基于RBF与OS-ELM神经网络的AUV传感器在线故障诊断

段 杰; 李 辉; 陈自立; 龚时华; 赵朝闻

doi:10.11993/j.issn.2096-3920.2018.02.010

基于RBF与OS-ELM神经网络的AUV传感器在线故障诊断

doi: 10.11993/j.issn.2096-3920.2018.02.010

中国船舶重工集团公司第705研究所昆明分部, 云南昆明, 650118

详细信息

作者简介:
段杰(1992-), 男, 在读硕士, 主要研究方向为武器系统与运用工程.

中图分类号: U674.941; TP183
计量
- 文章访问数: 779
- HTML全文浏览量: 2
- PDF下载量: 282
- 被引次数: 0
出版历程
- 收稿日期: 2017-06-26
- 修回日期: 2017-10-01
- 刊出日期: 2018-05-08

Online Fault Diagnosis of AUV Sensor Based on RBF and OS-ELM Neural Networks

Kunming Branch of the 705 Research Institute, China Shipbuilding Industry Corporation, Kunming 650106, China

摘要

摘要: 传感器是自主式水下航行器(AUV)的重要组成部分, 实时准确地对AUV传感器进行在线故障诊断, 对提高AUV的安全性具有重要意义。文中通过对机器学习算法的分析, 建立了基于径向基函数(RBF)神经网络的AUV传感器预测器, 该预测器具有较高的实时性和准确性; 在此基础上, 首次将在线贯序学习机(OS-ELM)算法应用于传感器在线故障诊断, 进一步提高了预测器的实时性和准确性。文中还利用某AUV传感器实航数据, 分别对2种故障诊断模型进行了仿真和对比分析, 结果表明, 结合RBF神经网络算法的OS-ELM神经网络预测器, 其预测精度和实时性较RBF神经网络预测器更高, 而且性能更稳定, 可为AUV控制系统各传感器在线故障诊断方案设计提供参考。
- 自主式水下航行器(AUV) /
- 径向基函数(RBF) /
- 在线贯序学习机(OS-ELM) /
- 神经网络 /
- 在线故障诊断 /
- 传感器
Abstract: Sensor is an important component part of an autonomous undersea vehicle(AUV). Real-time and accurate online fault diagnosis of AUV sensors is of great significance to improve the safety of an AUV. This study analyzes the machine learning algorithms, and builds a radial basis function(RBF) neural network-based AUV sensor predictor with high accuracy and real-time performance. Subsequently, the online sequential extreme learning machine(OS-ELM) algorithm is applied to the online sensor fault diagnosis to improve the real time performance and accuracy of the predictor. Two kinds of fault diagnosis models are simulated and compared by using the sea trial data of AUV sensor, and the results show that the prediction accuracy and real-time performance of the OS-ELM neural network predictor with RBF neural network algorithm are higher than that of RBF neural network predictor. This research may provide a reference for the design of on-line fault diagnosis scheme of AUV control system.
- autonomous undersea vehicle(AUV) /
- radial basis function(RBF) /
- online sequential extreme learning ma-chine(OS-ELM) /
- neural network /
- online fault diagnosis /
- sensor

HTML全文

参考文献(14)

