A novel regenerative braking energy recuperation system for electric vehicles based on driving style

被引:12
作者
Qiu, Chengqun [1 ,2 ]
Wan, Xinshan [2 ]
Wang, Na [2 ]
Cao, Sunjia [2 ]
Ji, Xinchen [2 ]
Wu, Kun [3 ]
Hu, Yaoyu [4 ]
Meng, Mingyu [5 ]
机构
[1] Jiangsu Univ, Sch Automot & Traff Engn, Zhenjiang 212013, Peoples R China
[2] Yancheng Teachers Univ, Jiangsu Prov Intelligent Optoelect Devices & Measu, Yancheng 224007, Jiangsu, Peoples R China
[3] Yancheng Inst Technol, Sch Mech Engn, Yancheng 224051, Jiangsu, Peoples R China
[4] Tsinghua Univ, Dept Math Sci, Beijing 100084, Peoples R China
[5] Tokyo Inst Technol, Interdisciplinary Grad Sch Sci & Engn, Yokohama 2268502, Japan
基金
中国国家自然科学基金;
关键词
Electric vehicles; Energy recovery; Driving style; Regenerative braking; Recovery management strategy; CONTROL STRATEGY; BEHAVIOR; DRIVER; MODEL; SIMULATIONS; IMPROVEMENT; EFFICIENCY; RECOVERY; IMPACT;
D O I
10.1016/j.energy.2023.129055
中图分类号
O414.1 [热力学];
学科分类号
摘要
The regenerative braking energy recovery system of pure electric vehicle is to recover and reuse the consumed driving energy under the premise of ensuring the braking safety. In this paper, the regenerative braking energy recovery system of pure electric vehicle was optimized based on driving style, and the driver model is constructed and the parameters that characterise driving style are determined. BLSTM (Bidirectional Long Short Term Memory) neural network model method was introduced for deep self-learning, and IDP (Iterative dynamic programming)-BLSTM based regenerative braking energy recovery management control strategy was established. Through theoretical analysis and numerical model of the system, the results of parameter representation of the energy system were preliminarily evaluated and road test was carried out. The results of real vehicle test show that IDP-BLSTM method can meet the personalized requirements of various drivers, improve driving experience and safety, and recover braking energy efficiently.
引用
收藏
页数:16
相关论文
共 43 条
  • [1] Andras Sasfi, 2023, Automatica, V155
  • [2] Fuel saving and lower pollutants emissions using an ethanol-fueled engine in a hydraulic hybrid passengers vehicle
    Barbosa, Tarsis Prado
    Eckert, Jony Javorski
    Roso, Vinicius Ruckert
    Pacheco Pujatti, Fabricio Jose
    Rodrigues da Silva, Leonardo Adolpho
    Horta Gutierrez, Juan Carlos
    [J]. ENERGY, 2021, 235
  • [3] Solving mixed classical and fractional partial differential equations using short-memory principle and approximate inverses
    Bertaccini, Daniele
    Durastante, Fabio
    [J]. NUMERICAL ALGORITHMS, 2017, 74 (04) : 1061 - 1082
  • [4] Impact of driving characteristics on electric vehicle energy consumption and range
    Bingham, C.
    Walsh, C.
    Carroll, S.
    [J]. IET INTELLIGENT TRANSPORT SYSTEMS, 2012, 6 (01) : 29 - 35
  • [5] Chao Yang, 2021, Energy, P219
  • [6] Chen Zheng, 2023, Energy, P263
  • [7] SVR approach for predicting vehicle velocity for comfortable ride while crossing speed humps
    Darwiche, Mohamad
    Mokhiamar, Ossama
    [J]. ALEXANDRIA ENGINEERING JOURNAL, 2022, 61 (08) : 6119 - 6128
  • [8] Self-reported frequency and perceived difficulty of adopting eco-friendly driving behavior according to gender, age, and environmental concern
    Delhomme, Patricia
    Cristea, Mioara
    Paran, Francoise
    [J]. TRANSPORTATION RESEARCH PART D-TRANSPORT AND ENVIRONMENT, 2013, 20 : 55 - 58
  • [9] An innovative real-time test setup for ADAS's based on vehicle cameras
    Di Mare, Giancarlo
    Vico, Ferruccio
    Crisci, Francesco
    Montieri, Antonio
    Amoroso, Donato
    Marino, Bruno
    Ferrara, Ferdinando
    D'Avino, Claudio
    [J]. TRANSPORTATION RESEARCH PART F-TRAFFIC PSYCHOLOGY AND BEHAVIOUR, 2019, 61 : 252 - 258