基于遗传BP神经网络的磁流变悬置模型辨识
|
摘要
为克服误差逆向传播算法的多层前馈型BP神经网络收敛速度慢、局部极小化问题,提出用遗传算法(GA)的全局搜索能力寻求最优的BP神经网络权值和阀值,以提高神经网络的收敛速度和克服局部最优。以磁流变液压悬置动态特性试验结果为数据样本,分别用未优化的BP神经网络和优化后的GA-BP神经网络对磁流变液压悬置正、逆模型进行辨识。结果表明,相对于BP神经网络,GA-BP神经网络具有更高的辨识精度、更快的收敛速度,在磁流变液压悬置数学模型辨识方面具备更优的性能。
Initial weights and thresholds of BP neural network are optimized by using Genetic Algorithm(GA) method to solve its slow convergence speed and local optimum. The defect of BP neural network is thus overcome by the proposed method. The direct and inverse dynamic models for a prototype of Magneto-rheological(MR) mount are identified by using traditional BP neural network and novel GA-BP neural network. The results show that the GA-BP neural network has faster convergence rate and higher precision compared with the traditional BP neural network in the identification of direct and inverse model for MR mount.
Initial weights and thresholds of BP neural network are optimized by using Genetic Algorithm(GA) method to solve its slow convergence speed and local optimum. The defect of BP neural network is thus overcome by the proposed method. The direct and inverse dynamic models for a prototype of Magneto-rheological(MR) mount are identified by using traditional BP neural network and novel GA-BP neural network. The results show that the GA-BP neural network has faster convergence rate and higher precision compared with the traditional BP neural network in the identification of direct and inverse model for MR mount.
引文
[1]KOO J H,GONCALVES F D,AHMADIAN M.A comprehensive analysis of the response time of MR dampers[J].Smart Materials and Structures,2006,15(2):351-358.
[2]NGUYEN C C.The performance of an adaptive magnetorheological fluid mount[C]//Proceedings of the ASME International Mechanical Engineering Congress and Exposition.Seattle,USA:ASME,2008:261-268.
[3]SAVARESI S M.Identification of semi-physical and black-box non-linear models:The case of MR-dampers for vehicles control[J].Automatica,2005,41(1):113-127.
[4]BOADA M J L,CALVO J A.Modeling of a magnetorheological damper by recursive lazy learning[J].International Journal of Non-Linear Mechanics,2011(46):479-485.
[5]HMADKHANLOU F,MAHBOOB M.An improved model for magnetorheological fluid-based actuators and sensors[J].Journal of Intelligent Material Systems and Structures,2010,21(1):3-18.
[6]HONG S R,WERELEY N M,CHOI Y T,et al.Analytical and experimental validation of a nondimensional Bingham model for mixed-mode magnetorheological dampers[J].Journal of Sound and Vibration,2008,312(3):399-417.
[7]周强,瞿伟廉.磁流变阻尼器的两种力学模型和试验验证[J].地震工程与工程振动,2002,22(4):144-150.ZHOU Qiang,QU Wei-lian.Two mechanic models for magnetorheological damper and corresponding test verification[J].Earthquake Engineering and Engineering Vibration,2002,22(4):144-150.
[8]WERELEY N,PANG L.Nondimensional analysis of semi-active electrorheological and magnetorheological dampers using approximate parallel plate models[J].Smart Materials and Structures,1998(7):732-743.
[9]WANG Xiao-jie,GORDANINEJAD F.A new magnetorheological fluid-elastomer mount:Phenomenological modeling and experimental study[J].Smart Materials and Structures,2009,18(9):130-138.
[10]DU H,LAM J,ZHANG N.Modelling of a magnetorheological damper by evolving radial basis function networks[J].Engineering Applications of Artificial Intelligence,2006,19(8):869-881.
[11]SCHURTER K,ROSCHKE P N.Fuzzy modeling of a magnetorheological damper using anfis[C]//The Ninth IEEE International Conference Fuzzy Systems.San Antonio,USA:IEEE,2000.
[12]AHN K K,TROUNG D Q,ISLAM M A.Modeling of a magnetorheological(MR)fluid damper using a self tuning fuzzy mechanism[J].Journal of Mechanical Science and Technology,2009(23):1485-1499.
[13]WANG D H,LIAO W H.Neural network modeling and controllers for magnetorheological fluid dampers[C]//The10th IEEE International Conference on Fuzzy Systems.Melbourne,Australia:IEEE,2001.
[14]王修勇,宋璨.磁流变阻尼器的性能试验与神经网络建模[J].振动与冲击,2009,28(4):42-46.WANG Xiu-yong,SONG Can.Test of a MR damper and its modeling using neural network[J].Journal of Vibration and Shock,2009,28(4):42-46.
