Anti-Interference Dynamic Integral Neural Network for Optimizing Energy Management in Retrofitted Hybrid Electric Vehicles

The use of hybrid electric vehicles (HEVs) is growing due to their efficiency in lowering pollutants and fuel consumption. Retrofitting existing fuel-powered engines with additional electrical power components allows for a simpler and more effective way to convert them into HEVs. Nevertheless, despite the possibility to decrease CO2 emissions and fuel usage compared to traditional vehicles, HEVs are still worse concerning the pollutants’ emissions than pure electric equivalents. Secondly, retrofitting process sometimes may lead to less effective generation of power as integration of old technologies of engines into existing efficient electrical systems which hinder the optimal utilization of efficiencies. To avoid these drawbacks, this manuscript presents an approach for improving EM in retrofitted HEVs. To this end the following type of technique is presented called the Anti-Interference Dynamic Integral Neural Network (AIDINN). The objective of this method is to minimize energy consumption and greenhouse gas, as well as fuel, emissions in HEVs. Thus, by predicting the speed and style of EV, AIDINN ensures proper utilization of the energy resources with limited energy waste and enhancing the efficiency of the vehicles. The proposed technique is implemented in MATLAB and compared with various existing approaches, including Artificial Neural Networks (ANN), Convolutional Neural Network (CNN), Genetic Algorithm (GA), Clustering and Disjoint Principal Component Analysis (CDPCA) and Finite Element Analysis (FEA). The proposed AIDINN method achieves an efficiency of 98.7%, a fuel consumption rate of 115 ml, and emissions of 0.7 g/km. These outcomes confirm the superiority of the AIDINN in optimizing EM in retrofitted HEVs, effectively reducing fuel consumption and emissions while maximizing overall efficiency.