Hidden semi-Markov model (HSMM) has been widely used in equipment condition monitoring. However, the HSMM is usually modeled in fixed working mode. It is incompetent to monitor the condition when the working mode is time-varying. In this paper, taking time-varying working mode into account, we propose a novel switching hidden semi-Markov model (SHSMM) to represent the degradation process. The reciprocal of duration is modeled and utilized to quantize the influence of working mode on the degradation process. Compared to traditional HSMM and time-varying HMM, the proposed SHSMM has a more generalized form and a more powerful ability to describe the degradation process with time-varying working mode. The proposed SHSMM is then applied to tool wear monitoring (TWM) with time-varying cutting mode. Experimental results show that, via the proposed SHSMM, the monitoring confidence increases and the estimation of remaining useful life (RUL) has a great improvement.

Mechanistic cutting force model has the potential for monitoring micro-milling tool wear. However, the existing studies mainly consider the linear cutting force model, and they are incompetent to monitor the micro-milling tool wear which has a significant nonlinear effect on the cutting force due to the cutting-edge radius size effect. In this study, a nonlinear mechanistic cutting force model considering the comprehensive effect of cutting-edge radius and tool wear on the micro-milling force is constructed for micro-milling tool wear monitoring. A stepwise offline optimization approach is proposed to estimate the multiple parameters of the model. By minimizing the gap between the theoretical force expressed by the nonlinear model and the force measured in real-time, the tool wear condition is online monitored. Experiments show that, compared with the linear model, the nonlinear model has significantly improved cutting force prediction accuracy and tool wear monitoring accuracy.