing algorithms and emphasizing the importance of layered autonomy and collaboration in multi-agent systems.The observed adversarial behaviors demonstrate that agents using MARL-LAC effectively maintain cohesive formations that conceal their intentions by confusing the offensive agent while successfully encircling the target.展开更多
Atomistic simulations were adopted to study the solute segregation effect on dislocation transmutation across the{1012}twin boundaries in magnesium.For pure magnesium,the dislocation-twin reaction resulted in the form...Atomistic simulations were adopted to study the solute segregation effect on dislocation transmutation across the{1012}twin boundaries in magnesium.For pure magnesium,the dislocation-twin reaction resulted in the formation of sessile dislocations accompanied by the fast migration of the twin boundary,and no〈c+a〉dislocation occurred.With Al segregation,instead,two basal dislocations transmuted into one prismatic〈c+a〉dislocation in the twin.Twin migration was significantly impeded,and the resultant twin disconnections stayed localized and had a higher step character than in pure Mg.To reveal the mechanism of the effect of solute segregation,the Peierls barriers of twin disconnections were calculated,and the dynamic evolutions of twin disconnection dipoles were simulated.The results suggested that Al segregation softened the Peierls barrier of twin disconnections but imposed a high pinning force on twin disconnections,thus attenuating their mobility.Moreover,given the same Al segregation,the twin disconnection dipole with a higher step showed greater stability,which explained the presence of localized twin disconnections with a higher step in the cases with Al segregation than in pure magnesium.The solute segregation induced low mobility of twin disconnections contributed to the occurrence of〈c+a〉dislocations.展开更多
Multimodal dialogue systems often fail to maintain coherent reasoning over extended conversations and suffer from hallucination due to limited context modeling capabilities.Current approaches struggle with crossmodal ...Multimodal dialogue systems often fail to maintain coherent reasoning over extended conversations and suffer from hallucination due to limited context modeling capabilities.Current approaches struggle with crossmodal alignment,temporal consistency,and robust handling of noisy or incomplete inputs across multiple modalities.We propose Multi Agent-Chain of Thought(CoT),a novel multi-agent chain-of-thought reasoning framework where specialized agents for text,vision,and speech modalities collaboratively construct shared reasoning traces through inter-agent message passing and consensus voting mechanisms.Our architecture incorporates self-reflection modules,conflict resolution protocols,and dynamic rationale alignment to enhance consistency,factual accuracy,and user engagement.The framework employs a hierarchical attention mechanism with cross-modal fusion and implements adaptive reasoning depth based on dialogue complexity.Comprehensive evaluations on Situated Interactive Multi-Modal Conversations(SIMMC)2.0,VisDial v1.0,and newly introduced challenging scenarios demonstrate statistically significant improvements in grounding accuracy(p<0.01),chain-of-thought interpretability,and robustness to adversarial inputs compared to state-of-the-art monolithic transformer baselines and existing multi-agent approaches.展开更多
The F_(1)-ATPase and V_(1)-ATPase are rotary biomotors.Alignment of their amino acid sequences,which originate from bovine heart mitochondria(1BMF)and Enterococcus hirae(3VR6),respectively,demonstrates that the segmen...The F_(1)-ATPase and V_(1)-ATPase are rotary biomotors.Alignment of their amino acid sequences,which originate from bovine heart mitochondria(1BMF)and Enterococcus hirae(3VR6),respectively,demonstrates that the segment forming the ATP catalytic pocket is highly conserved.Single-molecule experiments,however,have revealed subtle differences in efficiency between the F_(1) and V_(1) motors.Here,we perform both atomistic and coarse-grained molecular dynamics simulations to investigate the mechanochemical coupling and coordination in F_(1) and V_(1) ATPase.Our results show that the correlation between conformational changes in F_(1) is stronger than that in V_(1),indicating that the mechanochemical coupling in F_(1) is tighter than in V_(1).Moreover,the unidirectional rotation of F_(1) is more processive than that of V_(1),which accounts for the higher efficiency observed in F_(1) and explains the occasional backward steps detected in single-molecule experiments on V_(1).展开更多
