ICA and BP Neutral Network Based Fault Detecting Algorithm for Large Engine

Abstract

With the rapid development of information technology, some experience intensive work like fault detecting has been greatly improved by information technology. Traditional fault detecting method depends on the knowledge of expert to some extent which can not satisfy the requirement of large engine, which is with poor testability. Regarding this problem, this paper apply the technology of Independent Components Analysis (ICA) and BP neutral network to the process of fault detecting, the accuracy and efficiency are greatly improved with these methods, and the experiment result has proven the validity of the method described.