Residual lifetime prediction for heterogeneous degradation data by Bayesian semi-parametric method

2025-04-22

AI Summary

Manufacturing variability induces heterogeneity in degradation data, rendering conventional assumptions of homogeneous populations invalid. To address this, this paper proposes a Bayesian semiparametric approach for probabilistic and precise individual remaining useful life (RUL) prediction. The core contribution lies in the first integration of a Dirichlet process mixture of normals with a transformation-based MCMC sampler, enabling a fully nonparametric degradation trajectory model. This framework obviates the need to pre-specify the number of subpopulations or parametric forms of degradation distributions, thereby supporting adaptive clustering of heterogeneous degradation paths and direct inference of individual RUL distributions. Experimental evaluation on both synthetic and real-world fatigue crack growth datasets demonstrates that the proposed method significantly outperforms classical parametric models in terms of robustness and predictive accuracy.

Technology Category

• Machine Learning: Bayesian Learning
• Reasoning under Uncertainty: Relational Probabilistic Models
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

Degradation data are considered for assessing reliability in highly reliable systems. The usual assumption is that degradation units come from a homogeneous population. But in presence of high variability in the manufacturing process, this assumption is not true in general; that is different sub-populations are involved in the study. Predicting residual lifetime of a functioning unit is a major challenge in the degradation modeling especially in heterogeneous environment. To account for heterogeneous degradation data, we have proposed a Bayesian semi-parametric approach to relax the conventional modeling assumptions. We model the degradation path using Dirichlet process mixture of normal distributions. Based on the samples obtained from posterior distribution of model parameters we obtain residual lifetime distribution for individual unit. Transformation based MCMC technique is used for simulating values from the derived residual lifetime distribution for prediction of residual lifetime. A simulation study is undertaken to check performance of the proposed semi-parametric model compared with parametric model. Fatigue Crack Size data is analyzed to illustrate the proposed methodology.

Problem

• Predict residual lifetime in heterogeneous degradation data
• Address high variability in manufacturing process sub-populations
• Develop Bayesian semi-parametric model for reliability assessment

Innovation

• Bayesian semi-parametric method for heterogeneous data
• Dirichlet process mixture models degradation paths
• MCMC technique simulates residual lifetime distribution