Hybrid electric vehicles employ a hybrid propulsion system to combine the energy efficiency of electric motor and a long driving range of internal combustion engine, thereby achieving a higher fuel economy as well as convenience compared with conventional ICE vehicles. However, the relatively complicated powertrain structures of HEVs necessitate an effective power management policy to determine the power split between ICE and EM. In this work, we propose a deep reinforcement learning framework of the HEV power management with the aim of improving fuel economy. The DRL technique is comprised of an offline deep neural network construction phase and an online deep Q-learning phase. Unlike traditional reinforcement learning, DRL presents the capability of handling the high dimensional state and action space in the actual decision-making process, making it suitable for the HEV power management problem. Enabled by the DRL technique, the derived HEV power management policy is close to optimal, fully model-free, and independent of a prior knowledge of driving cycles. Simulation results based on actual vehicle setup over real-world and testing driving cycles demonstrate the effectiveness of the proposed framework on optimizing HEV fuel economy.
more »
« less
Fuel economy improvement and emission reduction of 48 V mild hybrid electric vehicles with P0, P1, and P2 architectures with lithium battery cell experimental data
This paper intends to provide design selections of hybrid powertrain architectures in 48 V mild hybrid electric vehicles. Based on the location of the electric machine in the driveline, the hybrid powertrain architectures can be categorized into five groups, P0, P1, P2, P3, and P4. This paper uses simulation software to investigate the fuel economy improvements and emission reduction of 48 V mild hybrid electric vehicles with P0, P1, and P2 architectures. A baseline conventional and a 12 V start/stop vehicle models based on the production vehicle are built for comparison. The 48 V battery pack model is based on experimental data including open-circuit voltage and internal resistance of a 20 Ah lithium polymer battery cell. Four standard driving cycles are used to assess the fuel economy and emissions of the vehicle models. With features of engine idle elimination, electric power assist, and regenerative braking, the 48 V P0 and P1 respectively gains average 13.5% and 15.5% simulated fuel economy compared to baseline vehicle. The 48 V P2 enables feature of electric launch/driving and improves the fuel economy by average 18.5% better than baseline vehicle. The 48 V mild hybrid system seems to be one of the promising techniques to meet future fuel economy standards and emission regulations.
more » « less- PAR ID:
- 10546755
- Publisher / Repository:
- SAGE Publications
- Date Published:
- Journal Name:
- Advances in Mechanical Engineering
- Volume:
- 13
- Issue:
- 10
- ISSN:
- 1687-8132
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Hybrid electric vehicles can achieve better fuel economy than conventional vehicles by utilizing multiple power sources. While these power sources have been controlled by rule-based or optimization-based control algorithms, recent studies have shown that machine learning-based control algorithms such as online Deep Reinforcement Learning (DRL) can effectively control the power sources as well. However, the optimization and training processes for the online DRL-based powertrain control strategy can be very time and resource intensive. In this paper, a new offline–online hybrid DRL strategy is presented where offline vehicle data are exploited to build an initial model and an online learning algorithm explores a new control policy to further improve the fuel economy. In this manner, it is expected that the agent can learn an environment consisting of the vehicle dynamics in a given driving condition more quickly compared to the online algorithms, which learn the optimal control policy by interacting with the vehicle model from zero initial knowledge. By incorporating a priori offline knowledge, the simulation results show that the proposed approach not only accelerates the learning process and makes the learning process more stable, but also leads to a better fuel economy compared to online only learning algorithms.more » « less
-
The proliferation of electric vehicles (EVs) is resulting in a big transition in the automotive industry, with the goal of reducing greenhouse gas emissions and improving energy efficiency. There are a variety of different architectural configurations and power distribution strategies that can be optimized for drivability performance, all-electric range, and overall efficiency. This paper describes the efforts of the research team in exploring different EV architectures to better understand their impacts on system performance in terms of energy efficiency and vehicle drivability. In search for an ideal powertrain architecture for a shared-use EV, the research team conducted a comprehensive analysis of a various EV architectures (including RWD and AWD) with different motor parameters, considering a spectrum of targeted vehicle technology specifications such as acceleration and braking performance, and fuel economy. To quantify these performance indices, a model-based design approach was utilized, leveraging the EV