A novel health prognosis method for system based on improved degenerated Hidden Markov model. (December 2022)

• Record Type: Journal Article
• Authors: Liu, Qinming; Chen, Xiang; Dong, Ming; Chen, F. Frank
• Is Part Of: Robotics and computer-integrated manufacturing. Volume 78(2022)
• Publication Date: 2022-12
• Subjects: Hidden Markov model -- Degradation health diagnostics -- Residual useful lifetime -- Genetic algorithm -- Approximation algorithm; Robots, Industrial -- Periodicals; Computer integrated manufacturing systems -- Periodicals; Robotics -- Periodicals; Robots industriels -- Périodiques; Productique -- Périodiques; Robotique -- Périodiques; 670.285
• DOI: 10.1016/j.rcim.2022.102402
• Languages: English
• ISSNs: 0736-5845

Abstract

Highlights: An improved Degenerated Hidden Markov Model (DGHMM) with a core of the quasi power relation is presented based on prognostics information. The quasi power relation accelerated degradation can better describe the process that the performance of the system decreases gradually with the increase of service age. The model adopts the degradation factors described the process of recession for equipment continuous decreasing in performance. The improved genetic algorithm can replace the conventional EM algorithm for parameters estimation. An algorithm named greed approximation based on approximation algorithm and Viterbi algorithm can be proposed. Abstract: Health prognosis for power system is considered as a crucial process of condition-based maintenance. In order to solve the problem of large deviation between Hidden Markov Model and actual system health diagnosis, this paper developed an improved Degenerated Hidden Markov Model (DGHMM) with a core of the quasi power relation. First, the model adopts the degradation factors described the process of recession for equipment continuous decreasing in performance. Compared with the conventional exponential accelerated degradation, the quasi power relation accelerated degradation can better describe the process that the performance of the system decreases gradually with the increase of service age. Then, the improved genetic algorithm can replace the conventional EM algorithm for parameters estimation, which overcomes the limitation that the EM algorithm is easy to fall into local optimization. At the same time, in terms of the limitation of life prognosis problem as a result of the Hidden Markov Model must obey exponential distribution, an algorithm named greed approximation based on approximation algorithm and Viterbi algorithm can be proposed to seek maximum probability remaining observation for the purpose of seeking maximum probability dynamically surplus state path to predict the residual life of system. Finally, the proposed method is validated and evaluated with the data set of caterpillar hydraulic pumps. The results show that the method of system health diagnosis and life prognosis based on the improved degraded hidden Markov model is more effective in describing system degeneration and the accuracy of equipment state diagnosis, and is also feasible in the prediction of residual life.