The rapid advancement of machine learning based tight-binding Hamiltonian(MLTB)methods has opened new avenues for efficient and accurate electronic structure simulations,particularly in large-scale systems and long-ti...The rapid advancement of machine learning based tight-binding Hamiltonian(MLTB)methods has opened new avenues for efficient and accurate electronic structure simulations,particularly in large-scale systems and long-time scenarios.This review begins with a concise overview of traditional tight-binding(TB)models,including both(semi-)empirical and first-principles approaches,establishing the foundation for understanding MLTB developments.We then present a systematic classification of existing MLTB methodologies,grouped into two major categories:direct prediction of TB Hamiltonian elements and inference of empirical parameters.A comparative analysis with other ML-based electronic structure models is also provided,highlighting the advancement of MLTB approaches.Finally,we explore the emerging MLTB application ecosystem,highlighting how the integration of MLTB models with a diverse suite of post-processing tools from linear-scaling solvers to quantum transport frameworks and molecular dynamics interfaces is essential for tackling complex scientific problems across different domains.The continued advancement of this integrated paradigm promises to accelerate materials discovery and open new frontiers in the predictive simulation of complex quantum phenomena.展开更多
基金supported by the National Natural Science Foundation of China(7157105771390522)the Key Lab for Public Engineering Audit of Jiangsu Province,Nanjing Audit University(GGSS2016-08)
文摘Different from the organization structure of complex projects in Western countries, the Liang Zong hierarchical organization structure of complex projects in China has two different chains, the chief-engineer chain and the general-director chain,to handle the trade-off between technical and management decisions. However, previous works on organization search have mainly focused on the single-chain hierarchical organization in which all decisions are regarded as homogeneous. The heterogeneity and the interdependency between technical decisions and management decisions have been neglected. A two-chain hierarchical organization structure mapped from a real complex project is constructed. Then, a discrete decision model for a Liang Zong two-chain hierarchical organization in an NK model framework is proposed. This model proves that this kind of organization structure can reduce the search space by a large amount and that the search process should reach a final stable state more quickly. For a more complicated decision mechanism, a multi-agent simulation based on the above NK model is used to explore the effect of the two-chain organization structure on the speed, stability, and performance of the search process. The results provide three insights into how, compared with the single-chain hierarchical organization, the two-chain organization can improve the search process: it can reduce the number of iterations efficiently; the search is more stable because the search space is a smoother hill-like fitness landscape; in general, the search performance can be improved.However, when the organization structure is very complicated, the performance of a two-chain organization is inferior to that of a single-chain organization. These findings about the efficiency of the unique Chinese-style organization structure can be used to guide organization design for complex projects.
文摘In this study, we develop a mixed reality game system to investigate characteristics ofjudgrnents of individual players in an evacuation process. The characteristics of judgments of the players that are inferred from the performance of the game are then incorporated into a multi-agent simulation as rules. The behavior of evacuees is evaluated in approximations of real situations, by using the agent simulation including different judgments of evacuees. Using the results of the simulation, effective methods are discussed for achieving the escape of the evacuees within a short time.
文摘The prediction of the behavior of people in a disaster has a useful role to play in the design of urban structures such as department stores, schools, and office buildings. We focus on using emergency exit signs to effectively guide the evacuation of people on a floor with a dynamically changing layout. A multi-agent simulation is developed to simulate the behavior of evacuees on a floor. A mathematical model is constructed to obtain optimal sign locations to efficiently assist evacuation under the condition that obstacles are dynamically generated on the floor. The optimal sign locations are calculated by the mathematical model. Then, the developed simulation is performed to evaluate the effectiveness of the emergency exit signs and the behavior of evacuees on simple layout models using the calculated optimal sign locations.
基金This work was financially supported by Russian Science Foundation with co-financing of Bank Saint Petersburg[Agreement#17-71-30029].