development tools developed by MATLAB/Simulink and Simscape. Standard driving cycles, e.g., Highway Fuel Economy Driving Schedule (HWFET) and Urban Dynamometer Driving Schedule (UDDS) were utilized to evaluate different EV powertrain architectures and rear/front wheel power splits. The simulation results showed that for the architectures (with respective parameters) investigated in this study, the AWD architectures have higher energy efficiency than the RWD architecture in the range of 5.4 – 37.9%. To further scrutinize performance across a wide spectrum of driving scenarios, we introduced a specialized modal driving profile. This comprehensive profile encompasses a diverse array of modal events, including varying acceleration rates and steady-state speeds, among others. In our analysis, we found that a standard torque split of 50/50 keeps a good balance between energy efficiency and drivability for our target AWD architecture.more » « less
-
Abstract Battery electric vehicles (BEVs) have emerged as a promising alternative to traditional internal combustion engine (ICE) vehicles due to benefits in improved fuel economy, lower operating cost, and reduced emission. BEVs use electric motors rather than fossil fuels for propulsion and typically store electric energy in lithium-ion cells. With rising concerns over fossil fuel depletion and the impact of ICE vehicles on the climate, electric mobility is widely considered as the future of sustainable transportation. BEVs promise to drastically reduce greenhouse gas emissions as a result of the transportation sector. However, mass adoption of BEVs faces major barriers due to consumer worries over several important battery-related issues, such as limited range, long charging time, lack of charging stations, and high initial cost. Existing solutions to overcome these barriers, such as building more charging stations, increasing battery capacity, and stationary vehicle-to-vehicle (V2V) charging, often suffer from prohibitive investment costs, incompatibility to existing BEVs, or long travel delays. In this paper, we propose P eer-to- P eer C ar C harging (P2C2), a scalable approach for charging BEVs that alleviates the need for elaborate charging infrastructure. The central idea is to enable BEVs to share charge among each other while in motion through coordination with a cloud-based control system. To re-vitalize a BEV fleet, which is continuously in motion, we introduce Mobile Charging Stations (MoCS), which are high-battery-capacity vehicles used to replenish the overall charge in a vehicle network. Unlike existing V2V charging solutions, the charge sharing in P2C2 takes place while the BEVs are in-motion, which aims at minimizing travel time loss. To reduce BEV-to-BEV contact time without increasing manufacturing costs, we propose to use multiple batteries of varying sizes and charge transfer rates. The faster but smaller batteries are used for charge transfer between vehicles, while the slower but larger ones are used for prolonged charge storage. We have designed the overall P2C2 framework and formalized the decision-making process of the cloud-based control system. We have evaluated the effectiveness of P2C2 using a well-characterized simulation platform and observed dramatic improvement in BEV mobility. Additionally, through statistical analysis, we show that a significant reduction in carbon emission is also possible if MoCS can be powered by renewable energy sources.more » « less
-
more » « less
Abstract The transportation sector is the largest contributor to CO2emissions and a major source of criteria air pollutants in the United States. The impact of climate change and that of air pollution differ in space and time, but spatially-explicit, systematic evaluations of the effectiveness of alternative fuels and advanced vehicle technologies in mitigating both climate change and air pollution are lacking. In this work, we estimate the life cycle monetized damages due to greenhouse gas emissions and criteria air pollutant emissions for different types of passenger-moving vehicles in the United States. We find substantial spatial variability in the monetized damages for all fuel-vehicle technologies studied. None of the fuel-vehicle technologies leads simultaneously to the lowest climate change damages and the lowest air pollution damages across all U.S. counties. Instead, the fuel-vehicle technology that best mitigates climate change in one region is different from that for the best air quality (i.e. the trade-off between decarbonization and air pollution mitigation). For example, for the state of Pennsylvania, battery-electric cars lead to the lowest population-weighted-average climate change damages (a climate change damage of 0.87 cent/mile and an air pollution damage of 1.71 cent/mile). In contrast, gasoline hybrid-electric cars lead to the lowest population-weighted-average air pollution damages (a climate change damage of 0.92 cent/mile and an air pollution damage of 0.77 cent/mile). Vehicle electrification has great potential to reduce climate change damages but may increase air pollution damages substantially in regions with high shares of coal-fired power plants compared to conventional vehicles. However, clean electricity grid could help battery electric vehicles to achieve low damages in both climate change and air pollution.
