Types Of Hybrid Electric Vehicles Research Articles

Enabling cross-type full-knowledge transferable energy management for hybrid electric vehicles via deep transfer reinforcement learning

Deep reinforcement learning (DRL) now represents an emerging artificial intelligence technology to develop energy management strategies (EMSs) for hybrid electric vehicles (HEVs). However, developing specific DRL-based EMSs for different HEVs is currently a laborious task. Therefore, we design a transferable optimization framework crossing types of HEVs to expedite the development of DRL-based EMSs. In this framework, a novel enhanced twin delayed deep deterministic policy gradient (E-TD3) algorithm is first formulated, and then a deep transfer reinforcement learning (DTRL) method is designed by incorporating transfer learning into DRL. After that, a full-knowledge transfer method based on E-TD3 and DTRL is innovatively proposed. To assess the efficacy of the designed method, an E-TD3-based EMS of a light HEV is pre-trained to be the existing source EMS whose all learned knowledge is then transferred to be reused for a hybrid electric bus (HEB) to facilitate the acquisition of the target new EMS. Simulation results demonstrate that, in the designed transferable framework, the development cycle of the HEB's EMS can be shortened by 90.38 % and the fuel consumption can be saved by 6.07 %. This article provides a practical method to reuse existing DRL-based EMSs for the rapid development of new EMSs across HEV types.

Intelligent Renewable Energy Source Allocation Scheme for Internet of Things Enabled PHEVs Systems

Plug-in hybrid electric vehicles (PHEVs) have received a lot of interest because of their ability to cut fuel usage by using electricity from the grid as an alternative energy source. PHEVs differ from typical hybrid electric vehicles (HEVs) in terms of increased battery capacity, the availability of plug-in recharging, and improved battery state of charge (SOC) management systems. Efficient energy consumption and excellent performance are critical issues for hybrid powertrains. The estimation of SOC in PHEVs is a difficult NP-hard problem that is frequently tackled utilising metaheuristic techniques. In this paper, we offer an enhanced dingo optimisation with deep learning-based prediction (EDOA-DLP) model specifically tailored for PHEVs. The EDOA-DLP model includes an efficient SOC estimate algorithm for real-time energy management. The EDOA-DLP technique's performance has been thoroughly proven through considerable experimentation in a variety of circumstances. The results show that the proposed EDOA-DLP method beats other current methods in terms of predicting SOC accurately and reaching the targeted goals for PHEVs. Overall, this research presents a unique EDOA-DLP SOC prediction approach for PHEVs, with promising results in terms of energy management and performance optimisation. The experimental results highlight the EDOA-DLP model's improved performance. Overall, this research presents a unique EDOA-DLP SOC prediction approach for PHEVs, with promising results in terms of energy management and performance optimisation. The experimental results illustrate the EDOA-DLP model's improved performance when compared to competing methodologies, highlighting its potential to improve the efficiency and efficacy of PHEV systems.

Electric vehicles survey and a multifunctional artificial neural network for predicting energy consumption in all-electric vehicles

This study contains a survey on the architecture of electric vehicles and an artificial neural network application for prediction of energy consumption in all-electric vehicles. In this study, the term “electric vehicles” (EVs) refers to various types of electrified vehicles. The technologies behind these electric vehicles were also discussed. The survey focuses on hybrid electric vehicles (HEVs), pure electric vehicles (PEVs), and plug-in hybrid electric vehicles (PHEVs). The study also presents the design simulation of a typical hybrid electric vehicle. A hybrid electric vehicle was designed using ADVISOR, and it was compared with another car known as the targeted car. The fuel consumption of the designed car was found to be lower than that of the targeted car. The study also introduced a multifunctional artificial neural network model for predicting electrical energy consumption in all-electric vehicles. The proposed model has nine input variables, which are virtual functions calculated from the nine selected parameters using a virtual function formula. The number of input variables was made to be equal to the number of output variables so that the artificial neural network could simulate a unique solution. The proposed model was compared with a multi-output inverse function model of an artificial neural network. The accuracy of the proposed model was 1.23–6.85 times higher than that of the inverse function model for the nine case studies considered in terms of mean square error.

