Hybrid physics–data model for real-time compressor aerodynamic performance prediction in fuel cells
- 6 July 2026
- journal article
- Published by SAGE Publications in International Journal of Engine Research
Abstract
In the actual operation of fuel-cell systems, providing the most accurate centrifugal compressor aerodynamic performance prediction in real-time is crucial for system efficiency and control. One key factor influencing the prediction is choke, which causes blade vibrations, limits the system’s maximum power and leads to a sharp decline in efficiency. However, the embedded multi-dimensional look-up tables typically necessitates a substantial amount of bench tests and makes extrapolation difficult. To address this, the study innovatively introduces a hybrid modeling framework that uses a small-sample physics-based model as a prior constraint and a data-driven method to compensate for physics-based prediction errors. The residual learning serves as a bridge trained with Gaussian process regression (GPR) by minimizing the root mean square error (RMSE). The hybrid model is implemented and validated on a fuel cell centrifugal compressor. Results show that, the physics-based prediction effectively constrains the shape of the characteristic curves, while the data-driven method significantly improves accuracy, especially in the choke region, with a 5% enhancement. In real-time prediction, as training samples expand, the accuracy improves further with the validation data almost all falling within the 95% confidence interval. The maximum training time is 20.96 s, indicating suitability for real-time prediction. This study highlights the potential of hybrid model of fuel-cell centrifugal compressors in engineering applications.Keywords
Funding Information
- Fundamental Research Funds for the Central Universities (Grant No. 2025MS020)
- Fundamental Research Funds for the Central Universities (Grant No. JB2023037)
- Natural Science Foundation of Beijing Municipality (Grant No. JQ24016)
This publication has 42 references indexed in Scilit:
- Experimental investigation of two-stage surge evolution and mechanism in a centrifugal compressor with variable geometry orificeAerospace Science and Technology, 2026
- Modeling of mixing losses of centrifugal compressors for supercritical carbon dioxide power cyclesApplied Thermal Engineering, 2025
- Characterization of complete compressor map using a multi-fidelity approach with low requirements of input working pointsAerospace Science and Technology, 2025
- Experimental study on the effects of compressor rotational speed on surge characteristics: Spatial and temporal frequenciesAerospace Science and Technology, 2024
- Optimum loss models for performance prediction of supercritical CO2 centrifugal compressorApplied Thermal Engineering, 2021
- Data-driven oxygen excess ratio control for proton exchange membrane fuel cellApplied Energy, 2018
- Air flow trajectory and surge avoidance of centrifugal compressor under variable pressure operation of automotive fuel cellsInternational Journal of Automotive Technology, 2016
- A component map tuning method for performance prediction and diagnostics of gas turbine compressorsApplied Energy, 2014
- Data-driven approach to machine condition prognosis using least square regression treeJournal of Mechanical Science and Technology, 2009
- Neural-network based analysis and prediction of a compressor’s characteristic performance mapApplied Energy, 2007