Data-driven prognostics based on time-frequency analysis and symbolic recurrent neural network for fuel cells under dynamic load

• Published in: Reliability engineering & system safety 2023-05, Vol.233 (May), p.109123, Article 109123
• Main Authors: Wang, Chu, Dou, Manfeng, Li, Zhongliang, Outbib, Rachid, Zhao, Dongdong, Zuo, Jian, Wang, Yuanlin, Liang, Bin, Wang, Peng
• Format: Article
• Language: English
• Subjects: Automatic; Dynamic load; Electric power; Empirical mode decomposition; Engineering Sciences; Proton exchange membrane fuel cell; Remaining useful life; Symbolic representation gated recurrent unit; Time-frequency-energy spectrum
• ISSN: 0951-8320; 1879-0836
• DOI: 10.1016/j.ress.2023.109123

•HHT-based method eliminates dynamic load noise and extracts degradation features.•Symbol-based GRU achieves reliable and efficient long-term prognostics.•Proposed data-driven method provides competitive prognostics horizon and accuracy.•Multiple failure thresholds can assess prognostics consistency and generalizability. Data-centric prognostics is beneficial to improve the reliability and safety of proton exchange membrane fuel cell (PEMFC). For the prognostics of PEMFC operating under dynamic load, the challenges come from extracting degradation features, improving prediction accuracy, expanding the prognostics horizon, and reducing computational cost. To address these issues, this work proposes a data-driven PEMFC prognostics approach, in which Hilbert-Huang transform is used to extract health indicator in dynamic operating conditions and symbolic-based gated recurrent unit model is used to enhance the accuracy of life prediction. Comparing with other state-of-the-art methods, the proposed data-driven prognostics approach provides a competitive prognostics horizon with lower computational cost. The prognostics performance shows consistency and generalizability under different failure threshold settings.