汽车工程
自适应神经模糊推理系统
能源管理
计算机科学
电动汽车
控制理论(社会学)
工程类
功率(物理)
能量(信号处理)
模糊逻辑
人工智能
模糊控制系统
控制(管理)
数学
量子力学
统计
物理
作者
Aissa Benhammou,Mohammed Amine Hartani,Tedjini Hamza,Yacine Guettaf,Mohammed Amine Soumeur
标识
DOI:10.1016/j.isatra.2024.01.037
摘要
The issues faced by hybrid electric vehicles (HEVs) include locating and managing free energy to preserve resource dynamics and constraints while preserving prolonged autonomy. This study assessed a hybrid electric vehicle (HEV) equipped with a fuel cell (FC), battery, direct current generators (DCGs), and supercapacitor (SC) to meet the power needs of an automobile utilizing variable power converters. This study examines four HEV energy management strategies (EMSs), increasing clean environmental power penetration by utilizing the HEV's kinetic energy, as a new contribution. Strategies for Proportional-Integral (PI), State-Machine (SM), Artificial Neural Network (ANN), and Adaptive Neural Fuzzy Inference System (ANFIS) EMSs are discussed. In addition to implementing direct torque control with a space vector modulation-based ANFIS controller (ANFIS-DTC-SVM), this study proposes to insert DCGs in the front wheels of HEVs for free energy production. Simulations of EMSs yielded approximative findings, achieving a 22.2 (%) free-exploited kinetic energy. The ANN-based EMS surpassed the competition, yielding the highest energy efficiency 98.2 (%) and the lowest fuel consumption 48.68 (SI). As a result of maximizing battery utilization and limiting fuel consumption, the examined HEV's dependability and stability were confirmed and reached, highlighting the importance of kinetic energy.
科研通智能强力驱动
Strongly Powered by AbleSci AI