Reliability assessment of heavy-duty computer numerical control machine tools based on multi-performance multi-sequence hidden Markov model

摘要

Reliability assessment is vital to improve the efficiency and availability of heavy-duty computer numerical control machine tools (HCNCMT). Traditional reliability assessment methods based on time-to-failure data are difficult to achieve timely and accurate reliability estimation. In this paper, a new multi-performance multi-sequence hidden Markov model is proposed for the reliability assessment of the HCNCMT by building the relationship model between machine running states and multiple key performance parameters. It significantly improves assessment accuracy by fully mining a large number of performance degradation data and provides better support for its maintenance. Finally, four heavy-duty gantry computer numerical control boring and milling machines are taken as examples to validate the effectiveness of the proposed method.