Lane-changing control for hybrid electric vehicles with dedicated hybrid transmission based on robust model predictive control

Car-following and lane-changing are extremely important for vehicles. The traditional adaptive cruise control (ACC) strategy has various drawbacks due to the complicated driving conditions. A new control strategy of robust model predictive control (RMPC) for car-following and lane-changing is proposed based on a new type of hybrid electric vehicle (HEV) with dedicated hybrid transmission (DHT-HEV). The control model includes a vehicle model, a following and lane-changing model and an RMPC controller. The vehicle model integrates the DHT-HEV and dynamic models with a longitudinal dynamic model, seven degrees of freedom (DOF) vehicle dynamic model and three DOF control model. The following and lane-changing model is described as car-following and lane-changing models of two-quintic function. The RMPC controller is used to balance the control of vehicle longitudinal and lateral dynamics with the lateral acceleration disturbance. Simulation results demonstrate that the RMPC controller can track the reference trajectory during two lane-changing process when the test scenarios of different accelerations are set compared with the conventional ACC control. Different Np (predictive horizon) and Nc (control horizon) are also analysed to improve the solving performance of RMPC. Results indicate that the solving performance of the system is optimal when Np = 30 and Nc = 1. Furthermore, different weight coefficient matrixes ( Q and R) are taken into the consideration by coordinating the car-following performance and lateral stability. Accordingly, the controllers of RMPC-LC, RMPC-ACC and RMPC-LA are set, demonstrating that the control of RMPC-LA best balances two aspects and is always within a safe car-following distance. Meanwhile, the hardware in the loop (HIL) is utilised to verify the effectiveness of the proposed RMPC control strategy, which comprises model compilation, the establishment connection between the D2P ECU and the simulator and control input.

Accurate and Efficient Energy Management System of Fuel Cell/Battery/Supercapacitor/AC and DC Generators Hybrid Electric Vehicles

The development of hybrid electric vehicles (HEVs) is rapidly gaining traction as a viable solution for reducing carbon emissions and improving fuel efficiency. One type of HEV that is gaining significant interest is the fuel cell/battery/supercapacitor HEV (FC/Bat/SC HEV), which combines fuel cell, battery, supercapacitor, AC, and DC generators. These FC/B/SC HEVs are particularly appealing because they excel at efficiently managing energy and cater to a wide range of driving requirements. This study presents a novel approach for exploiting the kinetic energy of a sensorless HEV. The vehicle has a primary fuel cell resource, a supercapacitor, and lithium-ion battery energy storage banks, where each source is connected to a special converter. The obtained hybrid system allows the vehicle to enhance autonomy, support the fuel cell during low production moments, and improve transient and steady-state load requirements. The exploitation of kinetic energy is performed by the DC and AC generators that are linked to the electric vehicle front wheels to transfer the HEV’s wheel rotation into power, contributing to the overall power balance of the vehicle. The energy management system for electric vehicles determines the FC setpoint power through the classical state machine method. At the same time, a robust speed controller-based artificial intelligence algorithm reduces power losses and enhances the supply efficiency for the vehicle. Furthermore, we evaluate the performance of a robust controller with a speed estimator, specifically using the adaptive neuro-fuzzy inference system (ANFIS) and the model reference adaptive system (MRAS) estimator in conjunction with the direct torque control-support vector machine (DTC-SVM), to enhance the torque and speed performance of HEVs. The results demonstrate the feasibility and reliability of the vehicle while utilizing the additional DC and AC generators to extract free kinetic energy, both of which contributed to 28% and 24% of the total power for the vehicle, respectively. This approach leads to a vehicle supply efficiency exceeding 96%, reducing the burden on fuel cells and batteries and resulting in a significant reduction in fuel consumption, which is estimated to range from 25% to 35%.

