Application Of B-Spline Neurofuzzy-Networks In Tool Fault Diagnosis

Along with automation in manufacturing industry, the importance of the mechanical fault diagnosis technology is more and more obvious. Tool is one of the most important factors in the machining process. Tool wear can affect the quality, cost and the production rate of the product. The operate-person observed tool and replaced it in the early period of machining. However, in automatic manufacturing system, the tool-failure causes invalid of machine function and the whole system's failure. Therefore, the prediction of tool wear and failure is very urgent.In this paper, we set up an experiment system of the milling tool wear monitoring and collect a variety of fault data using vibratory sensor. In the researches on signal processing, the thesis lays on FFT transform and gets the better characters through amplitude-frequency field analysis of the signal. In the process of the fault diagnosis, a perfect result can be obtained trough the diagnosis of BP network. But as can be seen, there have some limitations in the BP network. The relation between input and output that obtained by BP network cannot be expressed in acceptable way and the constringency rate of the BP network is slow. As the response of these limitations, the paper researched on the tool wear monitoring system based on neurofuzzy-networks using B-spline basic function. In terms of the positivity, compact support and normalization of B-spline basic function, the adjustment of the weights are accomplished locally and the output is simple. The results of the experiments show that the structure of the B-spline neurofuzzy-networks is clear and the training is more speedily than that of BP network.The research provides B-spline neurofuzzy-networks are completely possible to analyze shape-milling tool condition. Because the construction of the network has the expandability, it can be used in other tool condition. The model improves machining quality and efficiency.