Neural Network- and Fuzzy Control-Based Energy Optimization for the Switching in Parallel Hybrid Two-Wheeler

Abstract

Optimization of a two-wheeler hybrid electric vehicle (HEV) is a typical challenge compared to that for four-wheeler HEVs. Some of the challenges which are particular to two-wheeler HEVs are throttle integration, smooth switching between power sources, add-on weight compensation, efficiency improvisation in traffic, and energy optimization. Two power sources need to be synchronized skillfully for optimum energy utilization. A prominent variant of HEV is that it easily converts conventional scooters into parallel hybrids by “Through-the-Road (TTR)” architecture. This paper focuses on three switching control strategies of HEVs based on the state of charge, fuzzy logic, and neural network. Further, to optimize energy usage, all these control strategies are compared. Energy management control for the TTR model is developed with vehicle parameters in the Simulink environment and simulated using the “World Harmonized Motorcycle Test Cycle” (WMTC) drive cycle. The multivariable input model is presented with a fuzzy rule-based hybrid switching control. A similar system is also modeled with a neural network-based decision control and the observations are tabulated for the fuel economy and energy management. Simulation results show that the neural network-based optimization results in minimal energy consumption among all three hybrid operations.

Energy Management in Hybrid Electric and Hybrid Energy Storage System Vehicles: A Fuzzy Logic Controller Review

“…Sabri et al applied FLC-based EMS in a TTR HEV, achieving a 62% reduction in fuel consumption compared to rule-based EMS [22]. Narwade et al compared FLC and Neural Network (NN) EMS for a two-wheeler TTR parallel HEV, with NN EMS demonstrating superior performance based on total energy consumed [55]. Geng et al proposed FLC EMS in a fuel cell extended-range vehicle, demonstrating improved performance in terms of acceleration time and total mileage [56].…”

Machine Learning and Optimization in Energy Management Systems for Plug-In Hybrid Electric Vehicles: A Comprehensive Review

“…The literature, as encapsulated in references [71,[126][127][128]136,[162][163][164][165], underscores the wide-ranging applications and empirical validations of this combined approach. These references likely detail specific instances where the fuzzy logic and neural network synergy has been applied successfully, showcasing its effectiveness in optimizing energy distribution, improving fuel efficiency, and enhancing overall vehicle performance.…”

Hardware-in-the-Loop Scheme of Linear Controllers Tuned through Genetic Algorithms for BLDC Motor Used in Electric Scooter under Variable Operation Conditions

“…To perform the prognostic, first, a diagnostic bond graph (DBG) model of the electric scooter was developed, later sub models were obtained through structural model decomposition, the ACS estimated distributed faults, and the ELM modeled the intermittent fault degradation. In another case, the research presented in [15] described the energy optimization of a two-wheeler hybrid electric vehicle (HEV). First, a through-the-road (TTR) parallel HEV system structure was proposed and modeled, and then three control strategies were switched, considering the state of the charge, fuzzy logic, and a neural network.…”