A5009564694- Fuel Cells and Related Materials
- Advanced Battery Technologies Research
- Electrocatalysts for Energy Conversion
- Electric and Hybrid Vehicle Technologies
- Fault Detection and Control Systems
- Electric Vehicles and Infrastructure
- Microgrid Control and Optimization
- Frequency Control in Power Systems
- Power Systems and Renewable Energy
- Advancements in Solid Oxide Fuel Cells
Northwestern Polytechnical University
2020-2025
Fault diagnosis is essential for the stable and efficient operation of proton exchange membrane fuel cell (PEMFC) system. However, manifold balance plant (BOP) components coupling phenomenon involving multiple physical fields will significantly increase probability system fault, which makes it difficult to realize a timely effective diagnosis. In this study, novel online method an open-cathode PEMFC proposed, only based on output voltage measurements, both normal state fault states caused by...
As a renewable and efficient power source, proton exchange membrane fuel cells (PEMFCs) are receiving more attention from the world, but it still has shortcomings with poor durability insufficient reliability, so purpose of this paper is to effectively improve reliability PEMFCs by data-driven fault diagnosis method. In method, principal component analysis (PCA) first adopted reduce dimensionality data. Then, classification method named eXtreme Gradient Boosting (XGBoost) which based on...
In this paper, a hybrid power system for electric vehicle with fuel cell stack and Lithium-ion battery is designed converters transferring are modeled. Besides, an improved state machine strategy developed to split the produced by sources. The rules avoid overcharging in high SOC over discharging low SOC, charge discharge frequently normal area while decreasing hydrogen consumption. simulation results verify that performs better than traditional strategy.
Fuel cell diagnosis is very important to ensure the reliability of its operation and application. The data-driven method concerned for simplicity accuracy. This paper proposes a fuel fault based on multi-Grained Cascade Forest (gcForest) principal component analysis (PCA). uses PCA reduce dimensionality data extract appropriate features. Based relatively simplified features, classification algorithm gcForest used diagnose status cell. Through experimental analysis, this proposed can quickly...