The Application Of Wavelet Analysis And Neural Network In Cutting Tool's Fault Diagnosis

The techniques for fault diagnosis are under rapid development.This is due to the interlacing between the demands from the practical applications and the achievements in various fields of the theory and the technology.As the modern technology develops,the engineering control systems become more and more complicated and advanced in practical applications,therefore the reliability and the security of those systems will play a critical role to both the society and the economy.More and more attention has been paid in the reliability and security in the last two decades.From the academic view,fault diagnosis has a closer relationship with many areas on science and technology such as modern control theory,signal processing,pattern recognition and artificial intelligence.The rapid development and the increasing achievements on these areas during the past two decades lay a solid foundation for the fault diagnosis of complicated systems.With the enhancement of manufacture automatization,especially,the appearance of flexible manufacture system(FMS),on-line monitoring of production processes has been receiving increased attention.In-process tool wear has a profound influence on the precision and roughness of workpiece,and,even results in discarded product and interrupted machine.Tool failure,statistically,accounts for over 75% of facility faults.Hence,on-line supervision of tool condition has become an urgent requirement.(1) According to Wavelet Analysis has the excellent time-frequency window and Neural network can effectively realize nonlinear mapping from inputs to outputs, the AE signals of cutting tool conditions is processed with wavelet analysis on the plat of MATLAB ,and the root mean square (rms) of every frequency are picked up as eigen values of pattern recognition.Then using BP netwok and its improved algorithm and RBF network for pattern recognition to achieve intelligent fault diagnosis.Experiments proved that, RBF network is superior to BP network and L-M algorithm is superior to learning adaptive gradient algorithm,but learning adaptive gradient algorithm is superior to conventional BP algorithm regardless of speed or accuracy,and the higher fault forecast-rate can be gotten..