A Physically Segmented Hidden Markov Model Approach for Continuous Tool Condition Monitoring: Diagnostics and Prognostics

A Physically Segmented Hidden Markov Model Approach for Continuous Tool Condition Monitoring: Diagnostics and Prognostics
Title:
A Physically Segmented Hidden Markov Model Approach for Continuous Tool Condition Monitoring: Diagnostics and Prognostics
Other Titles:
IEEE Transactions on Industrial Informatics
Keywords:
Publication Date:
01 November 2012
Citation:
O. Geramifard, J.X. Xu, J.H. Zhou, X. Li,, "A Physically Segmented Hidden Markov Model Approach for Continuous Tool Condition Monitoring: Diagnostics and Prognostics", IEEE Trans.on Industrial Informatics, vol. 8, no. 4, pp. 964-973, Nov 2012.
Abstract:
In this paper, a temporal probabilistic approach based on hidden Markov model, named, physically segmented hidden Markov model with continuous output, is introduced for continuous tool condition monitoring in machinery systems. The proposed approach has the advantage of providing an explicit relationship between the actual health states and the hidden state values. The provided relationship is further exploited for formulation and parameter estimation in the proposed approach. The introduced approach is tested for continuous tool wear prediction in a CNC-milling machine and compared with two well-established neural network approaches, namely, multi-layer perceptron and Elman network. In the experimental study, the prediction results are provided and compared after adopting appropriate hyper-parameter values for all the approaches by cross-validation. Based on the experimental results, physically segmented hidden Markov Model approach outperforms the neural network approaches. Moreover, the prognosis ability of the proposed approach is studied.
License type:
PublisherCopyrights
Funding Info:
Description:
ISSN:
1551-3203
Files uploaded:

File Size Format Action
all-tii-11-579.pdf 1.41 MB PDF Open