Fault Diagnosis for Ships Anti-Rolling System Based on BP-FNN

摘要：

According to a certain model ships anti-rolling system this paper analyzes the fault information and establishes a fault diagnosis model using fuzzy-nerve network algorithms. Based on the fuzzy logic processing data and using the past experience and knowledge,the nerve network avoids some problems of fault tree diagnosis system,such as matching conflict,combination explosion,and infinite recursion.In order to train the nerve network,this paper adopt the improved BP arithmetic which can solve the problem of convergence speed and convergence surge. The result shows this fault diagnosis system has strong robustness and generalization. That method that uses model free diagnosis is easy to learn by itself and constant perfect system function,and has some theories and engineering application value.

关键词： fault diagnosis neural network fuzzy logic anti-rolling system

作者: Bing Li Gaoyun Li Hongtao Cao Lanyong Zhang

作者单位: College of Automation,Harbin Engineering University,Harbin 150001 China

会议类型: 国际会议

会议名称: 2011 International Conference on Opto-Electronics Engineering and Information Science(2011光电电子工程与信息科学国际会议 ICOEIS 2011)

会议地点: 西安

会议语种:英文

页码: 1530-1533

在线出版日期: 2011-12-23（万方平台首次上网日期，不代表论文的发表时间）