基于LM-BP神经网络的FlexRay总线系统的预测控制
|
摘要
为了提高汽车高速数据传输总线FlexRay车载网络的控制性能,确保FlexRay总线网络在大负载传输数据时控制系统工作的稳定性,提出一种基于Levenberg-Marquardt(LM)算法神经网络的FlexRay总线预测控制系统的方法。通过采样当前时刻的FlexRay车载网络的工作状态预测下一时刻车载网络的运行状态,以在线自适应调节任务工作量的方式适应车载网络系统中时刻变化的负载,提高FlexRay网络控制系统的可靠性和稳定性。仿真结果表明,LM-BP神经网络预测控制具有很好的自适应性和鲁棒性,有效提高了FlexRay车载网络的安全性和稳定性。
A FlexRay bus predictive control system based on Levenberg-Marquardt(LM)algorithm and neural network is proposed to improve the control performance of the FlexRay vehicle-mounted network with automobile high-speed data transmission bus,and ensure the control system working stability of the FlexRay bus network while data transmitting in large load. The working condition of FlexRay vehicle-mounted network at present moment is sampled to predict the working condition of FlexRay vehicle-mounted network at next moment. The method of online adaptive workload regulation is used to adapt to the time-varying load in vehicle-mounted network system,which can improve the reliability and robustness of the FlexRay vehiclemounted network system. The simulation results show that the LM-BP neural network predictive control has strong adaptability and robustness,and can improve the security and stability of FlexRay vehicle-mounted network effectively.
A FlexRay bus predictive control system based on Levenberg-Marquardt(LM)algorithm and neural network is proposed to improve the control performance of the FlexRay vehicle-mounted network with automobile high-speed data transmission bus,and ensure the control system working stability of the FlexRay bus network while data transmitting in large load. The working condition of FlexRay vehicle-mounted network at present moment is sampled to predict the working condition of FlexRay vehicle-mounted network at next moment. The method of online adaptive workload regulation is used to adapt to the time-varying load in vehicle-mounted network system,which can improve the reliability and robustness of the FlexRay vehiclemounted network system. The simulation results show that the LM-BP neural network predictive control has strong adaptability and robustness,and can improve the security and stability of FlexRay vehicle-mounted network effectively.
引文
[1]赵睿,秦贵和,范铁虎.FlexRay通信协议的总线周期优化[J].计算机应用研究,2010,27(10):3847-3850.ZHAO Rui,QIN Guihe,FAN Tiehu. Bus cycle optimization for FlexRay communication protocol[J]. Application research of computers,2010,27(10):3847-3850.
[2]项欣南.FlexRay总线静态段参数优化及其在线控制动系统中的应用[D].长沙:湖南大学,2016.XIANG Xinnan. FlexRay bus static section parameters optimization and online control system[D]. Changsha:Hunan University,2016.
[3] ZENG H,NATALE D I,GHOSAL M. Schedule optimization of time-triggered systems communicating over the FlexRay static segment[J]. IEEE transactions on industrial informatics,2011,7(1):1-17.
[4] KANG M,PARK K,JEONG M. Frame packing for minimizing the bandwidth consumption of the FlexRay static segment[J].IEEE transactions on industrial electronics, 2013, 60(9):4001-4008.
[5]张峤,邓贵仕.Levenberg-Maequardt神经网络在煤矿作业人员因可靠性评价中的应用研究[J].大连理工大学学报,2015,55(4):424-430.ZHANG Qiao,DENG Guishi. Application of Levenberg-Maequardt neural networks in reliability evaluation of coal mine workers[J]. Journal of Dalian University of Technology,2015,55(4):424-430.
[6]王刚,丁天宝,荣健,等.FlexRay网络中带宽利用率的理论研究[J].计算机应用,2011,31(10):2634-2637.WANG Gang,DING Tianbao,RONG Jian,et al. Study on bandwidth utilization rate in FlexRay networks[J]. Computer applications,2011,31(10):2634-2637.
[7]李斌,龙飞.一种FlexRay总线优化方法研究[J].计算机软件及应用,2015,32(5):142-143.LI Bin,LONG Fei. A FlexRay bus optimization method[J].Computer software and applications,2015,32(5):142-143.
[8]陈晓雷.神经网络自适应控制器仿真研究[D].太原:太原理工大学,2007.CHEN Xiaolei. Neural network adaptive controller simulation[D]. Taiyuan:Taiyuan University of Technology,2007.
[9]王炳萱.LM优化算法和神经网络预测控制在非线性系统中的研究[D].太原:太原理工大学,2016.WANG Bingxuan. Research on LM optimization algorithm and neural network predictive control in nonlinear systems[D]. Taiyuan:Taiyuan University of Technology,2016.
[10]谢嘉乐.基于改进的LM-BP神经网络的车牌识别算法研究与应用[D].广州:广东工业大学,2016.XIE Jiale. Research and application of license plate recognition algorithm based on improved LM-BP neural network[D].Guangzhou:Guangdong University of Technology,2016.