Collaborative Optimization of Energy Management Strategy and Adaptive Cruise Control Based on Deep Reinforcement Learning

Hybrid electric vehicles (HEVs) have great prospects in reducing fossil fuel consumption, and adaptive cruise control (ACC) technology provides safe and convenient travel for drivers. The fusion of the two technologies can theoretically improve the safety, comfort, and fuel economy of vehicles. Hence, the energy management strategy (EMS) of Prius, a typical HEV configuration, is studied under the car-following scenario. This optimization problem involves complex systems, inconsistent objectives, and stringent constraints, which may be challenging to conventional algorithms. Therefore, a novel deep deterministic policy gradient (DDPG)-based ecological driving strategy (DDPG-ECO) is proposed and the weights of multiple objectives are analyzed to optimize the training results. The extensive simulation experiment compares the effects of Ornstein-Uhlenbeck action noise (OUAN) and soft-max action noise (SAN), which act on the acceleration action. Simulations under different driving cycles show that the fuel economy of DDPG-ECO can achieve more than 90% of dynamic programming (DP)-based methods on the conditions of ensuring car-following performances.

ADAPTIVE ENERGY MANAGEMENT STRATEGY FOR SUSTAINABLE OPERATION OF HYBRID ELECTRIC VEHICLE

Hybrid electric vehicles (HEVs) in the transportation sector is spearheading the industry towards embracing green technology to ensure the sustainability of the environment. HEVs offer significant reduction of exhaust emissions while retaining vehicle performance achieved via a revolutionary energy management strategy (EMS) which reforms the management of power flow from the dual energy sources of a HEV. However, researchers are faced with challenges to extract the maximum performance out of HEVs due to the contradicting nature between its main objectives, namely vehicle performance, fuel consumption and cost. In this study, an investigation focusing on the fuel-saving potential of a power-split type HEV using a fuzzy logic-based EMS is conducted. The purpose of this research is to explore methods to improve fuel efficiency of a HEV through a smart and adaptive EMS. The power flow in the proposed model is decided based on its current vehicle speed and the global discharge rate value derived from the real-time battery state-of-charge and remaining trip distance. From simulations over standard drive cycles, the proposed controller is able to outperform a rule-based EMS by an improvement of up to 65.4% in terms of fuel consumption which subsequently reduces the volume of pollutants released to the atmosphere.

A Study on the Anomaly Detection of Engine Clutch Engagement/Disengagement Using Machine Learning for Transmission Mounted Electric Drive Type Hybrid Electric Vehicles

Transmission mounted electric drive type hybrid electric vehicles (HEVs) engage/disengage an engine clutch when EV↔HEV mode transitions occur. If this engine clutch is not adequately engaged or disengaged, driving power is not transmitted correctly. Therefore, it is required to verify whether engine clutch engagement/disengagement operates normally in the vehicle development process. This paper studied machine learning-based methods for detecting anomalies in the engine clutch engagement/disengagement process. We trained the various models based on multi-layer perceptron (MLP), long short-term memory (LSTM), convolutional neural network (CNN), and one-class support vector machine (one-class SVM) with the actual vehicle test data and compared their results. The test results showed the one-class SVM-based models have the highest anomaly detection performance. Additionally, we found that configuring the training architecture to determine normal/anomaly by data instance and conducting one-class classification is proper for detecting anomalies in the target data.

Design of Gerotor Pump and Influence on Oil Supply System for Hybrid Transmission

Electric continuously variable transmission (E-CVT) is a vital part of the automobile in order to enhance the power coupling. The oil pump is an important power source component in the hybrid transmission system. Its efficiency exerts a significant impact on the efficiency of the oil supply system and even the hybrid transmission system. In this study, a gerotor pump is designed in line with the requirements of a certain type of hybrid electric vehicle. A Non-dominated Sorting Genetic Algorithm II (NSGA-II) genetic algorithm was employed to optimize the rotor tooth profile. The proportional-derivative (PD) control of the oil supply system was realized to lower the functional error of the oil supply system based on the AMESim simulation platform. In addition, the prototype test was performed to verify the rationality of the design.

A Comprehensive Review on Classification, Energy Management Strategy, and Control Algorithm for Hybrid Electric Vehicles

The energy management strategy (EMS) and control algorithm of a hybrid electric vehicle (HEV) directly determine its energy efficiency, control effect, and system reliability. For a certain configuration of an HEV powertrain, the challenge is to develop an efficient EMS and an appropriate control algorithm to satisfy a variety of development objectives while not reducing vehicle performance. In this research, a comprehensive, multi-level classification for HEVs is introduced in detail from the aspects of the degree of hybridization (DoH), the position of the motor, the components and configurations of the powertrain, and whether or not the HEV is charged by external power. The principle and research status of EMSs for each type of HEV are summarized and reviewed. Additionally, the EMSs and control algorithms of HEVs are compared and analyzed from the perspectives of characteristics, applications, real-time abilities, and historical development. Finally, some discussions about potential directions and challenges for future research on the energy management systems of HEVs are presented. This review is expected to bring contribution to the development of efficient, intelligent, and advanced EMSs for future HEV energy management systems.

