Equipment development planning(EDP)is usually a long-term process often performed in an environment with high uncertainty.The traditional multi-stage dynamic programming cannot cope with this kind of uncertainty with ...Equipment development planning(EDP)is usually a long-term process often performed in an environment with high uncertainty.The traditional multi-stage dynamic programming cannot cope with this kind of uncertainty with unpredictable situations.To deal with this problem,a multi-stage EDP model based on a deep reinforcement learning(DRL)algorithm is proposed to respond quickly to any environmental changes within a reasonable range.Firstly,the basic problem of multi-stage EDP is described,and a mathematical planning model is constructed.Then,for two kinds of uncertainties(future capabi lity requirements and the amount of investment in each stage),a corresponding DRL framework is designed to define the environment,state,action,and reward function for multi-stage EDP.After that,the dueling deep Q-network(Dueling DQN)algorithm is used to solve the multi-stage EDP to generate an approximately optimal multi-stage equipment development scheme.Finally,a case of ten kinds of equipment in 100 possible environments,which are randomly generated,is used to test the feasibility and effectiveness of the proposed models.The results show that the algorithm can respond instantaneously in any state of the multistage EDP environment and unlike traditional algorithms,the algorithm does not need to re-optimize the problem for any change in the environment.In addition,the algorithm can flexibly adjust at subsequent planning stages in the event of a change to the equipment capability requirements to adapt to the new requirements.展开更多
Since its establishment about ten years ago, TEDA has taken advantage of eachopportune time created by China’s policy of opening wider and wider to the outsideworld and the rapid economic growth to deepen its reform ...Since its establishment about ten years ago, TEDA has taken advantage of eachopportune time created by China’s policy of opening wider and wider to the outsideworld and the rapid economic growth to deepen its reform and extend its exploitation,and thus has maintained a favorable momentum and an extraordinary high speed foreconomic development. With the total economic output of the whole area raised to展开更多
The system portfolio selection is a fundamental frontier issue in the development planning and demonstration of weapon equipment.The scientific and reasonable development of the weapon system portfolio is of great sig...The system portfolio selection is a fundamental frontier issue in the development planning and demonstration of weapon equipment.The scientific and reasonable development of the weapon system portfolio is of great significance for optimizing the design of equipment architecture,realizing effective resource allocation,and increasing the campaign effectiveness of integrated joint operations.From the perspective of system-ofsystems,this paper proposes a unified framework called structure-oriented weapon system portfolio selection(SWSPS)to solve the weapon system portfolio selection problem based on structural invulnerability.First,the types of equipment and the relationship between the equipment are sorted out based on the operation loop theory,and a heterogeneous combat network model of the weapon equipment system is established by abstracting the equipment and their relationships into different types of nodes and edges respectively.Then,based on the combat network model,the operation loop comprehensive evaluation index(OLCEI)is introduced to quantitatively describe the structural robustness of the combat network.Next,a weapon system combination selection model is established with the goal of maximizing the operation loop comprehensive evaluation index within the constraints of capability requirements and budget limitations.Finally,our proposed SWSPS is demonstrated through a case study of an armored infantry battalion.The results show that our proposed SWSPS can achieve excellent performance in solving the weapon system portfolio selection problem,which yields many meaningful insights and guidance to the future equipment development planning.展开更多
基金supported by the National Natural Science Foundation of China(71690233,72001209)the Scientific Research Foundation of the National University of Defense Technology(ZK19-16)。
文摘Equipment development planning(EDP)is usually a long-term process often performed in an environment with high uncertainty.The traditional multi-stage dynamic programming cannot cope with this kind of uncertainty with unpredictable situations.To deal with this problem,a multi-stage EDP model based on a deep reinforcement learning(DRL)algorithm is proposed to respond quickly to any environmental changes within a reasonable range.Firstly,the basic problem of multi-stage EDP is described,and a mathematical planning model is constructed.Then,for two kinds of uncertainties(future capabi lity requirements and the amount of investment in each stage),a corresponding DRL framework is designed to define the environment,state,action,and reward function for multi-stage EDP.After that,the dueling deep Q-network(Dueling DQN)algorithm is used to solve the multi-stage EDP to generate an approximately optimal multi-stage equipment development scheme.Finally,a case of ten kinds of equipment in 100 possible environments,which are randomly generated,is used to test the feasibility and effectiveness of the proposed models.The results show that the algorithm can respond instantaneously in any state of the multistage EDP environment and unlike traditional algorithms,the algorithm does not need to re-optimize the problem for any change in the environment.In addition,the algorithm can flexibly adjust at subsequent planning stages in the event of a change to the equipment capability requirements to adapt to the new requirements.
文摘Since its establishment about ten years ago, TEDA has taken advantage of eachopportune time created by China’s policy of opening wider and wider to the outsideworld and the rapid economic growth to deepen its reform and extend its exploitation,and thus has maintained a favorable momentum and an extraordinary high speed foreconomic development. With the total economic output of the whole area raised to
基金This work was supported by the National Natural Science Foundation of China(71690233,71971213,71571185)Scientific Research Foundation of National University of Defense Technology(ZK19-16).
文摘The system portfolio selection is a fundamental frontier issue in the development planning and demonstration of weapon equipment.The scientific and reasonable development of the weapon system portfolio is of great significance for optimizing the design of equipment architecture,realizing effective resource allocation,and increasing the campaign effectiveness of integrated joint operations.From the perspective of system-ofsystems,this paper proposes a unified framework called structure-oriented weapon system portfolio selection(SWSPS)to solve the weapon system portfolio selection problem based on structural invulnerability.First,the types of equipment and the relationship between the equipment are sorted out based on the operation loop theory,and a heterogeneous combat network model of the weapon equipment system is established by abstracting the equipment and their relationships into different types of nodes and edges respectively.Then,based on the combat network model,the operation loop comprehensive evaluation index(OLCEI)is introduced to quantitatively describe the structural robustness of the combat network.Next,a weapon system combination selection model is established with the goal of maximizing the operation loop comprehensive evaluation index within the constraints of capability requirements and budget limitations.Finally,our proposed SWSPS is demonstrated through a case study of an armored infantry battalion.The results show that our proposed SWSPS can achieve excellent performance in solving the weapon system portfolio selection problem,which yields many meaningful insights and guidance to the future equipment development planning.
