Skip to main navigation Skip to search Skip to main content

Deep learning-assisted multi-dimensional lifecycle prediction and optimization of protonic ceramic electrolysis cells for sustainable hydrogen production

  • Zheng Li
  • , Nan Zheng
  • , Mengxuan Zeng
  • , Xi Chen
  • , Zhipeng Zhou
  • , Ruinan Wang
  • , Keqing Zheng
  • , Meng Ni

Research output: Journal article publication › Journal article › Academic research › peer-review

Abstract

To achieve multi-dimensional lifecycle optimization for enhancing the performance of protonic ceramic electrolysis cells (PCECs) for sustainable hydrogen production, this study presents a deep learning–assisted framework. This framework enables evaluation of the electrochemical, economic, and environmental performance of PCECs, thus providing a holistic understanding of their lifecycle behaviour. More importantly, a surrogate model, trained on a detailed 3D PCEC stack model, is developed using multi-head attention mechanism and long short-term memory network. It's found that inlet temperature is the most important parameter for the system performance, and higher temperature improves hydrogen yield but accelerates degradation. It is also found that increasing electrode porosity and stack operational lifetime strongly reduces environmental impacts of hydrogen production. Compared to a grid-powered PCEC system, a nuclear-powered PCEC system shows strong potential to reduce the hydrogen production cost and environmental cost by 17.9% and 70.0%, respectively. The optimization between hydrogen production, production costs, and environmental impacts identifies an optimal stack configuration with an operating life of 34.45 khr. The optimized production cost and environmental cost are 4.49 $/kg H2 and 0.46 $/kg H2, respectively. Overall, the proposed framework demonstrates the potential of AI-driven lifecycle modelling to guide the design of PCEC systems for realizing sustainable hydrogen production.

Original languageEnglish
Article number148221
JournalJournal of Cleaner Production
Volume557
DOIs
Publication statusPublished - 22 Apr 2026

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

  1. SDG 7 - Affordable and Clean Energy
    SDG 7 Affordable and Clean Energy
  2. SDG 12 - Responsible Consumption and Production
    SDG 12 Responsible Consumption and Production

Keywords

  • Hydrogen production
  • Levelized cost of hydrogen (LCOH)
  • Life cycle assessment (LCA)
  • Life cycle cost assessment (LCCA)
  • Protonic ceramic electrolysis cells (PCECs)

ASJC Scopus subject areas

  • Renewable Energy, Sustainability and the Environment
  • General Environmental Science
  • Strategy and Management
  • Industrial and Manufacturing Engineering

Fingerprint

Dive into the research topics of 'Deep learning-assisted multi-dimensional lifecycle prediction and optimization of protonic ceramic electrolysis cells for sustainable hydrogen production'. Together they form a unique fingerprint.

Cite this