Cross-Type Transfer for Deep Reinforcement Learning Based Hybrid Electric Vehicle Energy Management

Developing energy management strategies (EMSs) for different types of hybrid electric vehicles (HEVs) is a time-consuming and laborious task for automotive engineers. Experienced engineers can reduce the developing cycle by exploiting the commonalities between different types of HEV EMSs. Aiming at improving the efficiency of HEV EMSs development automatically, this paper proposes a transfer learning based method to achieve the cross-type knowledge transfer between deep reinforcement learning (DRL) based EMSs. Specifically, knowledge transfer among four significantly different types of HEVs is studied. We first use massive driving cycles to train a DRL-based EMS for Prius. Then the parameters of its deep neural networks, wherein the common knowledge of energy management is captured, are transferred into EMSs of a power-split bus, a series vehicle and a series-parallel bus. Finally, the parameters of 3 different HEV EMSs are fine-tuned in a small dataset. Simulation results indicate that, by incorporating transfer learning (TL) into DRL-based EMS for HEVs, an average 70% gap from the baseline in respect of convergence efficiency has been achieved. Our study also shows that TL can transfer knowledge between two HEVs that have significantly different structures. Overall, TL is conducive to boost the development process for HEV EMS.

A novel power management strategy for hybrid off-road vehicles

Hybrid off-road vehicles generally use an engine and an energy storage system (e.g., ultracapacitor) as the power sources for propulsion. By optimally splitting power demand to different actuators (i.e., electric motors), fuel economy can be improved greatly. Thus, the control strategies of hybrid vehicles play an important role in fuel savings. While many optimal control strategies have been proposed, two major concerns present themselves: the need for prior knowledge of future driving conditions and the slow computation speed. In this paper, a novel near-optimal power management strategy, called efficiency-based evaluation real time control strategy (EERCS), is developed to rapidly obtain near-optimal fuel economy. We formulate the normalized efficiency of power flow as the criterion. By maintaining high system efficiency under all conditions, the controller can obtain near-optimal fuel economy with no need for prior knowledge. To validate the control effect, the proposed novel controller is compared with dynamic programming (DP) and power-weighted efficiency analysis for rapid sizing (PEARS+). A complex multi-mode power-split hybrid track-type dozer is selected for the case study. Simulation results show that the new power management strategy produces results similar to those of DP and PEARS+ together, with a faster computation speed. Two distributed drive cycles are used to verify the robustness of EERCS. The resulting control law can also be applied online as a static mapping function of the powertrain state. The proposed novel strategy is also a promising control tool that can be extended to other types of hybrid electric vehicles.

Representation, generation, and optimization methodology of hybrid electric vehicle powertrain architectures

Since the first commercial application of hybrid electric vehicle (HEV) powertrains, power-split architectures have been a major option for construction of HEV powertrains. Are power-split HEV powertrains the best solution to all design-objective settings, or will other design schemes arise that better fit the design requirements? To generalize the system optimization to different types of HEV powertrains, representation and generation methods for generic architectures of HEV powertrain are developed, which completely clarify the available design domain of the HEV powertrain architecture. Then, an integrated multi-objective optimization that simultaneously optimizes the architecture, component parameters, and control strategy is engineered to obtain the Pareto optimal design schemes of HEV powertrains in various situations of trade-off between acceleration capacity and fuel economy. The results suggest that the power-split HEV powertrain is superior in fuel economy and the HEV powertrain adopting the architecture with torque coupling among the engine and motor/generators (1-1 type) is superior in acceleration capacity. However, the achievable optimal fuel economies of power-split and 1-1 type HEV powertrains are almost the same, whereas the trade-off ranges of power-split HEV powertrains are narrower than those of the 1-1 type architecture HEV powertrains. Conceptually, the results reflect that when design methods are restricted to a specific subspace of the design domain, due to the limited consideration of variation in HEV powertrain architectures, the theoretical optimality of the design is not guaranteed. Practically, 1-1 type architecture can be more adaptive to different trade-offs among design objectives. For variations in design objectives, the appropriate HEV powertrain can be constructed by modifying in component parameters of the 1-1 No. 5 architecture HEV powertrain rather than reconstruction of the powertrain with architectural modifications.

