Skip to Content
You are currently on the new version of our website. Access the old version .
Applied SciencesApplied Sciences
  • Article
  • Open Access

5 April 2026

19 Pages

High-Efficiency Methanol Steam Reformer with Artificial Intelligence Complex System Response (AICSR) Optimized Pd–CuZn Catalysts for Portable Hydrogen Generation

,
,
and
1
Department of Engineering and System Science, National Tsing Hua University, Hshinchu 300044, Taiwan
2
Chemistry Department, National Tsing Hua University, Hshinchu 300044, Taiwan
3
Research Center for Applied Sciences, Academia Sinica, Taipei City 115201, Taiwan
*
Author to whom correspondence should be addressed.
This article belongs to the Section Energy Science and Technology

Abstract

We engineered a compact methanol steam reforming (MSR) system tailored to power a 1 kW High-Temperature Proton Exchange Membrane (HT-PEM) fuel cell. The unit integrates an evaporator, reformer, and burner within a cylindrical titanium-alloy vacuum flask to minimize parasitic heat loss. Guided by an Artificial Intelligence Complex System Response (AICSR) framework, we developed a segmented catalyst architecture that positions an optimized Pd/ZnO/Al2O3 catalyst downstream of a commercial Cu–Zn catalyst bed. This spatial configuration reduces palladium consumption by >50% while maintaining a hydrogen generation rate of 8000 sccm at 250 °C. During a 40 h stability test, the system exhibited a low deactivation rate of 0.235% h−1, with methanol conversion decaying gradually from 98.1% to 88.7%. The downstream PdZn intermetallic phase actively promoted the water–gas shift (WGS) reaction, restricting CO concentration to an average of 3.9% (minimum 2.5%). Achieving a system thermal efficiency of 88.589% and a 20 min startup time, this design validates AI-assisted spatial catalyst distribution as a highly viable strategy for compact hydrogen generation.

Article Metrics

Citations

Article Access Statistics

Multiple requests from the same IP address are counted as one view.