Data-Driven Prognostics Using Random Forests: Prediction of Tool Wear

Abstract

Manufacturers have faced an increasing need for the development of predictive models that help predict mechanical failures and remaining useful life of a manufacturing system or its system components. Model-based or physics-based prognostics develops mathematical models based on physical laws or probability distributions, while an in-depth physical understanding of system behaviors is required. In practice, however, some of the distributional assumptions do not hold true. To overcome the limitations of model-based prognostics, data-driven methods have been increasingly applied to machinery prognostics and maintenance management, transforming legacy manufacturing systems into smart manufacturing systems with artificial intelligence. While earlier work demonstrated the effectiveness of data-driven approaches, most of these methods applied to prognostics and health management (PHM) in manufacturing are based on artificial neural networks (ANNs) and support vector regression (SVR). With the rapid advancement in artificial intelligence, various machine learning algorithms have been developed and widely applied in many engineering fields. The objective of this research is to explore the ability of random forests (RFs) to predict tool wear in milling operations. The performance of ANNs, SVR, and RFs are compared using an experimental dataset. The experimental results have shown that RFs can generate more accurate predictions than ANNs and SVR in this experiment.