Deep Reinforcement Learning-Based Energy Management for a Series Hybrid Electric Vehicle Enabled by History Cumulative Trip Information

It is essential to develop proper energy management strategies (EMSs) with broad adaptability for hybrid electric vehicles (HEVs). This paper utilizes deep reinforcement learning (DRL) to develop EMSs for a series HEV due to DRL's advantages of requiring no future driving information in derivation and good generalization in solving energy management problem formulated as a Markov decision process. History cumulative trip information is also integrated for effective state of charge guidance in DRL-based EMSs. The proposed method is systematically introduced from offline training to online applications; its learning ability, optimality, and generalization are validated by comparisons with fuel economy benchmark optimized by dynamic programming, and real-time EMSs based on model predictive control (MPC). Simulation results indicate that without a priori knowledge of future trip, original DRL-based EMS achieves an average 3.5% gap from benchmark, superior to MPC-based EMS with accurate prediction; after further applying output frequency adjustment, a mean gap of 8.7%, which is comparable with MPC-based EMS with mean prediction error of 1 m/s, is maintained with concurrently noteworthy improvement in reducing engine start times. Besides, its impressive computation speed of about 0.001 s per simulation step proves its practical application potential, and this method is independent of powertrain topology such that it is applicative for any type of HEVs even when future driving information is unavailable.

Micro gas and steam turbines power generation system for hybrid electric vehicles

Hybrid electric vehicles (HEV) are currently considered a viable solution for fossil fuel saving and pollutant emissions reduction in transportation sector. The typical HEV configuration contains a reciprocating internal combustion engine – gasoline or diesel. Aiming to increase performance and reduce pollution, a study on performance, size and mass of a HEV configuration with micro gas and steam turbine was developed. The proposed system generates 100 kW output power and operates with compressed natural gas (CNG hybrid technology), which is a fuel more environmentally friendly than gasoline or diesel. The study revealed that analysed system performs better than most advanced equivalent ICE engines while its size and mass fit into the bodywork of a car. A solution for arrangement of the system components in the case of a car is also presented.

Development Trends of Transmissions for Hybrid Electric Vehicles Using an Optimized Energy Management Strategy

Energy conservation and emissions reduction have become increasingly significant for automobiles due to the severity of the current energy situation. Hybrid electric vehicle (HEV) technology is one of the most promising solutions. This study investigated the total efficiency of a HEV powertrain. To improve the total efficiency, the engine should be regulated to work at its highest efficiency and drive the wheels directly as much as possible. To accomplish this, we developed an energy management strategy based on the direct drive area (DDA) of the engine’s efficiency map. Several typical HEV models were built to compare the fuel consumption using DDA and rule-based strategies. Furthermore, the function of the HEV transmission system with DDA was considered. The transmission in a HEV should regulate the engine to work at its highest efficiency as much as possible, which is rather different than the regulation in an internal combustion engine vehicle. The functional change may lead to transmission systems with fewer gears but optimal gear ratios. If this trend is realized, the manufacturing cost of HEVs could be largely reduced.

Experimental Evaluation of the Effect of Cycle Profile on the Durability of Commercial Lithium Ion Power Cells

The effect of the charge/discharge profile on battery durability is a critical factor for the application of batteries and for the design of appropriate battery testing protocols. In this work, commercial high-power prismatic lithium ion cells for hybrid electric vehicles (HEVs) were cycled using a pulse-heavy profile and a simple square-wave profile to investigate the effect of cycle profile on battery durability. The pulse-heavy profile was designed to simulate on-road conditions for a typical HEV, while the simplified square-wave profile was designed to have the same total charge throughput, but with lower peak currents. The 5 Ah batteries were cycled for 100 kAh with periodic performance tests to monitor the state of the batteries. Results indicate that, for the batteries tested, the capacity fade for the two profiles was very similar and was 11±0.5% compared to beginning of life (BOL). The change in internal resistance of the batteries during testing was also monitored and found to increase 21% and 12% compared to BOL for the pulse-heavy and square-wave profiles, respectively. The results suggest that simplified testing protocols using square-wave cycling may provide adequate insight into capacity fade behavior for more complex hybrid vehicle drive cycles.

