Scalable and portable computational framework enabling online probabilistic remaining useful life (RUL) estimation. (July 2023)

• Record Type: Journal Article
• Authors: Lyathakula, Karthik Reddy; Yuan, Fuh-Gwo
• Is Part Of: Advances in engineering software. Volume 181(2023)
• Publication Date: 2023-07
• Subjects: Probabilistic remaining useful life estimation -- Uncertainty quantification -- Bayesian inference -- Markov chain Monte Carlo -- Sequential Monte Carlo -- High performance -- Computing -- Raspberry Pi cluster; Computer-aided engineering -- Periodicals; Engineering -- Computer programs -- Periodicals; Engineering -- Software -- Periodicals; Periodicals; 620.0028553
• DOI: 10.1016/j.advengsoft.2023.103461
• Languages: English
• ISSNs: 0965-9978

Abstract

Highlights: Demonstrated a generalized framework for probabilistic fatigue life estimation in adhesively bonded joints. Demonstrates workflow of using high-fidelity finite element simulations, and deep learning techniques for developing a generalized, scalable, portable, and compact framework for rapid probabilistic fatigue life estimation. Computational speed-up of two statistical sampling methods: the Markov chain Monte Carlo method and Sequential Monte Carlo are compared. Vectorized crack propagation simulations are introduced to enhance the computational time for statistical modeling. The portability and compactness of the framework are demonstrated by deploying on the Raspberry-Pi cluster. Abstract: This work demonstrates a framework that enables online prognostics in adhesive joints by estimating the real-time probabilistic remaining useful life (RUL) using ANNs based hybrid physics models and vectorized sequential Monte Carlo (SMC) simulations. The framework is developed by integrating the physics-based damage degradation model and uncertainty quantification (UQ) techniques to estimate both probabilistic fatigue failure life and RUL. The fatigue damage growth (FDG) simulator, a hybrid surrogate model that simulates real-time fatigue degradation in adhesive joints, is used. In the initial set of results, the generalized framework is validated by estimating the probabilistic fatigue failure life using two UQ methods: Markov Chain Monte Carlo (MCMC) and SMC method. The computational results are successfully compared against experimental data. The conventional MCMC sampling methods are inherently serial, which limits the exploitation of the computational speed-up provided by the FDG simulator and hinders the real-time life predictions. The SMC method quantifies the uncertainties by parallelizing the sampling process, significantly reducing computational time and enabling real-time prediction. Next, the generalized framework is used to estimate probabilistic RUL from the fatigue crack propagation data. The parallel SMC method showed very good speedup compared to the MCMC method. To further enhance the computational speed-up with SMC method, vectorized FDG simulations are introduced into the framework and good scalability is achieved. Finally, the portability of the framework is demonstrated by deploying it on the portable Raspberry Pi cluster. Graphical abstract: Image, graphical abstract