Tool Wear Prediction in Machining of Aluminum Matrix Composites with the Use of Machine Learning Models

This paper discusses the diagnostic models of tool wear during face milling of Aluminum Matrix Composite (AMC), classified as a difficult-to-cut material. Prediction and classification models were considered. The models were based on one-dimensional simple regression or on multidimensional regression trees, random forest, nearest neighbor and multilayer perceptron neural networks. Measures of diagnostic signals obtained from measurements of cutting forces and vibration accelerations of the workpiece were used. The study demonstrated that multidimensional models outperformed one-dimensional models in terms of prediction accuracy and classification performance. Specifically, multidimensional predictive models exhibited lower maximum and average absolute prediction errors (0.036 mm vs. 0.050 mm and 0.026 mm vs. 0.045 mm, respectively), and classification models recorded fewer Type I and Type II errors. Despite the increased complexity, the higher predictive accuracy (up to 0.97) achieved with multidimensional models was shown to be suitable for industrial applications. However, simpler one-dimensional models offered the ad-vantage of greater reliability in signal acquisition and processing. It was also highlighted that the advantage of simple models from a practical point of view is the reduced complexity and consequent greater reliability of the system for acquiring and processing diagnostic signals.