引用本文: | 杨庆超,杨理华,朱石坚,等.柔性神经网络滑模主动控制技术[J].国防科技大学学报,2016,38(4):125-131.[点击复制] |
YANG Qingchao,YANG Lihua,ZHU Shijian,et al.Active control technology using flexible neural network sliding mode algorithm[J].Journal of National University of Defense Technology,2016,38(4):125-131[点击复制] |
|
|
|
本文已被:浏览 7109次 下载 5870次 |
柔性神经网络滑模主动控制技术 |
杨庆超1, 杨理华2, 朱石坚3, 楼京俊3 |
(1.海军工程大学 科研部, 湖北 武汉 430033;2. 海军潜艇学院 动力操纵系, 山东 青岛 266042;3.1.海军工程大学 科研部, 湖北 武汉 430033)
|
摘要: |
针对复杂激励条件下的振动控制,对Jiles-atherton模型的磁致伸缩作动器在双层隔振系统中的主动控制进行了研究。以传统滑模控制为基础,提出一种柔性神经网络滑模控制算法。用正则化方法设计控制器的切换矩阵,建立神经网络权值和柔性映射参数更新学习公式,并将该控制策略应用于双层隔振系统的振动主动控制中。通过单频、多频及随机信号激励进行仿真研究,结果表明:柔性神经网络滑模控制器具有较强的鲁棒性,具有较好的控制效果。 |
关键词: 双层隔振 磁致伸缩作动器 滑模控制 柔性神经网络 主动控制 |
DOI:10.11887/j.cn.201604020 |
投稿日期:2015-03-21 |
基金项目:国家自然科学基金资助项目(51179197,51579242);国家自然科学基金青年基金资助项目(51509253) |
|
Active control technology using flexible neural network sliding mode algorithm |
(1. Office of Research & Development, Naval University of Engineering, Wuhan 430033, China;2. Power Control Department, Navy Submarine Academy, Qingdao 266042, China)
|
Abstract: |
For solving the vibration control problem in complex excitation, the active control of magnetostrictive actuator of Jiles-atherton model in double-layer vibration isolation system was researched. Based on the traditional sliding mode control, a flexible neural network sliding mode control algorithm was proposed and the controller switching matrix was designed by the regularization method, then the updating formulas of the neural network weights and flexible mapping parameter were also established. Furthermore the control strategy was used for the active vibration control in double-layer vibration isolation system. Finally, the single frequency, multi frequency and random signal excitation were simulated and the results show that the flexible neural network sliding mode controller has a strong robustness and a good control effect. |
Keywords: double-layer vibration isolation magnetostrictive actuator sliding mode control flexible neural network active control |
|
|
|
|
|