A mixed adaptive dynamic programming(ADP)scheme based on zero-sum game theory is developed to address optimal control problems of autonomous underwater vehicle(AUV)systems subject to disturbances and safe constraints....A mixed adaptive dynamic programming(ADP)scheme based on zero-sum game theory is developed to address optimal control problems of autonomous underwater vehicle(AUV)systems subject to disturbances and safe constraints.By combining prior dynamic knowledge and actual sampled data,the proposed approach effectively mitigates the defect caused by the inaccurate dynamic model and significantly improves the training speed of the ADP algorithm.Initially,the dataset is enriched with sufficient reference data collected based on a nominal model without considering modelling bias.Also,the control object interacts with the real environment and continuously gathers adequate sampled data in the dataset.To comprehensively leverage the advantages of model-based and model-free methods during training,an adaptive tuning factor is introduced based on the dataset that possesses model-referenced information and conforms to the distribution of the real-world environment,which balances the influence of model-based control law and data-driven policy gradient on the direction of policy improvement.As a result,the proposed approach accelerates the learning speed compared to data-driven methods,concurrently also enhancing the tracking performance in comparison to model-based control methods.Moreover,the optimal control problem under disturbances is formulated as a zero-sum game,and the actor-critic-disturbance framework is introduced to approximate the optimal control input,cost function,and disturbance policy,respectively.Furthermore,the convergence property of the proposed algorithm based on the value iteration method is analysed.Finally,an example of AUV path following based on the improved line-of-sight guidance is presented to demonstrate the effectiveness of the proposed method.展开更多
Based on the construction of the 8-inch fabricat ion line, advanced process technology of 8-inch wafer, as well as the fourth-generation high-voltage double-diffused metal-oxide semiconductor(DMOS+) insulated-gate bip...Based on the construction of the 8-inch fabricat ion line, advanced process technology of 8-inch wafer, as well as the fourth-generation high-voltage double-diffused metal-oxide semiconductor(DMOS+) insulated-gate bipolar transistor(IGBT) technology and the fifth-generation trench gate IGBT technology, have been developed, realizing a great-leap forward technological development for the manufacturing of high-voltage IGBT from 6-inch to 8-inch. The 1600 A/1.7 kV and 1500 A/3.3 kV IGBT modules have been successfully fabricated, qualified, and applied in rail transportation traction system.展开更多
ln order to deal with the problems of insufficient or excessive maintenance in the current maintenance activities of China transit trains,this paper develops a novel multi-component system maintenance optimization app...ln order to deal with the problems of insufficient or excessive maintenance in the current maintenance activities of China transit trains,this paper develops a novel multi-component system maintenance optimization approach based on an opportunistic correlation model.Based on the minimal reliability and failure rate change rule of each train component,the novel proposed maintenance optimization benefits from an improved opportunistic maintenance model with system structure correlation,fault correlation and reliability correlation under imperfect maintenance.Then,different maintenance modes can be determined by a proposed mainte-nance factor under the different conditions of components.Specifically,the reliability threshold of each component is also considered to optimize the maintenance cost by the system reliability and operational availability of the train.Furthermore,as the mentioned problem belongs to the NP-Hard optimization problems,a modified particle swarm optimization(PSO)with the improvement of inertia weight is proposed to cope with the optimization problem.Based on a specific case under the practical recorded failure data,the analysis shows that the proposed model and approach can effectively cut the maintenance cost.展开更多
Transmission machinery is widely used in railway vehicles and is an important component in driving the operation of trains.Such transmission components are prone to faults under long exposure to harsh environments and...Transmission machinery is widely used in railway vehicles and is an important component in driving the operation of trains.Such transmission components are prone to faults under long exposure to harsh environments and complex working conditions.This affects normal operation and order,and thus it is important to ensure their safe and reliable operation.Electrical signal-based diagnosis technology has advantages of easy signal acquisition,with no need to install additional sensors,nor embedded monitoring of the object components.It has gradually become a research hotspot in the field of rail transportation diagnosis.This paper describes the fault modes of transmission machinery,takes the electrical signal-based diagnosis method as the entry point,collates and compares the existing diagnosis methods and research results in this field.It analyses their advantages and disadvantages,and finally puts forward problems for current and future research and development.展开更多