Steam and Oxyhydrogen Addition Influence on Energy Usage by Range Extender—Battery Electric Vehicles

The objective of this paper is to illustrate the benefits of the influence of the steam and oxyhydrogen gas (HHO) on the composition of emitted exhaust gases and energy usage of operating the internal combustion engine (ICE) that drives a generator-powered battery electric vehicle (BEV). The employed internal combustion generating sets can be used as trailer mounted electric energy sources allowing one to increase the range of BEV vehicles, mainly during long distance travel between cities. The basic configurations of hybrid and electric propulsion systems used in a given Electric Vehicles (xEV) includes all types of Hybrid Electric Vehicles (xHEV) and Battery Electric Vehicles (xBEV), which are discussed. Using the data collected during traction tests in real road traffic (an electric car with a trailer range extender (RE) fitted with ICE generators (5 kW petrol, 6.5 kW diesel), a mathematical model was developed in the Modelica package. The elaborated mathematical model takes into account the dynamic loads acting on the set of vehicles in motion and the electric drive system assisted by the work of RE. Conducted tests with steam and HHO additives for ICE have shown reduced (5–10%) fuel consumption and emissions (3–19%) of harmful gases into the atmosphere.

A Study on the Fuel Economy Potential of Parallel and Power Split Type Hybrid Electric Vehicles

What is the best number of gear steps for parallel type hybrid electric vehicles (HEVs) and what are the pros and cons of the power split type HEV compared to the parallel type have been interesting issues in the development of HEVs. In this study, a comparative analysis was performed to evaluate the fuel economy potential of a parallel HEV and a power split type HEV. First, the fuel economy potential of the parallel HEV was investigated for the number of gear steps. Four-speed, six-speed, and eight-speed automatic transmissions (ATs) and a continuously variable transmission (CVT) were selected, and their drivetrain losses were considered in the dynamic programming (DP). It was found from DP results that the power electronics system (PE) loss decreased because the magnitude of the motor load leveling power decreased as the number of gear steps increased. On the other hand, the drivetrain losses including the electric oil pump (EOP) loss increased with increasing gear step. The improvement rate from the 4-speed to the 6-speed was the greatest, while it decreased for the higher gear step. The fuel economy of the CVT HEV was rather low due to the large EOP loss in spite of the reduced PE loss. In addition, the powertrain characteristics of the parallel HEV were compared with the power split type HEV. In the power split type HEV, the PE loss was almost double compared to that of the parallel HEV because two large capacity motor-generators were used. However, the drivetrain loss and EOP loss of the power split type HEV were found to be much smaller due to its relatively simple architecture. It is expected that the power characteristics of the parallel and power split type HEVs obtained from the DP results can be used in the development of HEV systems.

Electric vehicles for improving resilience of distribution systems

In this study, improving the resilience of residential customers through employing Electric Vehicles (EV) is investigated. This solution is especially effective in case of unavailability of distribution systems for a considerable amount of time. An example of this situation is the aftermath of a hurricane when existing grid infrastructure may be fully or partially disabled. In this paper, specific attention is paid to hybrid electric vehicles, as their gasoline can be used as a sufficient source of energy during such conditions. In order to have a fair comparison, selected models of both hybrid and non-hybrid electric vehicles are considered. Moreover, based on available data from reliable literature, this paper has generated different load profiles for various consumption scenarios to model the severity of conditions and estimate the required energy. Moreover, two seasonal conditions are considered and the load profiles are developed based on characteristic curves of major household appliances, instead of their rated powers. Then, the selected electric vehicles are considered as the main power supply and the available serving time of each electric vehicle is computed. Results show that a typical hybrid electric vehicle can supply power to residential units for a reasonable amount of time during a power outage.