基于稀疏存储Elman神经网络的直线伺服控制

中国机械工程 ›› 2012, Vol. 23 ›› Issue (1): 55-58.

基于稀疏存储Elman神经网络的直线伺服控制

左健民1,2;潘超1,3;汪木兰4

1. 江苏大学,镇江,212013

2.江苏技术师范学院,常州,213001

3.上海铁路局,上海,200071

4.南京工程学院,南京,211167

出版日期:2012-01-10 发布日期:2012-01-15
基金资助:
江苏省“六大人才高峰”高层次人才项目(2008163)；江苏省高校自然科学基础研究项目(08KJB460003)
Jiangsu Provincial Natural Science Basic Program of Higher Education of China（No. 08KJB460003）

Linear Servo System Control Based on Improved Elman Neural Network with Sparse Memory

Zuo Jianmin1,2;Pan Chao1,3;Wang Mulan4

1.Jiangsu University, Zhenjiang,Jiangsu, 212013

2.Jiangsu Teachers University of Technology, Changzhou,Jiangsu, 213001

3.Shanghai Railway Administration,Shanghai, 200071
4.Nanjing Institute of Technology, Nanjing, 211167

Online:2012-01-10 Published:2012-01-15
Supported by:
Jiangsu Provincial Natural Science Basic Program of Higher Education of China（No. 08KJB460003）

摘要/Abstract

摘要：

为提高数控机床直线进给系统的动态跟踪性能及抗干扰能力,结合进给系统重复运动的特点,利用前一次或前几次的历史控制信息提高进给系统的动态性能,提出了具有动态稀疏存储功能的改进Elman神经网络;引入迅速联想的表格查询方式对神经网络的历史信息进行分类存储、选择利用以增强网络泛化能力,提高网络收敛速度;详细推导了改进Elman神经网络的数学模型及权值调整算法,并将其应用到直线进给伺服系统中,结果表明,基于稀疏存储Elman神经网络的速度控制器具有良好的跟踪精度和抗干扰能力。

关键词:

Elman神经网络, 稀疏存储, 直线伺服系统, 泛化能力

Abstract:

In order to improve the dynamic performance and disturbance resistance abilities of CNC machine tool direct-drive linear servo system with complexities of dynamics and nonlinear, taking advantages of historical control information of repeated motion, an improved Elman neural network with spares memory was proposed and rapid associate theory based on table-look up was introduced to enhance learning speed and generalization capability of neural network. The information of neural network was classified, stored and selected to use. The mathematical model of improved Elman neural network and the weight adjustment algorithm were derived in detail and applied to a linear feed servo system.The results show that the controller based on improved Elman neural network with spares memory exhibits satisfactory performance in tracking precision and disturbance resistance.

Key words: Elman neural network, sparse memory, linear servo system;generalization capability

中图分类号:

TM359.4



左健民1, 2, 潘超1, 3, 汪木兰4.

基于稀疏存储Elman神经网络的直线伺服控制

[J]. 中国机械工程, 2012, 23(1): 55-58.

ZUO Jian-Min-1, 2, BO Chao-1, 3, HONG Mu-Lan-4. Linear Servo System Control Based on Improved Elman Neural Network with Sparse Memory[J]. China Mechanical Engineering, 2012, 23(1): 55-58.

[1]	王国彪, 赖一楠, 范大鹏, 杨华勇, 王时龙. 新型精密传动机构设计与制造综述 [J]. J4, 201016, 21(16): 1891-1897.
[2]	王立存, 陈进, 张贤明, 陈国强. 基于泛函的制冷涡旋压缩机变壁厚涡旋型线理论及形状优化 [J]. J4, 201016, 21(16): 1898-1901.
[3]	李小力, 陈威, 闫蓉. 基于BP神经网络的空间轮廓误差自适应补偿 [J]. J4, 201016, 21(16): 1902-1906.
[4]	夏瑞雪, 卢荣胜, 刘宁, 董敬涛. 基于圆点阵列靶标的特征点坐标自动提取方法 [J]. J4, 201016, 21(16): 1906-1910.
[5]	陈立锋, 吴晓铃, 秦大同, 肖正明. 齿轮啮合过程摩擦功耗研究 [J]. J4, 201016, 21(16): 1911-1915.
[6]	李明磊, 贾育秦, 张学良, 刘丽琴, 杜娟, 温淑花, 兰国生. 基于多目标差异演化算法的并联机构结构优化 [J]. J4, 201016, 21(16): 1915-1920.
[7]	吴怀超, 吴白羽, 张秀华. 石蜡感温阀传热性能的数字仿真研究 [J]. J4, 201016, 21(16): 1921-1926.
[8]	鲁开讲, 师俊平, 张锋涛. 平面三自由度并联机构动力学优化设计 [J]. J4, 201016, 21(16): 1926-1931.
[9]	张敏杰, 王庆九, 管成. 并联式油液混合动力挖掘机动力系统仿真研究 [J]. J4, 201016, 21(16): 1932-1936.
[10]	刘安平, 刘济春. IPC-208B型原子力显微镜大范围扫描三维驱动系统研究 [J]. J4, 201016, 21(16): 1936-1940.
[11]	姚运萍, 王智渊. 螺栓连接受载能量损失与结合面参数识别 [J]. J4, 201016, 21(16): 1941-1943,1951.
[12]	陈建, 邓利娟. 恒力弹性机构的设计 [J]. J4, 201016, 21(16): 1944-1946.
[13]	罗洁思, 于德介, 史美丽. 基于SVD和线调频小波路径追踪的转速波动齿轮箱故障诊断 [J]. J4, 201016, 21(16): 1947-1951.
[14]	战晓磊, 辛洪兵, 汉斯·彼德　兰特斯. 基于虚拟现实的MOTOMAN-HP3型机器人运动学仿真 [J]. J4, 201016, 21(16): 1952-1954,1998.
[15]	苏厚军, 史铁林, 陈非. 高炉煤气透平机状态检修的设计与实施 [J]. J4, 201016, 21(16): 1955-1958.