Synapse
⌘+K
Synapse
PulseExploreJournal ClubResearchersJournals
Instagram
HomeJournal ClubExplore
March 26, 2026Case Studies in Thermal EngineeringOpen Access

A data-driven approach for multi-dimensional prediction of PEMFC performance using artificial neural networks

View Full Paper
Ask AI
Bookmark
Share

Authors

HLHuan LiuSLSichen LiuCZChenshuo Zhang

Discussion

Loading...

Member takes

Overview

Demonstrates enhanced performance prediction of PEMFCs using a multi-dimensional approach, suggesting improved monitoring and control strategies.

Key Points

  • This research aims to improve the prediction of PEMFC performance by integrating physical models with data-driven methods.
  • Developed a multi-dimensional prediction model using neural network algorithms.
  • Utilized geometric partitioning based on rib-priority.
  • Conducted relative standard deviation (RSD) convergence evaluation to reduce data volume.
  • Combined physical models with data-driven models for performance analysis.
  • Achieved mean absolute percentage error (MAPE) below 3% for performance predictions.
  • Obtained a coefficient of determination (R 2 ) over 0.998 for key parameters.
  • Improved prediction of characteristics like current density, reactant concentrations, water content, and temperature.

Cite This Study

Liu et al. (2026) studied this question.

synapsesocial.com/papers/69c4cd49fdc3bde4489197b0https://doi.org/10.1016/j.csite.2026.107970
View Full Paper
Ask AI
Bookmark
Share