Physics-Guided Conditional Diffusion Model for Rare Event Synthesis and Diagnosis for the Water-Gas Shift Reaction

2026-09-28

AI Summary

This study addresses the challenge of fault diagnosis in the water-gas shift reaction caused by the scarcity of rare abnormal operating condition data. We propose a data augmentation framework that integrates physical laws with conditional denoising diffusion probabilistic models. By incorporating reaction kinetics constraints as a physics-guided mechanism, the method ensures the thermodynamic consistency of synthetic data, thereby generating high-fidelity trajectories of rare events. Additionally, a hazard score metric is designed to quantify system risk. Experimental results demonstrate that this dual physics-data-driven approach significantly outperforms purely data-driven baselines, substantially improving both synthetic data quality and fault diagnosis accuracy under few-shot conditions. This work offers a novel paradigm for industrial process health management.

Abstract

As the world moves towards sustainable energy sources, hydrogen (H2) can be treated as an eco-friendly alternative to fossil fuels due to its high energy density and zero carbon emissions. The water-gas shift (WGS) reaction is a widely used industrial process for hydrogen production by converting carbon monoxide and steam into hydrogen and carbon dioxide. However, occurrences like severe fouling, catalyst deterioration, and thermal runaway can hamper the reaction kinetics/process safety and decrease the yield of H2. These incidents are rare, and gathering process data under such abnormal conditions is challenging. In this work, we propose a physics-guided conditional diffusion model to generate realistic rare-event trajectories for the WGS reaction. The proposed model integrates a conditional denoising diffusion probabilistic model (CDDPM) with governing laws of the reaction to generate physically consistent process trajectories. The conditioning features allow the model to produce high-quality synthetic profiles for rare-event domains that are typically beyond the training regimes. The generated rare-event trajectories then augment the raw dataset for a balanced distribution between normal and abnormal conditions. We further propose a hazard score to assess the risk severity of the operating condition based on the operating trajectory. Deep learning models are trained with the augmented dataset to diagnose the health status of the reaction. Simulation results show that the proposed physics-guided diffusion model outperforms data-driven models in terms of the quality of synthetic data and diagnosis performance for rare events.

Problem

• Water-Gas Shift Reaction
• Rare Event Synthesis
• Process Diagnosis
• Hydrogen Production
• Data Scarcity

Innovation

• Conditional Diffusion Model
• Physics-Guided Generation
• Rare Event Synthesis
• Hazard Score
• Fault Diagnosis