Adaptive power management of hybrid electric vehicle with neural based PID controller

Abstract

The term hybrid electric vehicle depicts the form of a hybrid vehicle which has two or more than two sources of energy used as the input of the vehicle. Designing and modeling of the hybrid vehicle is more or less a new barrier for this work, so we take the standard consideration for the every parameter used in designing of hybrid vehicle model. The main objective of the paper is to focus on the control strategies used in the hybrid electric vehicle such that, the motor torque-speed characteristics are capable of following the unknown load. Unknown load in this case refers to the unknown velocity pattern of the driver behind the wheels. After testing the system with standard drive cycles, we concluded that the tracing of the reference drive cycle can be made error free or error can be reduced by using the Neural based PID controller rather than the traditional PID controller. Not only the standard drive cycles, but with a suitably trained neural network, random cycles can also be accurately traced.