Abstract
The implementation of Hybrid Electric System (HES) is eagerly anticipated for its incorporation of cutting-edge technologies including Fuel ceel, battery and ultracapacitor. This technology is designed for electric vehicles because of its dependability. Therefore, an artificial intelligence and optimization-based Energy management system in Electric Vehicles was proposed. The battery and ultracapacitor cooperate to give extra power, such as initial acceleration and vehicle climbing. The ultracapacitor is coupled to the DC bus in parallel through a bidirectional DC-DC converter, allowing it to produce peak power and recover braking energy, alleviating pressure on the fuel cell system and battery. This increases battery life by seeking minimal charging and discharging. The energy management is aided by the CNN model, which employs the characteristics of the fuel cell, UC, battery, and EV. Along with such data, the EV's braking and accelerating impacts are taken into account. Speed, acceleration, (Battery's state of charge, voltage, current), (UC's SOC, current, voltage), (fuel cell's voltage and current), necessary power, and efficiency are all inputs to the proposed CNN model, which predicts the vehicle's speed and driving behaviour. To contribute to effective energy management, the CNN model's weights are optimally tuned using the suggested PP-SSO Algorithm, which is a standardized concept of the SSA Algorithm. Thus, the experimental evaluation and analysis will be carried out in MATLAB. Lastly, the supremacy of the suggested technique is established by means of performance indices.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call