文摘When arranging the pedestrian infrastructure,one of the most important components that make a tangible contribution to the safety of pedestrians is to organize the safe road crossing.In cities,pedestrians often cross a road in the wrong place due to established routes or inadequate location of crosswalks.Accidents with the participation of pedestrians who crossed the road neglecting the traffic rules,make up a significant part of the total amount of road accidents.In this paper,we propose a method that allows us,on the basis of the results of a computer simulation of pedestrian traffic,to obtain predicted routes for road crossing and to indicate optimal locations for crosswalks that take into account established pedestrian routes and increase their safety.The work describes an extension for the existing AntRoadPlanner simulation algorithm,which searches for and clusters points where pedestrians cross the roadway and suggests locations for new crosswalks.This method was tested on the basis of a comparative simulation of several territories before and after its application,as well as on the basis of a field study of the territories.The developed algorithm can also be used to search for other potentially dangerous places for pedestrians on plans of districts,for example,crossings in places with limited visibility.
基金Aeronautical Science Foundation of China (2006ZA51004)
文摘With the aid of multi-agent based modeling approach to complex systems, the hierarchy simulation models of carrier-based aircraft catapult launch are developed. Ocean, carrier, aircraft, and atmosphere are treated as aggregation agents, the detailed components like catapult, landing gears, and disturbances are considered as meta-agents, which belong to their aggregation agent. Thus, the model with two layers is formed i.e. the aggregation agent layer and the meta-agent layer. The information communication among all agents is described. The meta-agents within one aggregation agent communicate with each other directly by information sharing, but the meta-agents, which belong to different aggregation agents exchange their information through the aggregation layer first, and then perceive it from the sharing environment, that is the aggregation agent. Thus, not only the hierarchy model is built, but also the environment perceived by each agent is specified. Meanwhile, the problem of balancing the independency of agent and the resource consumption brought by real-time communication within multi-agent system （MAS） is resolved. Each agent involved in carrier-based aircraft catapult launch is depicted, with considering the interaction within disturbed atmospheric environment and multiple motion bodies including carrier, aircraft, and landing gears. The models of reactive agents among them are derived based on tensors, and the perceived messages and inner frameworks of each agent are characterized. Finally, some results of a simulation instance are given. The simulation and modeling of dynamic system based on multi-agent system is of benefit to express physical concepts and logical hierarchy clearly and precisely. The system model can easily draw in kinds of other agents to achieve a precise simulation of more complex system. This modeling technique makes the complex integral dynamic equations of multibodies decompose into parallel operations of single agent, and it is convenient to expand, maintain, and reuse the program codes.
基金supported by the National Key Research and Development Program of China(2016YFB0901104)。
文摘In this paper,a theoretical framework of Multiagent Simulation(MAS)is proposed for strategic bidding in electricity markets using reinforcement learning,which consists of two parts:one is a MAS system used to simulate the competitive bidding of the actual electricity market;the other is an adaptive learning strategy bidding system used to provide agents with more intelligent bidding strategies.An ExperienceWeighted Attraction(EWA)reinforcement learning algorithm(RLA)is applied to the MAS model and a new MAS method is presented for strategic bidding in electricity markets using a new Improved EWA(IEWA).From both qualitative and quantitative perspectives,it is compared with three other MAS methods using the Roth-Erev(RE),Q-learning and EWA.The results show that the performance of the MAS method using IEWA is proved to be better than the others.The four MAS models using four RLAs are built for strategic bidding in electricity markets.Through running the four MAS models,the rationality and correctness of the four MAS methods are verified for strategic bidding in electricity markets using reinforcement learning.
基金National Key Research and Development Program of China(2022YFB4600902)Shandong Provincial Science Foundation for Outstanding Young Scholars(ZR2024YQ020)。
文摘Wire arc additive manufacturing(WAAM)has emerged as a promising approach for fabricating large-scale components.However,conventional WAAM still faces challenges in optimizing microstructural evolution,minimizing additive-induced defects,and alleviating residual stress and deformation,all of which are critical for enhancing the mechanical performance of the manufactured parts.Integrating interlayer friction stir processing(FSP)into WAAM significantly enhances the quality of deposited materials.However,numerical simulation research focusing on elucidating the associated thermomechanical coupling mechanisms remains insufficient.A comprehensive numerical model was developed to simulate the thermomechanical coupling behavior in friction stir-assisted WAAM.The influence of post-deposition FSP on the coupled thermomechanical response of the WAAM process was analyzed quantitatively.Moreover,the residual stress distribution and deformation behavior under both single-layer and multilayer deposition conditions were investigated.Thermal analysis of different deposition layers in WAAM and friction stir-assisted WAAM was conducted.Results show that subsequent layer deposition induces partial remelting of the previously solidified layer,whereas FSP does not cause such remelting.Furthermore,thermal stress and deformation analysis confirm that interlayer FSP effectively mitigates residual stresses and distortion in WAAM components,thereby improving their structural integrity and mechanical properties.
