Batteries transfer management is one important aspect in electric vehicle(EV)network's intelligent operation management system.Batteries transfer is a special and much more complex VRP(Vehicle Routing Problem) whi...Batteries transfer management is one important aspect in electric vehicle(EV)network's intelligent operation management system.Batteries transfer is a special and much more complex VRP(Vehicle Routing Problem) which takes the multiple constraints such as dynamic multi-depots,time windows,simultaneous pickups and deliveries,distance minimization,etc.into account.We call it VRPEVB(VRP with EV Batteries).This paper,based on the intelligent management model of EV's battery power,puts forward a battery transfer algorithm for the EV network which considers the traffic congestion that changes dynamically and uses improved Ant Colony Optimization.By setting a reasonable tabv range,special update rules of the pheromone and path list memory functions,the algorithm can have a better convergence,and its feasibility is proved by the experiment in an EV's demonstration operation system.展开更多
In this paper,a model predictive control(MPC)based on back propagation neural network(BPNN)prediction model was proposed for compressor speed control of air conditioning system(ACS)and battery thermal management syste...In this paper,a model predictive control(MPC)based on back propagation neural network(BPNN)prediction model was proposed for compressor speed control of air conditioning system(ACS)and battery thermal management system(BTMS)coupling system of battery electric vehicle(BEV).In order to solve the problem of high cooling energy consumption and inferior thermal comfort in the cabin of the battery electric vehicle thermal management system(BEVTMS)during summer time,this paper combines the respective superiorities of artificial neural network(ANN)predictive modeling and MPC,and creatively combines the two methods and uses them in the control of BEVTMS.Firstly,based on ANN and heat transfer theory,BPNN prediction model,ACS and BTMS coupling system were established and verified.Secondly,a mathematical method of MPC was established to control the speed of the compressor.Then,the state parameters of the coupled system were predicted using a BPNN prediction model,and the predicted values were passed to the MPC,thus achieving accurate control of the compressor speed using the MPC.Finally,the effects of PID control and MPC based on BPNN prediction model on thermal comfort of cabin and compressor energy consumption at different ambient temperatures were compared in simulation under New European Driving Cycle(NEDC)conditions.The results showed for the constructed BPNN prediction model predicted and tested values of the selected parameters the mean squared error(MSE)ranged from 2.498%to 8.969%,mean absolute percentage error(MAPE)ranged from 4.197%to 8.986%,and mean absolute error(MAE)ranged from 3.202%to 8.476%.At ambient temperatures of 25℃,35℃ and 45℃,the MPC based on the BPNN prediction model reduced the cumulative discomfort time in the cabin by 100 s,39 s and 19 s,respectively,compared with the PID control.Under three NEDC conditions,the energy consumption is reduced by 1.82%,2.35%and 3.48%,respectively.When the ambient temperature was 35℃,the MPC based on BPNN prediction model can make the ACS and BTMS coupling system have better thermal comfort,and the energy saving effect of the compressor was more obvious with the temperature.展开更多
传输通信系统(Media Oriented System Transport,MOST)网络在车载多媒体通信等场合有着广泛的应用,目前针对MOST网络的研究多针对MOST25、MOST50等,而MOST150网络具有带宽高,速率快的优点,适用于车载多媒体通信,但其在车载电控系统中的...传输通信系统(Media Oriented System Transport,MOST)网络在车载多媒体通信等场合有着广泛的应用,目前针对MOST网络的研究多针对MOST25、MOST50等,而MOST150网络具有带宽高,速率快的优点,适用于车载多媒体通信,但其在车载电控系统中的应用较少。为此,本文针对MOST150网络及其功能特点进行了介绍,提出了MOST150网络及CAN-MOST模块在电动汽车用电池管理系统(Battery Management System,BMS)的应用,并进行实验验证,结果表明加入MOST的电池管理系统抗干扰以及复杂环境下的信号长距离传输能力有较大提升。展开更多
