Artificial intelligence based robust nonlinear controllers optimized by improved gray wolf optimization algorithm for plug-in hybrid electric vehicles in grid to vehicle applications

The paper proposes a control strategy for a plug-in hybrid electric vehicles (PHEVs) system that integrates a photovoltaic (PV) based renewable energy system (RES) and battery and supercapacitor (SC) based energy storage systems (ESS). In the proposed system, a current fed converter is implemented for the photovoltaic and supercapacitor which is a power electronic converter that operates by controlling the current flow in the circuit. The benefit of these converters is that core saturation and shot through cannot lead to device failure or half cycle symmetry. This is a feature of silicon controlled rectifier (SCR) based converters and is a key factor in the increased durability of these converters. A power bi-directional converter is employed for the battery in the EV system. This converter enables the battery to both charge and discharge power as required by the system which facilitates the energy flow between the battery and the rest of the system, allowing efficient energy management and utilization within the plug-in hybrid electric vehicles. Additionally, to efficiently utilize the photovoltaic system, an artificial neural network (ANN) is employed to determine the maximum power points (MPPs). A robust nonlinear higher order super twisting sliding mode controller (STSMC) and integral terminal sliding mode controller (ITSMC) have been designed for PHEVs to reduced chattering phenomena. Tables V to X provides a detailed comparison of error performance metrics and transient response characteristics for the state of charge of a renewable energy system and energy storage systems under the control of the optimized STSMC and ITSMC. The global asymptotic stability of the control approach is verified using Lyapunov stability analysis. Finally, MATLAB/Simulink and a hardware-in-the-loop (HIL) experiments are done to show the behavior of proposed system (Pirouzi et al., 2022).