文摘War rehearsals have become increasingly important in national security due to the growing complexity of international affairs.However,traditional rehearsal methods,such as military chess simulations,are inefficient and inflexible,with particularly pronounced limitations in command and decision-making.The overwhelming volume of information and high decision complexity hinder the realization of autonomous and agile command and control.To address this challenge,an intelligent warfare simulation framework named Command-Agent is proposed,which deeply integrates large language models(LLMs)with digital twin battlefields.By constructing a highly realistic battlefield environment through real-time simulation and multi-source data fusion,the natural language interaction capabilities of LLMs are leveraged to lower the command threshold and to enable autonomous command through the Observe-Orient-Decide-Act(OODA)feedback loop.Within the Command-Agent framework,a multimodel collaborative architecture is further adopted to decouple the decision-generation and command-execution functions of LLMs.By combining specialized models such as Deep Seek-R1 and MCTool,the limitations of single-model capabilities are overcome.MCTool is a lightweight execution model fine-tuned for military Function Calling tasks.The framework also introduces a Vector Knowledge Base to mitigate hallucinations commonly exhibited by LLMs.Experimental results demonstrate that Command-Agent not only enables natural language-driven simulation and control but also deeply understands commander intent.Leveraging the multi-model collaborative architecture,during red-blue UAV confrontations involving 2 to 8 UAVs,the integrated score is improved by an average of 41.8%compared to the single-agent system(MCTool),accompanied by a 161.8%optimization in the battle loss ratio.Furthermore,when compared with multi-agent systems lacking the knowledge base,the inclusion of the Vector Knowledge Base further improves overall performance by 16.8%.In comparison with the general model(Qwen2.5-7B),the fine-tuned MCTool leads by 5%in execution efficiency.Therefore,the proposed Command-Agent introduces a novel perspective to the military command system and offers a feasible solution for intelligent battlefield decision-making.
基金supported by the National Natural Science Foundation of China(62463007,62463005)the Natural Science Foundation of Hainan Province(625RC710,625MS047)+1 种基金the System Control and Information Processing Education Ministry Key Laboratory Open Funding,China(Scip20240119)the Science Research Funding of Hainan University,China(KYQD(ZR)22180,KYQD(ZR)23180).
文摘This paper focuses on the leader-following positive consensus problems of heterogeneous switched multi-agent systems.First,a state-feedback controller with dynamic compensation is introduced to achieve positive consensus under average dwell time switching.Then sufficient conditions are derived to guarantee the positive consensus.The gain matrices of the control protocol are described using a matrix decomposition approach and the corresponding computational complexity is reduced by resorting to linear programming and co-positive Lyapunov functions.Finally,two numerical examples are provided to illustrate the results obtained.
文摘With the advent of sixth-generation mobile communications(6G),space-air-ground integrated networks have become mainstream.This paper focuses on collaborative scheduling for mobile edge computing(MEC)under a three-tier heterogeneous architecture composed of mobile devices,unmanned aerial vehicles(UAVs),and macro base stations(BSs).This scenario typically faces fast channel fading,dynamic computational loads,and energy constraints,whereas classical queuing-theoretic or convex-optimization approaches struggle to yield robust solutions in highly dynamic settings.To address this issue,we formulate a multi-agent Markov decision process(MDP)for an air-ground-fused MEC system,unify link selection,bandwidth/power allocation,and task offloading into a continuous action space and propose a joint scheduling strategy that is based on an improved MATD3 algorithm.The improvements include Alternating Layer Normalization(ALN)in the actor to suppress gradient variance,Residual Orthogonalization(RO)in the critic to reduce the correlation between the twin Q-value estimates,and a dynamic-temperature reward to enable adaptive trade-offs during training.On a multi-user,dual-link simulation platform,we conduct ablation and baseline comparisons.The results reveal that the proposed method has better convergence and stability.Compared with MADDPG,TD3,and DSAC,our algorithm achieves more robust performance across key metrics.
