Physics guided diffusion model improves rare event detection in hydrogen production
Physics-Guided Conditional Diffusion Model for Rare Event Synthesis and Diagnosis for the Water-Gas Shift Reaction
Machine Learning
Summary
Hydrogen production through the water-gas shift reaction can sometimes suffer from rare problems that reduce output and safety. But collecting data on these rare events is hard. The authors developed a new method that uses physics laws combined with a special AI model to create realistic fake data about these rare issues. This helps train better AI tools to detect and diagnose problems during hydrogen production safely.
What this means in practice
- •For industrial process engineers: Generate realistic rare-event data to improve monitoring and diagnosis of hydrogen production processes under abnormal conditions.
- •For chemical plant safety teams: Assess and score operating risks in hydrogen production to enhance process safety and prevent hazardous events.
Authors
Md Abrar Rafid Siddique, Bibek Aryal, Qiugang Lu
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.