[1]	陈艾琴, 刘乾, 朱大奇. 基于BP神经网络的水下机器人推进器故障辨识算法[J]. 电脑知识与技术, 2009, 5(19): 5214-5216. Chen Ai-qin, Liu Qian, Zhu Da-qi. A Fault Identification Algorithm of Thrusters for Unmanned Underwater Vehicles Based on BP Neural Networks[J]. Computer Knowledgeand Technology, 2009, 5(19): 5214-5216.
[2]	朱大奇, 陈楚瑶, 颜明重. 基于CA-CMAC的快速传感器故障诊断方法[J]. 电子学报, 2008, 36(8): 1646-1650. Zhu Da-qi, Chen Chu-yao, Yan Ming-zhong. Fast Sensor Fault Diagnosis Method Based on CA-CMAC[J]. Acta Electronica Sinica, 2008, 36(8): 1646-1650.
[3]	胡暾, 赵哲身, 郑毅. 基于主元分析的传感器故障检测与诊断[J]. 仪表技术, 2005(6): 30-32. Hu Tun, Zhao Zhe-shen, Zheng Yi. Fault Detection and Diagnosis for Sensors Based On PAC[J]. Instrumentation Technology, 2005(6): 30-32.
[4]	严浙平, 陈涛, 秦政, 等. 灰色动态预测在AUV传感器故障诊断中的应用[J]. 传感技术学, 2008, 21(6): 1002- 1006. Yan Zhe-ping, Chen Tao, Qin Zheng, et al. Application of Sensor Fault Diagnosis Based on Grey Dynamic Prediction for AUV[J]. Chinese Journal of Sensors and Actua-tors, 2008, 21(6): 1002-1006.
[5]	崔荣鑫, 徐德民, 潘瑛, 等. 基于滑模观测器的AUV传感器故障检测[J]. 弹箭与制导学报, 2004, 24(4): 233- 240. Cui Rong-xin, Xu De-ming, Pan Ying, et al. AUV Sensor Fault Detection Based on Sliding Observer[J]. Journal of Projectiles, Rockets, Missiles and Guidance, 2004, 24(4): 233- 240.
[6]	朱大奇, 胡震. 水下机器人故障诊断与容错控制技术[M]. 北京: 国防工业出版社, 2012.
[7]	刘晓琴, 王大志, 杨青. 一种基于BP神经网络的传感器故障诊断方案[J]. 沈阳理工大学学报, 2006, 25(4): 16-19, 46. Liu Xiao-qin, Wang Da-zhi, Yang Qing. A Fault Diagnosis Approach to Sensor Based on BP Neural Network[J]. Transactionsof Shenyang Ligong University, 2006, 25(4): 16-19, 46.
[8]	邵向潮, 何永强, 蔡鹃, 等. 基于RBF神经网络的温度传感器故障诊断[J]. 吉首大学学报(自然版), 2010, 31(2): 79-82. Shao Xiang-chao, He Yong-qiang, Cai Juan, et al. Research on Fault Diagnosis of Temperature Sensor Based on RBF Neural Network[J]. Journal of Jishou University(Natural Science Edition), 2010, 31(2): 79-82.
[9]	王玉甲, 张铭均, 金志贤. 水下机器人传感器及推进器状态监测系统[J]. 机械工程学报, 2006, 42(s1): 214-218. Wang Yu-jia, Zhang Ming-jun, Jin Zhi-xian. Condition Monitorting System for Sensors and Thrusters of AUV[J]. Chinese Journal of Mechanical Engineering, 2006, 42(s1): 214-218.
[10]	陈明. Matlab神经网络原理与实例精解[M]. 北京: 清华大学出版社, 2015.
[11]	Moody J, Darken C. Fast Learning in Networks of Locally-tuned Processing Units[J]. Neural Computation, 1989 (1): 281-294.
[12]	Liang N Y, Huang G B, Saratchandran P, et al. A Fast and Accurate Online Sequential Learning Algorithm for Feed- forward Networks[J]. IEEE Transactions on Neural Networks, 2006, 17(6): 1411-1423.
[13]	Huang G B, Zhu Q Y, Siew C K. Extreme Learning Machine: Theory and Application[J]. Neurocomputing, 2006, 70(1): 489-501.
[14]	尹刚, 张英堂, 李志宁, 等. 改进在线贯序极限学习机在模式识别中的应用[J]. 计算机工程, 2012, 38(8): 164- 166. Yin Gang, Zhang Ying-tang, Li Zhi-ning, et al. Applicati- on of Modified Online Sequential Extreme Learning Machine in Pattern Recognition[J]. Computer Engineering, 2012, 38(8): 164-166.