Data-Driven Multi-Type and Multi-Level Fault Diagnosis of Proton Exchange Membrane Fuel Cell Systems Using Artificial Intelligence Algorithms

To improve the durability of Proton-exchange membrane fuel cell (PEMFC) in actual transportation application scenario, the research on fault diagnosis of PEMFC is receiving extensive attention. With the development of artificial intelligence, performing fault diagnosis with the massive sampling data of the fuel cell system has become a popular research topic. But few people have successfully verified the diagnosis performance of these artificial intelligence algorithms on a real high power on-board PEMFC system. Therefore, we intend to make a step forward with these data-driven artificial intelligence algorithms. We applied four data-driven artificial intelligence algorithms to diagnose three common faults of PEMFC (each fault type has two severity levels, slight and severe). AVL CRUISE M was firstly applied for generation of simulation fault dataset to speed up the algorithm screening process. Based on the dataset, these algorithms are trained and optimized. The trained artificial intelligence models were compared in terms of robustness, computational efficiency, precision, and storage space requirement. Algorithms that perform well on the simulation dataset were selected for experimental verification. They were transplanted and tested on the system controller in real time and demonstrated a high diagnostic precision. The work of this paper shows the potential of artificial intelligence algorithms in PEMFC fault diagnosis. The main research contents of this paper are as follows:

• Use AVL CRUISE M to simulate fault data.
• Use four data-driven artificial intelligence algorithms to diagnose faults based on simulation data.
• Run the algorithm on the controller and use the experimental data for verification.
• The selected algorithms can achieve 92.3% and 82.0% precision on the controller with 52.21 ms and 54.24 us respectively.