Indirect Signals Fusion by Neural Network and Wavelet Analysis for Drill-Wear Monitoring

초록

The objective of this study is to produce a sensor fusion system for tool-condition monitoring (TCM) that would lead to a more efficient and economical drill usage. Drill-wear monitoring has an important attribute in the automatic machining process as it can help preventing the damage of tools and workpieces, and optimizing the drill usage. This study presents the architectures of a multi-layer feed-forward neural network with Levenberg-Marquardt training algorithm and a learning vector quantization (LVQ) neural network based on sensor fusion for the monitoring of drill-wear condition. Input features to the proposed neural networks were extracted out of three sensing techniques of acoustic emission (AE), vibration, and electrical current signals by using wavelet packet transform (WPT) analysis. Training and testing were performed at a moderate range of cutting conditions in the dry drilling of steel plates. Results from the proposed method of sensor fusion system show good performance in actual drilling tests.