From green hydrogen production to artificial intelligence–driven energy management in hydrogen fuel cell electric vehicles: a comprehensive review of technologies, optimization techniques, international standards, and investment programs

Hydrogen (H₂) has gained prominence as a critical vector in advancing the global decarbonization agenda and achieving net-zero emission targets. This paper offers a comprehensive and interdisciplinary assessment of global H₂ infrastructure development and examines the transformative role of Artificial Intelligence (AI) in hydrogen-based energy systems. Key international standards, including those from the American National Standards Institute (ANSI), the Canadian Standards Association (CSA Group), and the International Organization for Standardization (ISO), are reviewed to outline their approaches to safety, performance, and interoperability. The study also provides an overview of global H₂ infrastructure development through several major publicly funded projects in the United States and Europe. Furthermore, the research explores advanced AI techniques, such as Reinforcement Learning (RL), Neural Networks (NN), and Generative Adversarial Networks (GANs), which are employed to optimize energy management in Hydrogen Fuel Cell Electric Vehicles (HFCEVs). Machine Learning (ML) models are applied across the H₂ value chain to support real-time decision-making, enable predictive maintenance, and facilitate fault detection. In addition, the effectiveness of AI-driven energy management systems is assessed in hybrid Renewable Energy Sources (RES) configurations integrated with Fuel Cells (FCs), based on technical, operational, and sustainability metrics. The study also evaluates the performance of metaheuristic optimization algorithms, including Genetic Algorithm (GA), Particle Swarm Optimization (PSO), and Flower Pollination Algorithm (FPA), to optimize H₂ consumption and enhance system efficiency. Finally, the paper identifies key challenges across the H₂ energy landscape and outlines future research directions that are essential for accelerating innovation and enabling large-scale deployment.