Fast Bayesian equipment condition monitoring via simulation based inference: applications to heat exchanger health

2026-04-22

AI Summary

This work addresses the challenge of inferring implicit degradation parameters from uncertain, indirect sensor data in industrial equipment health monitoring—a task traditionally hindered by the computational expense of Bayesian methods that precludes real-time deployment. The study introduces amortized simulation-based inference (SBI) to this domain for the first time, integrating a thermal-fluid simulation model with neural density estimation to directly map observational data to full posterior distributions over degradation parameters, without requiring an explicit likelihood function. Evaluated across multiple synthetic fouling and leakage scenarios, the proposed approach achieves diagnostic accuracy comparable to Markov chain Monte Carlo (MCMC) while accelerating inference by 82×, thereby offering both reliable uncertainty quantification and near-real-time performance suitable for rapid fault diagnosis in digital twin applications.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Probabilistic Inference
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs

Abstract

Accurate condition monitoring of industrial equipment requires inferring latent degradation parameters from indirect sensor measurements under uncertainty. While traditional Bayesian methods like Markov Chain Monte Carlo (MCMC) provide rigorous uncertainty quantification, their heavy computational bottlenecks render them impractical for real-time process control. To overcome this limitation, we propose an AI-driven framework utilizing Simulation-Based Inference (SBI) powered by amortized neural posterior estimation to diagnose complex failure modes in heat exchangers. By training neural density estimators on a simulated dataset, our approach learns a direct, likelihood-free mapping from thermal-fluid observations to the full posterior distribution of degradation parameters. We benchmark this framework against an MCMC baseline across various synthetic fouling and leakage scenarios, including challenging low-probability, sparse-event failures. The results show that SBI achieves comparable diagnostic accuracy and reliable uncertainty quantification, while accelerating inference time by a factor of82$\times$ compared to traditional sampling. The amortized nature of the neural network enables near-instantaneous inference, establishing SBI as a highly scalable, real-time alternative for probabilistic fault diagnosis and digital twin realization in complex engineering systems.

Problem

• condition monitoring
• Bayesian inference
• uncertainty quantification
• heat exchanger
• real-time diagnosis

Innovation

• Simulation-Based Inference
• Amortized Neural Posterior Estimation
• Bayesian Condition Monitoring
• Heat Exchanger Diagnostics
• Real-time Uncertainty Quantification