Design of an expert system based on neural, network ensembles for missile fault diagnosis

Abstract

According to the specialty and complexity of the missile fault diagnosis, a novel expert system design method based on the neural network ensembles is proposed in this paper. With large amounts of typical missile fault samples and raw measurable parametric data available, the missile fault diagnosis system based on neural network ensembles can be created applying general construction techniques of the neural network fault diagnosis system, including signal preprocessing, fault feature extraction/selection, and network training. Combining the fault diagnosis system based on neural network ensembles, the framework of the missile fault diagnosis expert system is constructed with more flexibility and effectiveness in missile fault diagnosis. It's proved that through diagnosis of the missile from several different sides by use of different parameters or combined parameters the designed system tends to give more reliable results.