基金National Key Research and Development Program of China,Grant/Award Number:2021YFC2801700Defense Industrial Technology Development Program,Grant/Award Numbers:JCKY2021110B024,JCKY2022110C072+6 种基金Science and Technology Innovation 2030-“New Generation Artificial Intelligence”Major Project,Grant/Award Number:2022ZD0116305Natural Science Foundation of Hefei,China,Grant/Award Number:202321National Natural Science Foundation of China,Grant/Award Numbers:U2013601,U20A20225Yangtze River Delta S&T Innovation Community Joint Research Project,Grant/Award Number:2022CSJGG0900Anhui Province Natural Science Funds for Distinguished Young Scholar,Grant/Award Number:2308085J02State Key Laboratory of Intelligent Green Vehicle and Mobility,Grant/Award Number:KFY2417State Key Laboratory of Advanced Design and Manufacturing Technology for Vehicle,Grant/Award Number:32215010。
文摘A mixed adaptive dynamic programming(ADP)scheme based on zero-sum game theory is developed to address optimal control problems of autonomous underwater vehicle(AUV)systems subject to disturbances and safe constraints.By combining prior dynamic knowledge and actual sampled data,the proposed approach effectively mitigates the defect caused by the inaccurate dynamic model and significantly improves the training speed of the ADP algorithm.Initially,the dataset is enriched with sufficient reference data collected based on a nominal model without considering modelling bias.Also,the control object interacts with the real environment and continuously gathers adequate sampled data in the dataset.To comprehensively leverage the advantages of model-based and model-free methods during training,an adaptive tuning factor is introduced based on the dataset that possesses model-referenced information and conforms to the distribution of the real-world environment,which balances the influence of model-based control law and data-driven policy gradient on the direction of policy improvement.As a result,the proposed approach accelerates the learning speed compared to data-driven methods,concurrently also enhancing the tracking performance in comparison to model-based control methods.Moreover,the optimal control problem under disturbances is formulated as a zero-sum game,and the actor-critic-disturbance framework is introduced to approximate the optimal control input,cost function,and disturbance policy,respectively.Furthermore,the convergence property of the proposed algorithm based on the value iteration method is analysed.Finally,an example of AUV path following based on the improved line-of-sight guidance is presented to demonstrate the effectiveness of the proposed method.
文摘Based on the construction of the 8-inch fabricat ion line, advanced process technology of 8-inch wafer, as well as the fourth-generation high-voltage double-diffused metal-oxide semiconductor(DMOS+) insulated-gate bipolar transistor(IGBT) technology and the fifth-generation trench gate IGBT technology, have been developed, realizing a great-leap forward technological development for the manufacturing of high-voltage IGBT from 6-inch to 8-inch. The 1600 A/1.7 kV and 1500 A/3.3 kV IGBT modules have been successfully fabricated, qualified, and applied in rail transportation traction system.
基金funded by the Hunan Science and Technology‘Lotus Bud’Talent Support Program(Gr ant No.2022TJ-XH-009).
文摘ln order to deal with the problems of insufficient or excessive maintenance in the current maintenance activities of China transit trains,this paper develops a novel multi-component system maintenance optimization approach based on an opportunistic correlation model.Based on the minimal reliability and failure rate change rule of each train component,the novel proposed maintenance optimization benefits from an improved opportunistic maintenance model with system structure correlation,fault correlation and reliability correlation under imperfect maintenance.Then,different maintenance modes can be determined by a proposed mainte-nance factor under the different conditions of components.Specifically,the reliability threshold of each component is also considered to optimize the maintenance cost by the system reliability and operational availability of the train.Furthermore,as the mentioned problem belongs to the NP-Hard optimization problems,a modified particle swarm optimization(PSO)with the improvement of inertia weight is proposed to cope with the optimization problem.Based on a specific case under the practical recorded failure data,the analysis shows that the proposed model and approach can effectively cut the maintenance cost.
文摘Transmission machinery is widely used in railway vehicles and is an important component in driving the operation of trains.Such transmission components are prone to faults under long exposure to harsh environments and complex working conditions.This affects normal operation and order,and thus it is important to ensure their safe and reliable operation.Electrical signal-based diagnosis technology has advantages of easy signal acquisition,with no need to install additional sensors,nor embedded monitoring of the object components.It has gradually become a research hotspot in the field of rail transportation diagnosis.This paper describes the fault modes of transmission machinery,takes the electrical signal-based diagnosis method as the entry point,collates and compares the existing diagnosis methods and research results in this field.It analyses their advantages and disadvantages,and finally puts forward problems for current and future research and development.
