Compare Research of Data Fusion and Neural Network Diagnosis Method

Abstract

Data fusion method is applied in fault diagnosis field. The faults are diagnosed through three levels which are data fusion level, feature level and decision level respectively. The feature level uses multi-collateral neural networks. The purpose of using neural networks is mainly getting Basic Probability Assignment (BPA) of D-S evidence theory. On the other hand the neural networks in feature level are used for local diagnosis and D-S evidence theory is adopted to integrate the local diagnosis results. This method is fit for complicated object. In order to improve the validity and practicability of this method using compare with single neural network to diagnose the same object faults. The results testify that data fusion method is superior to the single neural network method in diagnosing faults of complicated system.