Predicting tool wear size across multi-cutting conditions using advanced machine learning techniques

The need to monitor tool wear is crucial, particularly in advanced manufacturing industries, as it aims to maximise the lifespan of the cutting tool whilst guaranteeing the quality of workpiece to be manufactured. Although there have been many studies conducted on monitoring the health of cutting tools under a specific cutting condition, the monitoring of tool wear across multi-cutting conditions still remains a challenging proposition. In addressing this, this paper presents a framework for monitoring the health of the cutting tool, operating under multi-cutting conditions. A predictive model, using advanced machine learning methods with multi-feature multi-model ensemble and dynamic smoothing scheme, is developed. The applicability of the framework is that it takes into account machining parameters, including depth of cut, cutting speed and feed rate, as inputs into the model, thus generating the key features for the predictions. Real data from the machining experiments were collected, investigated and analysed, with prediction results showing high agreement with the experiments in terms of the trends of the predictions as well as the accuracy of the averaged root mean squared error values.