基金supported by the 973 Program under Grant No.2011CB302506, 2012CB315802National Key Technology Research and Development Program of China under Grant No.2012BAH94F02+5 种基金The 863 Program under Grant No.2013AA102301NNSF of China under Grant No.61132001, 61170273Program for New Century Excel-lent Talents in University under Grant No. NCET-11-0592Project of New Generation Broad band Wireless Network under Grant No.2014ZX03006003The Technology Development and Experiment of Innovative Network Architecture(CNGI-12-03-007)The Open Fund Project of CAAC InformationTechnology Research Base(CAACITRB-201201)
文摘Batteries transfer management is one important aspect in electric vehicle(EV)network's intelligent operation management system.Batteries transfer is a special and much more complex VRP(Vehicle Routing Problem) which takes the multiple constraints such as dynamic multi-depots,time windows,simultaneous pickups and deliveries,distance minimization,etc.into account.We call it VRPEVB(VRP with EV Batteries).This paper,based on the intelligent management model of EV's battery power,puts forward a battery transfer algorithm for the EV network which considers the traffic congestion that changes dynamically and uses improved Ant Colony Optimization.By setting a reasonable tabv range,special update rules of the pheromone and path list memory functions,the algorithm can have a better convergence,and its feasibility is proved by the experiment in an EV's demonstration operation system.
基金supported by the Natural Science Foundation of Chongqing (Grant No:cstc2021jcyj-msxmX0440)the youth project of science and technology research program of Chongqing Education Commission of China (Grant No:KJQN202301167)+3 种基金the Chongqing Graduate Education Teaching Reform Research Project (Grant No:YJG233120)the Special Major Project of Technological Innovation and Application Development of Chongqing(Grant No:CSTB2022TIAD-STX0002)Chongqing university of technology graduate education quality development action plan funding results-graduate student innovation program (Grant No:gzlcx20232026)the graduate student innovation projects (Grant No:gzlcx20232029)
文摘In this paper,a model predictive control(MPC)based on back propagation neural network(BPNN)prediction model was proposed for compressor speed control of air conditioning system(ACS)and battery thermal management system(BTMS)coupling system of battery electric vehicle(BEV).In order to solve the problem of high cooling energy consumption and inferior thermal comfort in the cabin of the battery electric vehicle thermal management system(BEVTMS)during summer time,this paper combines the respective superiorities of artificial neural network(ANN)predictive modeling and MPC,and creatively combines the two methods and uses them in the control of BEVTMS.Firstly,based on ANN and heat transfer theory,BPNN prediction model,ACS and BTMS coupling system were established and verified.Secondly,a mathematical method of MPC was established to control the speed of the compressor.Then,the state parameters of the coupled system were predicted using a BPNN prediction model,and the predicted values were passed to the MPC,thus achieving accurate control of the compressor speed using the MPC.Finally,the effects of PID control and MPC based on BPNN prediction model on thermal comfort of cabin and compressor energy consumption at different ambient temperatures were compared in simulation under New European Driving Cycle(NEDC)conditions.The results showed for the constructed BPNN prediction model predicted and tested values of the selected parameters the mean squared error(MSE)ranged from 2.498%to 8.969%,mean absolute percentage error(MAPE)ranged from 4.197%to 8.986%,and mean absolute error(MAE)ranged from 3.202%to 8.476%.At ambient temperatures of 25℃,35℃ and 45℃,the MPC based on the BPNN prediction model reduced the cumulative discomfort time in the cabin by 100 s,39 s and 19 s,respectively,compared with the PID control.Under three NEDC conditions,the energy consumption is reduced by 1.82%,2.35%and 3.48%,respectively.When the ambient temperature was 35℃,the MPC based on BPNN prediction model can make the ACS and BTMS coupling system have better thermal comfort,and the energy saving effect of the compressor was more obvious with the temperature.
