Strategy For Hybrid Electric Vehicles Research Articles

Adaptive Energy Management Strategy for Hybrid Electric Vehicles in Dynamic Environments Based on Reinforcement Learning

Energy management strategies typically employ reinforcement learning algorithms in a static state. However, during vehicle operation, the environment is dynamic and laden with uncertainties and unforeseen disruptions. This study proposes an adaptive learning strategy in dynamic environments that adapts actions to changing circumstances, drawing on past experience to enhance future real-world learning. We developed a memory library for dynamic environments, employed Dirichlet clustering for driving conditions, and incorporated the expectation maximization algorithm for timely model updating to fully absorb prior knowledge. The agent swiftly adapts to the dynamic environment and converges quickly, improving hybrid electric vehicle fuel economy by 5–10% while maintaining the final state of charge (SOC). Our algorithm’s engine operating point fluctuates less, and the working state is compact compared with Deep Q-Network (DQN) and Deterministic Policy Gradient (DDPG) algorithms. This study provides a solution for vehicle agents in dynamic environmental conditions, enabling them to logically evaluate past experiences and carry out situationally appropriate actions.

A learning‐based hierarchical energy management control strategy for hybrid electric vehicles

AbstractIn this work, a novel energy management control framework is developed for hybrid electric vehicles (HEVs) driving in car‐following scenarios. In order to enhance the energy efficiency while maintaining the driving safety, a hierarchical control approach consisting of an upper level speed tracking control scheme and a lower level energy management control strategy is proposed. For the upper level tracking control system, an iterative learning model predictive control (ILMPC) scheme is developed to guarantee the tracking performance and the driving safety simultaneously. Additionally, a model predictive control (MPC) algorithm is adopted at the lower level to optimize the torque distribution in real‐time based on the driving cycles generated by the upper level control system. With the proposed hierarchical control framework, HEVs are able to improve the energy efficiency significantly by taking the advantages of the operational repeatability. The convergence of the proposed control strategy is analyzed rigorously, and its effectiveness is illustrated through numerical simulations.

Learning-based hierarchical cooperative eco-driving with traffic flow prediction for hybrid electric vehicles

The integration of autonomous driving and hybrid electric vehicle technologies presents a promising solution for achieving environmental sustainability. This paper introduces an innovative energy-efficient driving strategy for hybrid electric vehicles that incorporates real-time traffic flow prediction. The study delves into the impact of both lateral and longitudinal vehicle maneuvers on energy consumption within dynamic traffic environments, offering novel insights into optimizing energy utilization. Firstly, a multi-lane traffic flow state rolling predictor is constructed based on the Hankel dynamic mode decomposition algorithm. Subsequently, a vehicle longitudinal and lateral coordinated control strategy is established by integrating the prioritized experience replay double deep Q-network algorithm. Finally, a novel energy management strategy is proposed that leverages Simulink dynamic model and the deep deterministic policy gradient algorithm to address the vehicle dynamic decision-making planning results. Within a hierarchical cooperative optimization framework, this research comprehensively considers safety, comfort, traffic efficiency, and fuel economy. By introducing a novel hierarchical collaborative ecological driving framework, we have achieved a substantial improvement in environmental sustainability, with traffic efficiency increasing by 10.27%-14.41% and fuel economy rising by 9.44%-10.47%. Hardware-in-the-loop validation has confirmed the proposed approach’s real-time capabilities and promising practical applications.

An adaptive fuzzy coordinated control strategy for hybrid electric vehicles considering clutch wear and engine temperature variation

AbstractAn improved method of clutch coordinated control based on the Kalman filter was proposed to solve the problem that the existing mode switching strategy of hybrid electric vehicles could not adapt to engine temperature changes and clutch wear. First, taking advantage of the relationship between the torque transmitted by the clutch and the starting resistance of the engine, combined with the characteristics of the clutch, the clutch wear was roughly calculated. Accordingly, the control strategy of the clutch in the existing mode switching was improved to adapt to the clutch wear. The adaptive control strategy proposed for clutch wear included the fuzzy control module of the initial engagement pressure, the fuzzy inference module of the clutch engaging pressure change, the clutch wear estimation module and so on. Second, the Kalman filter was used to process the results to improve the estimation accuracy of clutch wear. The engine starting resistance related to starting speed and temperature was modeled to enhance the adaptability of the control strategy to engine temperature. Finally, the designed control strategy was verified in simulation. The results show that the improved control strategy can complete the mode switching when the engine temperature is variable and the clutch is worn. The maximum impact degree increased from 5 m/s3 without wear to 8.5 m/s3 with wear, but it is still less than the index limit, and it can be considered that the proposed strategy can achieve the desired control effect. The fuzzy control algorithm proposed enhances the vehicle's ride comfort during mode switching from pure electric driving to hybrid driving.

Multi-Agent Deep Reinforcement Learning-Based Multi-Objective Cooperative Control Strategy for Hybrid Electric Vehicles

Multi-Agent Deep Reinforcement Learning-Based Multi-Objective Cooperative Control Strategy for Hybrid Electric Vehicles

Computationally efficient gear shift strategy for hybrid electric vehicles

Computationally efficient gear shift strategy for hybrid electric vehicles

A Power Preconditioning-Based Power Flow Predictive Control Strategy for Hybrid Electric Vehicle Using Fast Iteration Optimization Algorithm

A Power Preconditioning-Based Power Flow Predictive Control Strategy for Hybrid Electric Vehicle Using Fast Iteration Optimization Algorithm

Data-driven transferred energy management strategy for hybrid electric vehicles via deep reinforcement learning

Real-time applications of energy management strategies (EMSs) in hybrid electric vehicles (HEVs) are the harshest requirements for researchers and engineers. Inspired by the excellent problem-solving capabilities of deep reinforcement learning (DRL), this paper proposes a real-time EMS via incorporating the DRL method and transfer learning (TL). The related EMSs are derived from and evaluated on the real-world collected driving cycle dataset from Transportation Secure Data Center (TSDC). The concrete DRL algorithm is proximal policy optimization (PPO) belonging to the policy gradient (PG) techniques. For specification, many source driving cycles are utilized for training the parameters of deep networks based on PPO. The learned parameters are transformed into the target driving cycles under the TL framework. The EMSs related to the target driving cycles are estimated and compared in different training conditions. Simulation results indicate that the presented transfer DRL-based EMS could effectively reduce the time consumption and guarantee the control performance.