基金supported in part by the Beijing Natural Science Foundation under Grant 4252050in part by the National Science Fund for Distinguished Young Scholars under Grant 62425304in part by the Basic Science Center Programs of NSFC under Grant 62088101.
文摘This paper investigates the consensus tracking control problem for high order nonlinear multi-agent systems subject to non-affine faults,partial measurable states,uncertain control coefficients,and unknown external disturbances.Under the directed topology conditions,an observer-based finite-time control strategy based on adaptive backstepping and is proposed,in which a neural network-based state observer is employed to approximate the unmeasurable system state variables.To address the complexity explosion problem associated with the backstepping method,a finite-time command filter is incorporated,with error compensation signals designed to mitigate the filter-induced errors.Additionally,the Butterworth low-pass filter is introduced to avoid the algebraic ring problem in the design of the controller.The finite-time stability of the closed-loop system is rigorously analyzed with the finite-time Lyapunov stability criterion,validating that all closed-loop signals of the system remain bounded within a finite time.Finally,the effectiveness of the proposed control strategy is verified through a simulation example.
基金co-supported by the National Natural Science Foundation of China(Nos.72371052 and 71871042).
文摘Addressing optimal confrontation methods in multi-agent attack-defense scenarios is a complex challenge.Multi-Agent Reinforcement Learning(MARL)provides an effective framework for tackling sequential decision-making problems,significantly enhancing swarm intelligence in maneuvering.However,applying MARL to unmanned swarms presents two primary challenges.First,defensive agents must balance autonomy with collaboration under limited perception while coordinating against adversaries.Second,current algorithms aim to maximize global or individual rewards,making them sensitive to fluctuations in enemy strategies and environmental changes,especially when rewards are sparse.To tackle these issues,we propose an algorithm of MultiAgent Reinforcement Learning with Layered Autonomy and Collaboration(MARL-LAC)for collaborative confrontations.This algorithm integrates dual twin Critics to mitigate the high variance associated with policy gradients.Furthermore,MARL-LAC employs layered autonomy and collaboration to address multi-objective problems,specifically learning a global reward function for the swarm alongside local reward functions for individual defensive agents.Experimental results demonstrate that MARL-LAC enhances decision-making and collaborative behaviors among agents,outperforming the existing algorithms and emphasizing the importance of layered autonomy and collaboration in multi-agent systems.The observed adversarial behaviors demonstrate that agents using MARL-LAC effectively maintain cohesive formations that conceal their intentions by confusing the offensive agent while successfully encircling the target.
基金supported by the National Natural Science Foundation of China(52071039 and 52301156)National Natural Science Foundation of Jiangsu Province of China(BK20241873)Natural Science Foundation of Jiangsu Province(BK20232025 and BK20243005)are greatly acknowledged.
文摘Atomistic simulations were adopted to study the solute segregation effect on dislocation transmutation across the{1012}twin boundaries in magnesium.For pure magnesium,the dislocation-twin reaction resulted in the formation of sessile dislocations accompanied by the fast migration of the twin boundary,and no〈c+a〉dislocation occurred.With Al segregation,instead,two basal dislocations transmuted into one prismatic〈c+a〉dislocation in the twin.Twin migration was significantly impeded,and the resultant twin disconnections stayed localized and had a higher step character than in pure Mg.To reveal the mechanism of the effect of solute segregation,the Peierls barriers of twin disconnections were calculated,and the dynamic evolutions of twin disconnection dipoles were simulated.The results suggested that Al segregation softened the Peierls barrier of twin disconnections but imposed a high pinning force on twin disconnections,thus attenuating their mobility.Moreover,given the same Al segregation,the twin disconnection dipole with a higher step showed greater stability,which explained the presence of localized twin disconnections with a higher step in the cases with Al segregation than in pure magnesium.The solute segregation induced low mobility of twin disconnections contributed to the occurrence of〈c+a〉dislocations.
