Intelligent Classification and Measurement of Drill Wear

Abstract

Artificial neural networks are used for on-line classification and measurement of drill wear. The input vector of the neural network is obtained by processing the thrust and torque signals. Outputs are the wear states and flank wear measurements. The learning process can be performed by back propagation along with adaptive activation-function slope. The results of neural networks with and without adaptive activation-function slope, as well as various neural network architectures are compared. On-line classification of drill wear using neural networks has 100 percent reliability. The average flank wear estimation error using neural networks can be as low as 7.73 percent.