[15]孙志强,葛哲学.神经网络理论与MATLAB7实现[M].北京:科学出版社,2005.SUN Zhi-qiang,GE Zhe-xue.Neural network theory and realization of MATLAB7[M].Beijing:Science Press,2005.
[16]陈国良,王煦法.遗传算法及其应用[M].北京:人民邮电出版社,2001.CHEN Guo-liang,WANG Xu-fa.Genetic algorithm and its application[M].Beijing:Posts and Telecom Press,2001.
[17]王昊,胡海岩.磁流变阻尼器的模糊逼近[J].振动工程学报,2006,19(1):31-36.WANG Hao,HU Hai-yan.The fuzzy approximation of MR damper[J].Journal of Vibration Engineering,2006,19(1):31-36.
[2]NGUYEN C C.The performance of an adaptive magnetorheological fluid mount[C]//Proceedings of the ASME International Mechanical Engineering Congress and Exposition.Seattle,USA:ASME,2008:261-268.
[3]SAVARESI S M.Identification of semi-physical and black-box non-linear models:The case of MR-dampers for vehicles control[J].Automatica,2005,41(1):113-127.
[4]BOADA M J L,CALVO J A.Modeling of a magnetorheological damper by recursive lazy learning[J].International Journal of Non-Linear Mechanics,2011(46):479-485.
[5]HMADKHANLOU F,MAHBOOB M.An improved model for magnetorheological fluid-based actuators and sensors[J].Journal of Intelligent Material Systems and Structures,2010,21(1):3-18.
[6]HONG S R,WERELEY N M,CHOI Y T,et al.Analytical and experimental validation of a nondimensional Bingham model for mixed-mode magnetorheological dampers[J].Journal of Sound and Vibration,2008,312(3):399-417.
[7]周强,瞿伟廉.磁流变阻尼器的两种力学模型和试验验证[J].地震工程与工程振动,2002,22(4):144-150.ZHOU Qiang,QU Wei-lian.Two mechanic models for magnetorheological damper and corresponding test verification[J].Earthquake Engineering and Engineering Vibration,2002,22(4):144-150.
[8]WERELEY N,PANG L.Nondimensional analysis of semi-active electrorheological and magnetorheological dampers using approximate parallel plate models[J].Smart Materials and Structures,1998(7):732-743.
[9]WANG Xiao-jie,GORDANINEJAD F.A new magnetorheological fluid-elastomer mount:Phenomenological modeling and experimental study[J].Smart Materials and Structures,2009,18(9):130-138.
[10]DU H,LAM J,ZHANG N.Modelling of a magnetorheological damper by evolving radial basis function networks[J].Engineering Applications of Artificial Intelligence,2006,19(8):869-881.
[11]SCHURTER K,ROSCHKE P N.Fuzzy modeling of a magnetorheological damper using anfis[C]//The Ninth IEEE International Conference Fuzzy Systems.San Antonio,USA:IEEE,2000.
[12]AHN K K,TROUNG D Q,ISLAM M A.Modeling of a magnetorheological(MR)fluid damper using a self tuning fuzzy mechanism[J].Journal of Mechanical Science and Technology,2009(23):1485-1499.
[13]WANG D H,LIAO W H.Neural network modeling and controllers for magnetorheological fluid dampers[C]//The10th IEEE International Conference on Fuzzy Systems.Melbourne,Australia:IEEE,2001.
[14]王修勇,宋璨.磁流变阻尼器的性能试验与神经网络建模[J].振动与冲击,2009,28(4):42-46.WANG Xiu-yong,SONG Can.Test of a MR damper and its modeling using neural network[J].Journal of Vibration and Shock,2009,28(4):42-46.
[15]孙志强,葛哲学.神经网络理论与MATLAB7实现[M].北京:科学出版社,2005.SUN Zhi-qiang,GE Zhe-xue.Neural network theory and realization of MATLAB7[M].Beijing:Science Press,2005.
[16]陈国良,王煦法.遗传算法及其应用[M].北京:人民邮电出版社,2001.CHEN Guo-liang,WANG Xu-fa.Genetic algorithm and its application[M].Beijing:Posts and Telecom Press,2001.
[17]王昊,胡海岩.磁流变阻尼器的模糊逼近[J].振动工程学报,2006,19(1):31-36.WANG Hao,HU Hai-yan.The fuzzy approximation of MR damper[J].Journal of Vibration Engineering,2006,19(1):31-36.
版权所有：© 2023 中国地质图书馆 中国地质调查局地学文献中心