What is it about?
Proton exchange membrane fuel cells (PEMFCs) are important in the move towards clean energy and decarbonization of automotive power systems around the world. Adoption faces challenges such as changing component performance and degradation in real-world conditions. Data science models and artificial intelligence (AI) methods, including machine learning, neural networks, and hybrid physics-informed approaches, are applied to improve the reliability and efficiency of PEMFCs. Neural networks help with fault detection, spatial mapping of current distribution, and prediction of performance decline. Learning reinforcement is used to optimize cell humidity and identify thermal hotspots in single cell and fuel-cell stacks, which show the need for standardized and benchmarked AI-based diagnostic protocols. This review examines and compares current data science models for diagnosis in different operating scenarios, evaluates their success in forecasting chemical, electrochemical, and thermal failures, and explores the challenges and performance of these predictive tools in automotive fuel-cell applications. The findings support the development of regulatory standards and help speed up the industrial adoption of AI-driven and data science–based diagnostic solutions for fuel-cell technologies.
Featured Image
Why is it important?
PEMFCs are important for clean transportation and global decarbonization, but their large-scale adoption is limited by degradation, reliability, and performance variations under real-world operating conditions. AI and data science can address these challenges by enabling early detection, diagnosis, and prediction of fuel-cell failures. Machine learning, neural networks, reinforcement learning, and physics-informed hybrid models can monitor complex parameters such as voltage, current distribution, temperature, humidity, and pressure. These approaches can identify flooding, drying, thermal hotspots, catalyst degradation, membrane failure, and performance deterioration before severe damage occurs. The importance of this review lies in its systematic comparison of data-driven diagnostic approaches across chemical, electrochemical, and thermal failure mechanisms, while considering both single cells and fuel-cell stacks. It also highlights the limitations of current models, including insufficient benchmark datasets, inconsistent validation methods, limited real-world data, and poor standardization. Establishing standardized datasets, diagnostic protocols, and performance metrics is essential for reliable AI deployment. Ultimately, AI-driven diagnostics can support predictive maintenance, extend PEMFC lifetime, improve efficiency and safety, reduce operating costs, and accelerate the commercial and automotive adoption of hydrogen fuel-cell technologies.
Perspectives
The future of PEMFC technology will depend not only on improving materials and cell architecture but also on developing intelligent, self-diagnostic fuel-cell systems. AI and data science provide an opportunity to shift PEMFC operation from conventional monitoring toward predictive and adaptive management. A key perspective is that future diagnostic models should move beyond laboratory-based accuracy toward generalizable, real-time, and physics-aware prediction under dynamic automotive conditions. Combining sensor data with electrochemical, thermal, and transport models could improve the reliability and interpretability of AI predictions. The field also needs standardized datasets, benchmark operating conditions, common evaluation metrics, and explainable AI frameworks. These are essential for meaningful comparison between models and for regulatory acceptance. Ultimately, the integration of AI + physics-based modelling + digital twins + real-time sensing could enable PEMFCs to become self-monitoring systems capable of predicting degradation, optimizing operating conditions, and extending stack lifetime. Such advances could significantly reduce maintenance and replacement costs while improving safety and reliability, thereby accelerating the transition of PEMFCs from research laboratories to durable, commercially viable automotive power systems.
Dr. Shankar Raman Dhanushkodi
University of British Columbia
Read the Original
This page is a summary of: Review on Data Science Models Used in Diagnosis of Polymer Electrolyte Membrane Fuel Cells, Fuel Cells, June 2026, Wiley,
DOI: 10.1002/fuce.70118.
You can read the full text:
Contributors
The following have contributed to this page
