基于混合遗传算法的磁控形状记忆合金驱动器磁滞模型优化

中国机械工程 ›› 2015, Vol. 26 ›› Issue (4): 508-512.

基于混合遗传算法的磁控形状记忆合金驱动器磁滞模型优化

纪华伟;刘毛娜;胡小平

杭州电子科技大学,杭州,310018

出版日期:2015-02-25 发布日期:2015-02-25
基金资助:
国家自然科学基金资助项目(50805024);浙江省自然科学基金资助项目(Y1080855)

Optimization of MSMA Actuator Hysteresis Model Based on Hybrid GA

Ji Huawei;Liu Maona;Hu Xiaoping

Hangzhou Dianzi University,Hangzhou,310018

Online:2015-02-25 Published:2015-02-25
Supported by:
National Natural Science Foundation of China（No. 50805024）;Zhejiang Provincial Natural Science Foundation of China（No. Y1080855）

摘要/Abstract

摘要：

为了消除或减小磁滞非线性特性对磁控形状记忆合金驱动器定位精度的影响,应用BP神经网络建立了磁控形状记忆合金驱动器磁滞模型。针对BP网络算法存在的不足,以及网络结构、初始连接权值和阈值的选择对BP网络训练的影响很大等问题,提出一种混合遗传算法对神经网络磁滞模型的权值和阈值进行优化。将优化后的参数赋值给BP神经网络重新训练,结果表明,优化后的磁滞模型训练误差绝对值由25nm减小到5nm,有较好的收敛性。

关键词: 磁控形状记忆合金驱动器, 磁滞非线性, BP神经网络, 遗传算法

Abstract:

In order to improve the positioning precision of MSMA actuator, a BP neural network hysteresis nonlinear model was built. For the shortcomings that BP neural network existed, and the differences of network structure and the choices of initial connection weights and thresholds effected BP network training precision. For solving these problems, a hybrid algorithm of GA and BP algorithm was established, the network weights and thresholds were optimized by using the GA, and BP neural network hysteresis nonlinear model was renewally trained by using the optimized parameters. Results show that the optimized neural network hybrid model has better convergence, absolute value of training error is decreased from 25nm to 5nm.

Key words: magnetically controlled shape memory alloy(MSMA) , actuator;hysteresis nonlinearity;BP neural network;genetic algorithm(GA)

中图分类号:

纪华伟, 刘毛娜, 胡小平. 基于混合遗传算法的磁控形状记忆合金驱动器磁滞模型优化[J]. 中国机械工程, 2015, 26(4): 508-512.

Ji Huawei, Liu Maona, Hu Xiaoping. Optimization of MSMA Actuator Hysteresis Model Based on Hybrid GA[J]. China Mechanical Engineering, 2015, 26(4): 508-512.

参考文献

[1]吴新杰,王凤翔,张庆新.磁控形状记忆合金执行器及其应用前景[J].材料导报,2003,17(9):16-18.`
Wu Xinjie,Wang Fengxiang,Zhang Qingxin.Magneticaly Controlled Shape Memory Alloy Actuators and Their Potential Applications[J]. Materials Review,2003,17(9):16-18.
[2]Liu L,Tan K K,Putra A S,et al.Compensation of Hysteresis in Piezoelectric Actuator with Iterative Learning Control[J].Journal of Control Theory and Applications,2010,8(2):176-180.
[3]Tian M. Adaptive Control of Systems with Non Smooth Nonlinearities[D].Charlattesville,Virginia:University of Virginia, 1997: 113-123.
[4]Fan Bin.Nonlinearities Modeling of Smart Materials and Structure[D]. Houston:University of Houston, 2010:21-22.
[5]Fu J. On the Adaptive Controls of Non Linear Systems with Different Hysteresis Model Representation[D]. Montreal:Concordia University,2009:104-124.
[6]Ge Ping, Jouaneht M. Generalized Preisach Model for Hysteresis Non Linearity of Piezoceramic Actuators[J].Precision Engineering, 1997, 20(2):99-110.
[7]刘慧芳,贾振元,王福吉.基于神经网络的超磁致伸缩传感执行器磁滞模型[J].中国机械工程,2011,22(5):571-575.
Liu Huifang, Jia Zhenyuan, Wang Fuji. Study on Hysteresis Model of Giant Magnetostrictive Sensing Actuator Based on Neural Network[J]. China Mechanical Engineering,2011,22(5):571-575.
[8]刘向东,修春波,李黎,等.迟滞非线性系统的神经网络建模[J].压电与声光,2007,29(1):106-108.
Liu Xiangdong,Xiu Chunbo,Li Li,et al.Hysteresis Modeling Using Neural Networks[J].Piezoelectrics and Acoustooptics, 2007, 29(1): 106-108.
[9]Reynolds J J.An Investigation of Model Reference Adaptive Control of Unknown Dynamic Hysteretic Systems Using Slow Adaptation[D]. East Lansing,Michigan:Michigan State University,2007:1-5.
[10]王小平，曹立明.遗传算法理论、应用与软件实现[M].西安:西安交通大学出版社,2004:1-50.
[11]郑军红,叶修梓,陈志扬.基于神经网络和遗传算法的智能夹具规划[J].中国机械工程,2008,19（19）：2376-2381.
Zheng Junhong,Ye Xiuzi,Chen Zhiyang.Intelligent Fixture Planning Based on Artificial Neural Network and Genetic Algorithms[J]. China Mechanical Engineering,2008,19(19):2376-2381.