[11]程驰,帅志斌,李建秋,等.车载网络通讯协议FlexRay网络的分析及搭建[J].汽车安全与节能学报,2013,4(1):75-81.CHENG Chi,SHUAI Zhibin,LI Jianqiu,et al. Analysis and construction of vehicle network communication protocol FlexRay network[J]. Journal of automotive safety and energy conservation,2013,4(1):75-81.
[12] JANG K,PARK I,HAN J. Design framework for FlexRay network parameter optimization[J]. International journal of automotive technology,2011,12(4):589-597.
[13]张泽旭.神经网络控制与Matlab仿真[M].哈尔滨:哈尔滨工业大学出版社,2011.ZHANG Zexu. Neural network control and Matlab simulation[M]. Harbin:Harbin Institute of Technology Press,2011.
[14]魏东.非线性系统神经网络参数预测及控制[M].北京:机械工业出版社,2007.WEI Dong. Prediction and control of parameters of nonlinear system neural network[M]. Beijing:Machinery Industry Press,2007.
[15] LIU G Y,XU B G. A real-time scheduling scheme of quantized control systems under bandwidth constraints[C]//Proceedings of the 8th World Congress on Intelligent Control and Automation. Jinan,China:IEEE,2010:2334-2338.
[2]项欣南.FlexRay总线静态段参数优化及其在线控制动系统中的应用[D].长沙:湖南大学,2016.XIANG Xinnan. FlexRay bus static section parameters optimization and online control system[D]. Changsha:Hunan University,2016.
[3] ZENG H,NATALE D I,GHOSAL M. Schedule optimization of time-triggered systems communicating over the FlexRay static segment[J]. IEEE transactions on industrial informatics,2011,7(1):1-17.
[4] KANG M,PARK K,JEONG M. Frame packing for minimizing the bandwidth consumption of the FlexRay static segment[J].IEEE transactions on industrial electronics, 2013, 60(9):4001-4008.
[5]张峤,邓贵仕.Levenberg-Maequardt神经网络在煤矿作业人员因可靠性评价中的应用研究[J].大连理工大学学报,2015,55(4):424-430.ZHANG Qiao,DENG Guishi. Application of Levenberg-Maequardt neural networks in reliability evaluation of coal mine workers[J]. Journal of Dalian University of Technology,2015,55(4):424-430.
[6]王刚,丁天宝,荣健,等.FlexRay网络中带宽利用率的理论研究[J].计算机应用,2011,31(10):2634-2637.WANG Gang,DING Tianbao,RONG Jian,et al. Study on bandwidth utilization rate in FlexRay networks[J]. Computer applications,2011,31(10):2634-2637.
[7]李斌,龙飞.一种FlexRay总线优化方法研究[J].计算机软件及应用,2015,32(5):142-143.LI Bin,LONG Fei. A FlexRay bus optimization method[J].Computer software and applications,2015,32(5):142-143.
[8]陈晓雷.神经网络自适应控制器仿真研究[D].太原:太原理工大学,2007.CHEN Xiaolei. Neural network adaptive controller simulation[D]. Taiyuan:Taiyuan University of Technology,2007.
[9]王炳萱.LM优化算法和神经网络预测控制在非线性系统中的研究[D].太原:太原理工大学,2016.WANG Bingxuan. Research on LM optimization algorithm and neural network predictive control in nonlinear systems[D]. Taiyuan:Taiyuan University of Technology,2016.
[10]谢嘉乐.基于改进的LM-BP神经网络的车牌识别算法研究与应用[D].广州:广东工业大学,2016.XIE Jiale. Research and application of license plate recognition algorithm based on improved LM-BP neural network[D].Guangzhou:Guangdong University of Technology,2016.
[11]程驰,帅志斌,李建秋,等.车载网络通讯协议FlexRay网络的分析及搭建[J].汽车安全与节能学报,2013,4(1):75-81.CHENG Chi,SHUAI Zhibin,LI Jianqiu,et al. Analysis and construction of vehicle network communication protocol FlexRay network[J]. Journal of automotive safety and energy conservation,2013,4(1):75-81.
[12] JANG K,PARK I,HAN J. Design framework for FlexRay network parameter optimization[J]. International journal of automotive technology,2011,12(4):589-597.
[13]张泽旭.神经网络控制与Matlab仿真[M].哈尔滨:哈尔滨工业大学出版社,2011.ZHANG Zexu. Neural network control and Matlab simulation[M]. Harbin:Harbin Institute of Technology Press,2011.
[14]魏东.非线性系统神经网络参数预测及控制[M].北京:机械工业出版社,2007.WEI Dong. Prediction and control of parameters of nonlinear system neural network[M]. Beijing:Machinery Industry Press,2007.
[15] LIU G Y,XU B G. A real-time scheduling scheme of quantized control systems under bandwidth constraints[C]//Proceedings of the 8th World Congress on Intelligent Control and Automation. Jinan,China:IEEE,2010:2334-2338.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |