Performance Assessment and Optimization of the Ultra-High Speed Air Compressor in Hydrogen Fuel Cell Vehicles

Abstract

Air compressors in hydrogen fuel cell vehicles play a crucial role in ensuring the stability of the cathode air system. However, they currently face challenges related to low efficiency and poor stability. To address these issues, the experimental setup for the pneumatic performance of air compressors is established. The effects of operational parameters on energy consumption, efficiency, and mass flow rate of the air compressor are revealed based on a Morris global sensitivity analysis. Considering a higher flow rate, larger efficiency, and lower energy consumption simultaneously, the optimal operating combination of the air compressor is determined based on grey relational multi-objective optimization. The optimal combination of operational parameters consisted of a speed of 80,000 rpm, a pressure ratio of 1.8, and an inlet temperature of 18.3 °C. Compared to the average values, the isentropic efficiency achieved a 48.23% increase, and the mass flow rate rose by 78.88% under the optimal operational combination. These findings hold significant value in guiding the efficient and stable operation of air compressors. The comprehensive methodology employed in this study is applicable further to investigate air compressors for hydrogen fuel cell vehicles.

ML- and LSTM-Based Radiator Predictive Maintenance for Energy Saving in Compressed Air Systems

“…Studies on fault detection coupled with energy saving have been investigated [12][13][14][15][16][17]. Drakaki et al [12] surveyed recent work on machine learning (ML)-and Deep Learning (DL)-based induction motor predictive maintenance and then used power spectrum information as a feature for fault detection.…”

“…Rodriguez et al [15] provided a K-means clustering algorithm to predict faults for the predictive maintenance of wind turbines for energy saving, maximizing useful life, and maximizing productivity. Shi et al [16] considered a multi-objective optimization model for low energy consumption with higher flow rate and efficiency. However, they employed a traditional method, not ML technologies, and only planned to study unexpected component faults in future research.…”