文摘Multimodal dialogue systems often fail to maintain coherent reasoning over extended conversations and suffer from hallucination due to limited context modeling capabilities.Current approaches struggle with crossmodal alignment,temporal consistency,and robust handling of noisy or incomplete inputs across multiple modalities.We propose Multi Agent-Chain of Thought(CoT),a novel multi-agent chain-of-thought reasoning framework where specialized agents for text,vision,and speech modalities collaboratively construct shared reasoning traces through inter-agent message passing and consensus voting mechanisms.Our architecture incorporates self-reflection modules,conflict resolution protocols,and dynamic rationale alignment to enhance consistency,factual accuracy,and user engagement.The framework employs a hierarchical attention mechanism with cross-modal fusion and implements adaptive reasoning depth based on dialogue complexity.Comprehensive evaluations on Situated Interactive Multi-Modal Conversations(SIMMC)2.0,VisDial v1.0,and newly introduced challenging scenarios demonstrate statistically significant improvements in grounding accuracy(p<0.01),chain-of-thought interpretability,and robustness to adversarial inputs compared to state-of-the-art monolithic transformer baselines and existing multi-agent approaches.
基金supported by the National Natural Science Foundation of China(Grant Nos.22193032 and 32401033)the Research Fund of Wenzhou Institute,Chinese Academy of Sciences(Grant Nos.WIUCASQD2020009,WIUCASQD2023005,XSZD2024004,2021HZSY0061,and WIUCASICTP2022)。
文摘The F_(1)-ATPase and V_(1)-ATPase are rotary biomotors.Alignment of their amino acid sequences,which originate from bovine heart mitochondria(1BMF)and Enterococcus hirae(3VR6),respectively,demonstrates that the segment forming the ATP catalytic pocket is highly conserved.Single-molecule experiments,however,have revealed subtle differences in efficiency between the F_(1) and V_(1) motors.Here,we perform both atomistic and coarse-grained molecular dynamics simulations to investigate the mechanochemical coupling and coordination in F_(1) and V_(1) ATPase.Our results show that the correlation between conformational changes in F_(1) is stronger than that in V_(1),indicating that the mechanochemical coupling in F_(1) is tighter than in V_(1).Moreover,the unidirectional rotation of F_(1) is more processive than that of V_(1),which accounts for the higher efficiency observed in F_(1) and explains the occasional backward steps detected in single-molecule experiments on V_(1).
基金supported by the Advanced Materials-National Science and Technology Major Project(Grant No.2025ZD0618401)the National Natural Science Foundation of China(Grant No.12504285)+1 种基金the Natural Science Foundation of Jiangsu Province(Grant No.BK20250472)NFSG grant from BITS-Pilani,Dubai campus。
文摘The rapid advancement of machine learning based tight-binding Hamiltonian(MLTB)methods has opened new avenues for efficient and accurate electronic structure simulations,particularly in large-scale systems and long-time scenarios.This review begins with a concise overview of traditional tight-binding(TB)models,including both(semi-)empirical and first-principles approaches,establishing the foundation for understanding MLTB developments.We then present a systematic classification of existing MLTB methodologies,grouped into two major categories:direct prediction of TB Hamiltonian elements and inference of empirical parameters.A comparative analysis with other ML-based electronic structure models is also provided,highlighting the advancement of MLTB approaches.Finally,we explore the emerging MLTB application ecosystem,highlighting how the integration of MLTB models with a diverse suite of post-processing tools from linear-scaling solvers to quantum transport frameworks and molecular dynamics interfaces is essential for tackling complex scientific problems across different domains.The continued advancement of this integrated paradigm promises to accelerate materials discovery and open new frontiers in the predictive simulation of complex quantum phenomena.
