An HDP-HMM based approach for tool wear estimation and tool life prediction

Abstract

Tool wear estimation and prediction are keys of maintenance decision-making for milling machine. Various discrete-state degradation models have been developed for tool wear estimation and prediction. However, previous research assume that the number of discrete wear states is fixed based on prior understanding of tool degradation process. To break this limitation, a data-driven approach based on Hierarchical Dirichlet process-Hidden Markov model (HDP-HMM) is proposed. The number of states, transition probability matrix and omission probability distribution of hidden Markov model (HMM) can be automatically updated using observation data through a hierarchical Dirichlet process (HDP). Compared with weighted HMM and Conventional HMM, experiments on real data from high-speed CNC milling machine cutters demonstrates that the proposed approach yielded greater accuracy on tool wear estimation and kept a high reliability in tool life prediction.

Keywords:

• Tool wear estimation
• tool life prediction
• Hidden Markov models
• hierarchical Dirichlet process (HDP)
• predictive models

Additional information

Funding

This research was partially financed by National Natural Science Foundation of China (Grant Nos. 71701008 and 51875018) and National Key R&D Program of China 2018YFB1403300.

Notes on contributors

Danyang Han

Danyang Han is a PhD candidate in the School of Instrumentation Science and Opto-electronics Engineering at Beihang University, Beijing, China. He received his bachelor’s degree from the Ocean University of China in 2017. His research interests focus on prognostic and health management technologies.

Jinsong Yu

Jinsong Yu is an associate professor in the School of Automation Science and Electrical Engineering at Beihang University, Beijing, China. He received his PhD degree from Beihang University in 2004. From 2013 to 2014, he was a visiting scholar at the University of Canterbury, Christchurch, New Zealand. His research interest includes prognostic and health management technologies, instrumentation, and measurement technologies.

Diyin Tang

Diyin Tang is a lecturer in the School of Automation Science and Electrical Engineering at Beihang University, Beijing, China. She received her Bachelor and Ph.D. degrees from Beihang University, Beijing, China in 2008 and 2015, respectively. From 2012 to 2013, she was a visiting Ph.D. student in the Department of Mechanical and Industrial Engineering at University of Toronto, Canada. Her research interests include optimization for condition-based maintenance and degradation-based modeling.