Bi-LSTM predictive control-based efficient energy management system for a fuel cell hybrid electric vehicle

Abstract

Energy management systems (EMS) in hybrid electric vehicles play a vital role in achieving optimal energy utilization, improved fuel efficiency, lower emissions, and improved vehicle performance. Thus, this paper proposes a Bidirectional Long-Term Memory (Bi-LSTM) model based on an efficient EMS for a hybrid electric vehicle that manages the powertrain elements of the IC engine, electric motor(s), fuel cell, and energy storage system. The proposed EMS also continuously monitors various parameters, including vehicle speed, driver inputs, battery state of charge, engine load, and environmental conditions, to make real-time decisions on power distribution and operation modes. Further, the proposed system leverages the capabilities of the Bi-LSTM model to capture intricate temporal dependencies and bidirectional context in driving patterns using the real-time dataset. Empirical studies are conducted to substantiate the efficacy of the proposed energy management strategy vis-à-vis diverse controllers, encompassing Model Predictive Control and Sliding Mode Control. Real-world driving data is employed as the basis for these investigations, aiming to provide a robust assessment of the proposed energy management approach in practical scenarios. Results demonstrate the efficacy of the suggested methodology compared to traditional EMS approaches, showcasing improvements in energy utilization and reduced environmental impact. Finally, this research emphasizes a comparative analysis of the proposed topology with the existing approaches in a real-world fuel cell hybrid electric vehicle system. The findings provide insights into the feasibility of deploying intelligent EMS strategies for improved sustainability and efficiency in a modern energy-efficient environment.