Research on the Abrasive Water-Jet Cutting Machine Information Fusion Fault Diagnosis System Based on Fuzzy Neural Network

A system structure for water jet cutting machine fault diagnosis based on multi-information fusion is presented, which takes the time-varying, redundancy and uncertainty of the multi-fault characteristic information into consideration. We make use of the neural network´s ability of better fault tolerance, strong generalization capability, characteristics of self-organization, self-learning, and self-adaptation, and take advantage of multi-source information fusion technology to realize comprehensive processing for uncertainty information. The characteristic layer fusing model of the water jet cutting machine fault diagnosis, which makes use of fuzzy neural network to realize feature layer fusion and D-S evidence theory to complete decision layer fusion, has been established. The simulation results of water jet cutting machine fault diagnosis show that the method can effectively improve the diagnostic credibility and reduce diagnostic uncertainty.