Fusion of heterogeneous data for robust degradation prognostics

2025-06-06

AI Summary

To address the challenges of heterogeneous data fusion and insufficient robustness in remaining useful life (RUL) estimation for industrial equipment degradation prediction, this paper proposes a physics-informed, data-driven framework. First, kernel density-based sensitivity analysis quantifies the impact of uncertain inputs on outputs, enabling a Bayesian prior fusion mechanism that iteratively updates the probabilistic models of input variables. Second, an aggregation strategy for surrogate modeling significantly accelerates computationally expensive degradation simulations. The method seamlessly integrates physical models with multi-source heterogeneous data. Evaluated on a crack propagation toy model and a nuclear power plant steam generator fouling simulation, it reduces output uncertainty by 32%–47% and enables reliable RUL estimation under intermittent observations. Key innovations include: (i) the first synergistic framework combining kernel density sensitivity analysis with Bayesian probabilistic modeling, and (ii) an efficient, degradation-oriented surrogate modeling paradigm.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Intelligent Robots: State Estimation
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Assessing the degradation state of an industrial asset first requires evaluating its current condition and then to project the forecast model trajectory to a predefined prognostic threshold, thereby estimating its remaining useful life (RUL). Depending on the available information, two primary categories of forecasting models may be used: physics-based simulation codes and datadriven (machine learning) approaches. Combining both modelling approaches may enhance prediction robustness, especially with respect to their individual uncertainties. This paper introduces a methodology for fusion of heterogeneous data in degradation prognostics. The proposed approach acts iteratively on a computer model's uncertain input variables by combining kernel-based sensitivity analysis for variable ranking with a Bayesian framework to inform the priors with the heterogeneous data. Additionally, we propose an integration of an aggregate surrogate modeling strategy for computationally expensive degradation simulation codes. The methodology updates the knowledge of the computer code input probabilistic model and reduces the output uncertainty. As an application, we illustrate this methodology on a toy model from crack propagation based on Paris law as well as a complex industrial clogging simulation model for nuclear power plant steam generators, where data is intermittently available over time.

Problem

• Fusing heterogeneous data for robust degradation prognostics
• Combining physics-based and data-driven models for RUL estimation
• Reducing uncertainty in degradation simulation codes

Innovation

• Fusion of heterogeneous data for robust prognostics
• Kernel-based sensitivity analysis with Bayesian framework
• Aggregate surrogate modeling for expensive simulations