Online monitoring model of micro-milling force incorporating tool wear prediction process

Abstract

In modern manufacturing, micro-milling technology plays an essential role in manufacturing high-precision and complex micro-size parts. Exploring the changing rule of time-varying cutting is of great significance for understanding the micro-milling mechanism and improving the machining efficiency. In addition, tool wear identification and updating in advance can enhance the accuracy and sustainability of micromachining. This paper presents a tool wear prediction framework for micro-milling by a temporal convolution network, bi-directional long short-term memory, and the multi-objective arithmetic optimization algorithm. Then, a new integrated model for real-time micro-milling cutting force monitoring is constructed, considering tool deformation, tool runout, time-varying cutting coefficient, chip separation state, and tool wear estimation results. Based on the micro-milling experiment with workpiece material Al6061, the accuracy of the proposed tool wear prediction and cutting force model is verified. The developed model can provide theoretical guidance for statics and dynamics analysis in the micro-milling.