Data-driven fault diagnosis for PEMFC systems of hybrid tram based on deep learning
| Autor: | Weirong Chen, Xuexia Zhang, Jingzhe Zhou |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Inlet temperature
Renewable Energy Sustainability and the Environment business.industry Computer science Deep learning Energy Engineering and Power Technology Proton exchange membrane fuel cell Small sample 02 engineering and technology 010402 general chemistry 021001 nanoscience & nanotechnology Condensed Matter Physics computer.software_genre 01 natural sciences Fuzzy logic 0104 chemical sciences Data-driven Deep belief network Fuel Technology Artificial intelligence Data mining 0210 nano-technology business Cluster analysis computer |
| Zdroj: | International Journal of Hydrogen Energy. 45:13483-13495 |
| ISSN: | 0360-3199 |
| DOI: | 10.1016/j.ijhydene.2020.03.035 |
| Popis: | The running state of the hybrid tram and the service life of fuel cell stacks are related to the fault diagnosis strategy of the proton exchange membrane fuel cell (PEMFC) system. In order to accurately detect various fault types, a novel method is proposed to classify the different health states, which is composed of simulated annealing genetic algorithm fuzzy c-means clustering (SAGAFCM) and deep belief network (DBN) combined with synthetic minority over-sampling technique (SMOTE). Operation data generated by the tram are clustered by SAGAFCM algorithm, and valid data are selected as fault diagnosis samples which include the training sample and the test sample. However, the fault samples are usually unbalanced data. To reduce the influence of unbalanced data on the fault diagnosis accuracy, SMOTE is employed to form a new training sample by supplementing the data of the small sample. Then DBN is trained by the new training sample to obtain the fault diagnosis model. In this paper, the proposed method can well distinguish the four health states, which are high deionized water inlet temperature fault, hydrogen leakage fault, low air pressure fault and the normal state, with an accuracy of 99.97% for the training sample and 100% for the test sample. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect