A data-driven digital-twin prognostics method for proton exchange membrane fuel cell remaining useful life prediction

Prognostics and health management of proton exchange membrane fuel cell (PEMFC) systems have driven increasing research attention in recent years as the durability PEMFC stack remains a technical barrier for its large-scale commercialization. To monitor state during operation, digital twin (DT), smart manufacturing technique, is applied this paper to establish an ensemble remaining useful life prediction system. A data-driven DT constructed integrate physical knowledge system deep transfer learning model based on stacked denoising autoencoder used update with online measurement. case study experimental degradation data presented where proposed prognostics method has reached high accuracy. Furthermore, predicted results are proved be less affected even limited measurement data.