Tool wear mechanism, monitoring and remaining useful life (RUL) technology based on big data: a review

Abstract

AbstractTool wear is a key factor affecting many aspects of metal cutting machining, including surface quality, machining efficiency and tool life. As machining continues to evolve towards intelligence, hot spots and trends in tool wear-related research are also changing. However, in the current research on tool wear, there are still no recognized most effective tool wear suppression methods, signals are easily disturbed, low efficiency of signal processing methods and poor model generalization ability, etc. Therefore, a comprehensive summary and outlook of tool wear-related research is urgently needed, on the basis of which it is important to predict the hot spots and trends in tool wear research. In this paper, the current state of research on tool wear is systematically described from three aspects: tool wear mechanism, online monitoring and RUL (remaining useful life) prediction, and the shortcomings of tool wear-related research are pointed out. After an in-depth discussion, this paper also foresees the development trends of tool wear related research: (1) tool wear suppression research based on new technologies; (2) online monitoring and RUL prediction technology based on the fusion of data, features and pattern recognition; (3) intelligent, self-learning and self-regulating intelligent machining equipment that integrates multiple objectives (e.g. tool wear, chatter and remaining bearing life, etc.); (4) based on big data, the application of data-driven algorithms in tool wear mechanism, online monitoring and RUL prediction.