[1]	李西兴, 杨道明, 李鑫, 吴锐, . 基于混合遗传鲸鱼优化算法的柔性作业车间自动导引车融合调度方法[J]. 中国机械工程, 2021, 32(08): 938-950，986.
[2]	赵丽娟, 王雅东, 王斌. 含夹矸煤层条件下采煤机螺旋滚筒工作性能分析与预测[J]. 中国机械工程, 2021, 32(08): 976-986.
[3]	李冰1;张永德1;袁立鹏2;朱光强3;代雪松1;苏文海3. 液压四足机器人足端的力预测控制与运动平稳性[J]. 中国机械工程, 2021, 32(05): 523-532.
[4]	刘雪梅；刘涛；郭欢. 基于可用度评价的混联生产线缓冲区配置优化[J]. 中国机械工程, 2020, 31(18): 2220-2230.
[5]	岳彩旭;刘鑫;刘智博;谢娜;王彦武. 基于有限元仿真的拼接模具铣削用刀具优化[J]. 中国机械工程, 2020, 31(17): 2085-2094.
[6]	刘雪梅1;王笑1;柳跃雷2. 模糊时间窗约束下的装配线物料配送方案优化[J]. 中国机械工程, 2020, 31(17): 2095-2103.
[7]	吕佑龙;许鸿伟;郑城;张洁;郑鹏. 基于混合式特征选择模型的晶圆允收测试关键参数识别方法[J]. 中国机械工程, 2020, 31(16): 1978-1984,1997.
[8]	杨杰, 胡琦, 肖亭, 张文颖, 张超勇. 基于能耗的冷轧连退机组能效建模与工艺参数优化及排序建模优化[J]. 中国机械工程, 2020, 31(14): 1724-1732.
[9]	刘建胜;雷兆发;聂伟豪;涂海宁. 一种鱼骨仓储布局下的拣选路径优化方法[J]. 中国机械工程, 2020, 31(10): 1225-1232.
[10]	吕凤鹏;李朝阳;黄健;陈兵奎. RV减速器转臂轴承的优化设计[J]. 中国机械工程, 2020, 31(09): 1043-1048.
[11]	郭祥雨;王琳;张永健. 规则约束下基于免疫遗传算法的机加工艺规划[J]. 中国机械工程, 2020, 31(04): 482-488.
[12]	张恒;李爱平;傅翔;邵焕;刘雪梅. 面向混批加工的装夹方案选择与线平衡集成优化方法[J]. 中国机械工程, 2019, 30(20): 2497-2504.
[13]	聂黎1;张国辉2;王小刚1;白跃伟1. 基于博弈论的虚拟制造网络车间调度优化方法[J]. 中国机械工程, 2019, 30(12): 1492-1497.
[14]	肖帆;李光;游雨龙. 空间3R机械手逆向运动学的多模块神经网络求解[J]. 中国机械工程, 2019, 30(10): 1233-1238.
[15]	盛继新1;张邦基1;朱波2;王明1;金秋谈1. 两挡纯电动汽车传动系统参数优化和试验对比[J]. 中国机械工程, 2019, 30(07): 763-770,776.