Article
Thermodynamics
Nikolaos Aletras, Stijn Broekaert, Evangelos Bitsanis, Georgios Fontaras, Zissis Samaras, Leonidas Ntziachristos
Summary: This paper examines the potential fuel consumption savings of implementing a predictive equivalent consumption minimisation strategy in the energy management system of hybrid heavy-duty vehicles. Results show that the proposed algorithm can reduce fuel consumption and save CO2 emissions.
ENERGY CONVERSION AND MANAGEMENT
(2024)
Article
Thermodynamics
Xie Shaobo, Zhang Qiankun, Hu Xiaosong, Liu Yonggang, Lin Xianke
Summary: The study focuses on optimizing the battery size for plug-in hybrid electric buses, proposing a method to coordinate energy management strategy and battery aging for determining optimal battery size, considering the uncertainty in route length for urban bus fleet leading to varying travel distance.
Article
Energy & Fuels
Zhen Zhang, Tiezhu Zhang, Jichao Hong, Hongxin Zhang, Jian Yang
Summary: This article proposes a master-slave hybrid electric vehicle (MSHEV) with multiple energy sources, which transitions between different working modes and has lower power consumption and energy loss compared to electric vehicles (EVs) under actual driving conditions. By optimizing the battery state of charge and constructing a Response Surface Model-based approximate model and Multi-Island Genetic Algorithm-based optimization model, the energy management of the optimized MSHEV is enhanced, indicating significant importance and reference value in the optimization of energy management of hybrid electric vehicles.
Article
Thermodynamics
Tarsis Prado Barbosa, Jony Javorski Eckert, Vinicius Ruckert Roso, Fabricio Jose Pacheco Pujatti, Leonardo Adolpho Rodrigues da Silva, Juan Carlos Horta Gutierrez
Summary: This study compared the behavior of ethanol-fueled vehicles with internal combustion engines and hydraulic drivetrains, showing the potential of reducing fuel consumption in urban routes with hydraulic hybrid architecture and lowering CO2 and NOx emissions by optimizing engine-out emissions. The optimized solution also indicated fuel-saving potential in urban routes with stop-and-go events.
Article
Thermodynamics
Desiree Alcazar-Garcia, Jose Luis Romeral Martinez
Summary: This paper presents an adaptive and high-accuracy methodology that utilizes genetic algorithms to accelerate the design and implementation of ecological vehicles in smart cities. The methodology maximizes vehicle range with minimal computational effort and provides predictive information on cost, volume, and weight. The reliability and precision of the model have been verified using commercially available vehicles.
Article
Green & Sustainable Science & Technology
Zhen Zhang, Tiezhu Zhang, Jichao Hong, Hongxin Zhang, Jian Yang
Summary: This paper proposes a novel parallel electric-hydraulic hybrid electric vehicle (PEHHEV) with multiple working modes and power sources. It applies the long short-term memory (LSTM) neural network to the proximal policy optimization (PPO) algorithm to establish an energy management strategy for optimal working mode switching. Through offline training, online testing, and entropy evaluation, the PEHHEV achieved lower energy consumption and maintained dynamic performance under the PPO-LSTM-based strategy.
JOURNAL OF CLEANER PRODUCTION
(2023)
Article
Thermodynamics
Zhen Zhang, Tiezhu Zhang, Jichao Hong, Hongxin Zhang, Jian Yang, Qingxiao Jia
Summary: This study investigates a novel electric-hydraulic hybrid electric vehicle (EHHEV) and establishes a rule-based energy management strategy based on the hybrid system's energy flow. It combines Q-learning with deep neural networks to construct a double deep Q-network (DDQN)-guided energy management system, achieving optimal switching among working modes and significantly improving vehicle economy.
Article
Engineering, Chemical
Hao Chen, Tiezhu Zhang, Hongxin Zhang, Guangdong Tian, Ruijun Liu, Jian Yang, Zhen Zhang
Summary: This paper proposes an electro-hydraulic power coupled electric vehicle and demonstrates through simulation that the system can improve the vehicle's acceleration performance and energy recovery efficiency.
Article
Thermodynamics
Jichao Hong, Tiezhu Zhang, Zhen Zhang, Hongxin Zhang
Summary: This paper focuses on a novel type of electric-hydraulic hybrid vehicle with multiple working modes and zero emissions, which offers a deeper potential for energy efficiency. The study proposes the idea of combining deep reinforcement learning with a rule-based control strategy to control the electric-hydraulic ratio. An energy management strategy framework based on the self-adaptive electric-hydraulic ratio was developed, which can significantly reduce the energy consumption rate.
Article
Computer Science, Information Systems
Chigozie Uzochukwu Udeogu, Wansu Lim
Summary: This paper proposes an improved and adaptive deep learning-based velocity prediction control EMS for battery-supercapacitor HEVs, which prolongs battery lifetime and increases energy utilization efficiency through feature engineering and optimized power allocation.
Article
Engineering, Civil
Dongjian Song, Bing Zhu, Jian Zhao, Jiayi Han, Zhicheng Chen
Summary: This paper proposes a hybrid control strategy pHybrid based on a combination of reinforcement learning (RL) and supervised learning (SL), which achieves high-performance human-like car-following control. By incorporating a personalized car-following reference model and a motion uncertainty model of the preceding vehicle, pHybrid can better match the personalized needs of human drivers and improve safety, comfort, and tracking performance.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Automation & Control Systems
Peng Mei, Hamid Reza Karimi, Hehui Xie, Fei Chen, Cong Huang, Shichun Yang
Summary: Considering the importance of energy management strategy for hybrid electric vehicles, this paper addresses the energy optimization control issue using reinforcement learning algorithms. It establishes a hybrid electric vehicle power system model and designs a hierarchical energy optimization control architecture based on networked information. Three learning-based energy optimization control strategies, namely Q-learning, deep Q network (DQN), and deep deterministic policy gradient (DDPG) algorithms, are introduced. The superiority of the DDPG algorithm over Q-learning and DQN algorithms in terms of robustness and faster convergence for better energy management purposes is illustrated through simulation.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Review
Computer Science, Artificial Intelligence
Luiz G. Galvao, M. Nazmul Huda
Summary: Autonomous vehicles have the potential to solve traffic problems, but there is still room for improvement. This paper presents a review of state-of-the-art algorithms proposed for AV behavior prediction systems.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Automation & Control Systems
Yang Xing, Chen Lv, Yahui Liu, Yifan Zhao, Dongpu Cao, Sadahiro Kawahara
Summary: This article proposes a method for predicting driver's steering intentions based on a hybrid-learning time-series model and deep learning networks, aiming to achieve mutual understanding between humans and machines. The results of experiments show that the proposed method can achieve high prediction accuracy of steering intentions under different driving modes.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2022)
Article
Engineering, Electrical & Electronic
Ningkang Yang, Lijin Han, Rui Liu, Zhengchao Wei, Hui Liu, Changle Xiang
Summary: This article proposes a multiobjective energy management strategy based on multiagent reinforcement learning for a hybrid electric vehicle. The strategy takes into consideration fuel economy improvement, battery state of charge maintenance, battery degradation reduction, and constraint on ultracapacitor state of charge. The proposed strategy combines game theory and reinforcement learning to achieve a Nash equilibrium among multiple objectives. Simulation results show that the proposed strategy outperforms single-agent reinforcement learning and dynamic programming in optimizing multiple objectives.
IEEE TRANSACTIONS ON TRANSPORTATION ELECTRIFICATION
(2023)
