[an error occurred while processing this directive] [an error occurred while processing this directive] [an error occurred while processing this directive]
[an error occurred while processing this directive]

弹箭与制导学报 >

2019 , Vol. 39 >Issue 1: 45 - 49

DOI: https://doi.org/10.15892/j.cnki.djzdxb.2019.01.010

改进型 WNN 在火箭灭火车伺服系统中的应用

  • 侯润民 ,
  • 方安国 ,
  • 胡达 ,
  • 侯远龙
展开
  • 1 南京理工大学机械工程学院, 南京 210094
    2 湖北江山重工有限责任公司, 湖北襄阳 441057

侯润民(1987-), 男, 四川人, 讲师, 博士, 研究方向: 智能控制。

收稿日期: 2018-08-29

  网络出版日期: 2025-05-21

收起

Application of Improved Wavelet Neural Network to Rocket Fire Extinguishing Servo System

  • HOU Runmin ,
  • FANG Anguo ,
  • HU Da ,
  • HOU Yuanlong
Expand
  • 1 School of Mechanical Engineering, Nanjing University of Science and Technology, Nanjing 210094, China
    2 Hubei Jiangshan Heavy Industries Co. Ltd, Hubei Xiangyang 441057, China

Received date: 2018-08-29

  Online published: 2025-05-21

Fold

摘要

针对远距离火箭灭火车伺服系统中存在强耦合、非线性和参数时变等不确定性,文中提出了一种基于Levenberg-Marquardt算法的小波神经网络(waveletneuralneural,WNN)控制方法。由于Levenberg-Marquardt算法具有避免局部极小所带来的系统不稳定、收敛速度快等优点,使用Levenberg-Marquardt算法优化小波神经网络的各连接权值和各阈值从而提高控制精度。仿真结果和靶场试验表明,在参数摄动和负载扰动的情况下,该种控制策略与传统的WNN控制策略相比较有更好的控制精度和鲁棒性。

关键词： 交流伺服系统; 小波神经网络; Levenberg-Marquardt 算法

本文引用格式

侯润民 , 方安国 , 胡达 , 侯远龙 . 改进型 WNN 在火箭灭火车伺服系统中的应用[J]. 弹箭与制导学报, 2019 , 39(1) : 45 -49 . DOI: 10.15892/j.cnki.djzdxb.2019.01.010

Abstract

This paper proposes a fuzzy wavelet neural network with improved Levenberg Marquardt algorithm (WFNN-LM) to control the nonlinearity, wide variations in loads, time variation and uncertain disturbance of the ac servo system. The particle Levenberg Marquardt has the advantages of avoiding the unstable system caused by local minimum and fast convergence rate. Therefore using Levenberg Marquardt algorithm can optimize the network weights and threshold value parameter of wavelet neural network. Finally, the result of the simulation and the prototype test verified the good performance of the proposed method on control accuracy, applicability and robustness in the conditions of parameter perturbation and load disturbance.

Key words： AC servo system; fuzzy wavelet neural network; Levenberg-Marquardt algorithm

[an error occurred while processing this directive]

参考文献

[1]
LI S LIU Z G Adaptive speed control for permanent-magnet synchronous motor system with variations of load inertia[J]. IEEE Transactions on Industrid Electronics, 2009, 56(8): 3050-3059.
[2]
JEZERNIK K RODIC M High precision motion control of servo drives[J]. IEEE Transactions on Industrid Electronics, 2009, 56(10): 3810-3816.
[3]
SARMA M SARMA K K An ANN based approach to recognize initial phonemes of spoken words of Assamese language[J]. Applied Soft Computing, 2013, 13(5): 2281-2291.
[4]
KHAYAT O RAZJOOVAN J RAHATABAD F N, et al. A fast learnt fuzzy neural network for huge scale discrete data function approximation and prediction[J]. Journal of Intelligent & Fuzzy Systems, 2013, 24(4): 693-701.
[5]
DU JL YANG Y WANG DH, et al. A robust adaptive neural networks controller for maritime dynamic positioning system. Neurocomputing, 2013, 110: 128–136.
[6]
PRE?EREN PP STOPAR B Wavelet neural network employment for continuous GNSS orbit function construction: application for the assisted-GNSS principle[J]. Applied Soft Computing, 2013, 13(5): 2526-2536.
[7]
BODYANSKIY Y DOLOTOV A VYNOKUROVA O Evolving spiking wavelet-neuro-fuzzy self-learning system[J]. Applied Soft Computing, 2014, 14: 252-258.
[8]
BAYRAM D SEKER S Wavelet based Neuro Detector for low frequencies of vibration signals in electric motors[J]. Applied Soft Computing, 2013, 13(5): 2683-2691.
[9]
FU Xingang LI Shuhui FAIRBANK M, et al. Training recurrent neural networks with the Levenberg-Marquardt algorithm for optimal control of a grid-connected converter[J]. IEEE Transactions on Neural Networks and Learning Systems, 2015, 26(9): 1900-1912.
[10]
韩崇伟 火炮位置伺服系统的鲁棒控制与应用研究[D]. 西安: 西安交通大学, 2002.
[11]
郭亚军 王晓锋 马大为, 等. 自适应反演滑模控制在火箭炮交流伺服系统中的应用[J]. 兵工学报, 2011, 32(4): 493-497.
Options
文章导航

/

〈 〉

[an error occurred while processing this directive]