A Digital Twin approach based on nonparametric Bayesian network for complex system health monitoring. (January 2021)

• Record Type: Journal Article
• Authors: Yu, Jinsong; Song, Yue; Tang, Diyin; Dai, Jing
• Is Part Of: Journal of manufacturing systems. Volume 58(2021)Part B
• Page Start: 293
• Page End: 304
• Publication Date: 2021-01
• Subjects: Digital Twin -- Health monitoring -- Nonparametric Bayesian networks -- Dirichlet process mixture model; Manufacturing processes -- Periodicals; Production engineering -- Data processing -- Periodicals; Robots, Industrial -- Periodicals; Production, Technique de la -- Informatique -- Périodiques; Robots industriels -- Périodiques; Electronic journals; 670.42
• DOI: 10.1016/j.jmsy.2020.07.005
• Languages: English
• ISSNs: 0278-6125

Abstract

Highlights: A Digital Twin approach based on nonparametric Bayesian network is proposed for health monitoring in prognostic and health management (PHM). The Digital Twin model is updated based on Gaussian particle filtering (GPF) and Dirichlet process mixture model (DPMM) in real time. DPMM can learn the number and distribution of hidden variables through data, thus effectively learning the model structure autonomously. A Digital Twin model of an electro-optical system based on Modulation Transfer Function (MTF) as a health indicator was established. Abstract: This paper proposes a Digital Twin approach for health monitoring. In this approach, a Digital Twin model based on nonparametric Bayesian network is constructed to denote the dynamic degradation process of health state and the propagation of epistemic uncertainty. Then, a real-time model updating strategy based on improved Gaussian particle filter (GPF) and Dirichlet process mixture model (DPMM) is presented to enhance the model adaptability. On one hand, for those parameters in the nonparametric Bayesian network with prior models, the improved GPF is used to update them in real time. On the other hand, for parameters lacking a prior model, DPMM is proposed to learn hidden variables, which adaptively update the model structure and greatly reduce uncertainty. Experiments on the electro-optical system are conducted to validate the feasibility of the Digital Twin approach and verify the effectiveness of the nonparametric Bayesian network. The results of comparative experiments prove that the Digital Twin approach based on nonparametric Bayesian Network has a good model self-learning ability, which improves the accuracy of health monitoring.