Adaptive ECMS based on speed forecasting for the control of a heavy-duty fuel cell vehicle for real-world driving

Abstract

Aiming at reducing pollutant emissions, hydrogen and fuel cell hybrid electric vehicles (FCVs) represent a promising technological solution. In this scenario, this paper proposes an adaptive energy management strategy (A-EMS) based on speed forecasting for a heavy-duty FCV, in order to achieve stable battery charge sustenance in realistic driving conditions. A validated and optimized fuel cell system model has been integrated into a complete vehicle model developed in the GT-Suite environment. A short-term velocity prediction layer based on a long short term memory (LSTM) neural network has been built in the A-EMS framework. The network has been trained and tested with realistic driving data simulated by GT-Real Drive for routes of the Trans-European Transport Network. The vehicle speed prevision has been realized over different forecasting horizons (5, 10, and 20 s). The adaptive equivalent consumption minimization strategy (A-ECMS) combined with short-term vehicle speed prediction is the A-EMS core algorithm of the presented work. Its results are here compared with the standard ECMS (S-ECMS) for four different driving cycles, including both standardized (HDDT) and realistic driving profiles. Three different European routes, with varying characteristics and from different countries, have been selected to test the proposed strategy in various conditions. The short-term prediction layer achieves satisfactory forecasting accuracy, with a RMSE ranging from 1.76 km/h to 13.37 km/h. The A-ECMS provides an improved by an order of magnitude battery charge sustenance, evaluated in terms of maximum battery state of charge (SoC) variation and fluctuation degree, with a hydrogen consumption increase ranging from 3.76% to 11.40% compared to the S-ECMS, for which the driving cycle is supposed to be known beforehand. As an example, in the HDDT cycle, the absolute maximum SoC variation and its fluctuation degree are lowered by about 76% and 79%, respectively. In conclusion, the proposed A-ECMS demonstrated that it is applicable for real driving conditions without prior knowledge of the driving cycle while improving battery charge sustaining for a FCV.