Fuzzy Radial Basis Function (Frbf) Network Based Tool Condition Monitoring System Using Vibration Signals

Abstract

Thriving automation in industries leads to more research on the tool condition monitoring systems for better accuracy and fast recognition/evaluation of tool wear. Research on the applicability of the new advances in the soft-computing as well as in the signal processing fields is the inevitable consequence. In this work, a new soft-computing modeling technique, fuzzy radial basis function (FRBF) network has been applied to the prediction of drill wear using the vibration signal features. This work presents the wear prediction performance comparison of this new model with three other already tried and established soft-computing models, such as back propagation neural network (BPNN), radial basis function network (RBF) and normalized radial basis function network (NRBF), for both time-domain as well as wavelet packet approaches of feature extraction. Experimental results show that FRBF model with wavelet packet approach produces the best performance of predicting flank wear.

Artificial Intelligence-Based Hole Quality Prediction in Micro-Drilling Using Multiple Sensors

“…As mean and RMS values of time domain features are determined by considering the whole signals, these are likely to be affected by the noise and disturbance present in the drilling process. To eliminate the noise and disturbances, many attempts have been made earlier to extract features in the frequency domain and the time-frequency domain [48,52]. Among different time-frequency domain signal processing methods, the most common is the wavelet packet transform which can overcome the poor time localization of a fast Fourier transform (FFT) and loss of important information due to not consideration of the detail part in case of a discrete wavelet transform (DWT).…”

Condition Monitoring of Single Point Cutting Tools Based on Machine Learning Approach

“…12 Patra et al developed a tool condition (flank wear) monitoring system using the vibration signals of the machining process. 13 They showed that the fuzzy radial basis function based neural network can recognize the features extracted from the time domain by applying the wavelet packet approach, which underlies the vibration signals more effectively than other methods (e.g. back propagation neural network, radial basis function network, and normalized radial basis function network).…”

Tool Condition Monitoring and Remaining Useful Life Prognostic Based on a Wireless Sensor in Dry Milling Operations

“…The acquired vibration signals were used to extract the time–frequency features [ 19 ], whereas many of these features containing little useful information could be discarded based on the statistical selection criteria in TCM system. A soft-computing technique was applied to estimate the tool wear with the vibration signals [ 20 ], and the prediction performance comparison of the proposed model with three other models was summarized. Yesilyurt et al [ 21 ] indicated the existence and development of tool wear using vibration signals in the milling process, and the features of tool wear were revealed by the scalogram and its mean frequency.…”