Intelligent energy management strategy for hybrid electric vehicles using reinforcement learning

ABSTRACT Predicting the performance of a Hybrid EV (Electric Vehicle) is significant to alleviate the complications of insufficient fuel and other battery-related problems that affect the driving capacity. Many energy management techniques with ML (Machine Learning) and DL (Deep Learning) methodologies have been deployed in predicting the operation of vehicles based on energy sources and their features. Still, it is being noticed that prediction errors have increased along with the increase or decrease of input data. To solve the challenges addressed in existing studies, the proposed approach intends to use both ML and DL to predict faults from battery features that considerably manage the energy. It is accomplished through efficient feature extraction employed by Bi-LSTM (Bidirectional Long Short Term Memory), which extracts the best energy features required for predicting the defects. From the extracted input features collected hourly, daily, and monthly from the dataset, classification is done using the Modified XGBoost Algorithm with Empirical Loss function. Normal and Abnormal functioning of the Hybrid EV is classified effectively. Followed by that, the prediction of improper functioning is made with the assistance of the vehicle Id to maximise the vehicle’s performance through consideration of battery constraints. Experimentation is performed with MATLAB simulation, and the performance of the proposed system is evaluated using error metrics like RMSE (Root Mean Square Error), MAE (Mean Absolute Error), MSE (Mean Square Error), and accuracy. Efficiency is exhibited through the minimum loss obtained through the proposed work. From analysis of comparing LSTM method with proposed model, it is found that the LSTM method produced RMSE value of 1.055% which is 0.84% reduced in proposed model. On the other hand, the MAE of LSTM is 0.826% and the proposed model is decreased with 0.174%. Further, the MSE of LSTM is 1.113% and is 0.69% reduced in proposed model.

Optimized Passivity-based Control of a Hybrid Electric Vehicle Source using a Novel Equilibrium Optimizer

Passivity-based control is a well-known strategy for synthesizing stable controllers because it models and manages systems based on their global state space equations. It also permits proving the system's stability by making it passive, which is an undeniable advantage over traditional controllers that have limitations in terms of applications, saturation, and the inability to verify stability. Previous research used nonlinear control based on passivity method to control the energy distribution between the embedded sources, they did not investigate the impact of the dumping matrix parameter, which was typically considered to be a positive random value. In contrast, the results of this investigation show that it significantly affects system behaviour, especially in the transient-state domain. The primary objective of this study is to develop and evaluate an energy management strategy for hybrid electric vehicles powered by Fuel Cells as the primary source and Supercapacitors as the secondary source. The fast response with less overshoot is ensured by optimizing the damping matrix parameter using a well-known optimization technique named Novel Equilibrium Optimizer. The proposed technique is successfully demonstrated in a Matlab® simulation environment, and the control system exhibits robust dynamic behaviour. Finally, despite the complexity of this technique's mathematical proof, it provides a simple, efficient feedback control law for a real electrical vehicle application.

A Hierarchical Energy Control Strategy for Hybrid Electric Vehicle with Fuel Cell/Battery/Ultracapacitor Combining Fuzzy Controller and Status Regulator

In order to improve the fuel economy of fuel cell hybrid electric vehicles (FCHEV), a hierarchical energy management strategy (HEMS) is proposed to rationally allocate the required power to a hybrid power system with three energy sources: fuel cell, battery, and ultracapacitor. First of all, batteries and ultracapacitors are regarded as energy storage systems (ESS), which convert the distribution problem from three energy sources to two couples of energy sources. Secondly, fuzzy logic controllers are utilized in upper-layer energy management strategies (EMS) to distribute required power to fuel cell systems and the ESS. To extend the service life of the fuel cell and increase the maintenance ability of the state of charge (SOC) of the battery, a status regulation module is introduced to allocate the required power combined with fuzzy controller. Thirdly, an adaptive low-pass filter is applied to a lower-layer EMS based on the energy characteristics of the ultracapacitor, which fully utilizes the ultracapacitor. Finally, the economic and dynamic performance of the vehicle are compared between the HEMS and the power following strategy (PFS) under five typical cycle conditions: UDDS, WVUINTER, NEDC, HWFET and COMBINE. The results of the simulation show that the hydrogen consumption of the HEMS is reduced and the overall vehicle energy efficiency is increased in four operating conditions, which indicates that the proposed strategy has better economic performance. In addition, the dynamic performance of the vehicle is also improved.

Predictive eco-driving strategy for hybrid electric vehicles on off-road terrain considering vehicle stability constraint

Road vehicles can obtain traffic information via Intelligent Transportation System (ITS), which yields more potential in improving driving performance. However, ITS is not available for off-road vehicles and only limited information can be obtained by onboard sensors. Meanwhile, the off-road terrain suffers from terrible road conditions, which brings great difficulties to ensuring driving safety. Therefore, how to coordinate fuel economy, vehicle mobility and driving safety with limited traffic information is a challenging problem for off-road vehicles. To tackle the problem, an online predictive eco-driving strategy is proposed in this paper, which consists of safety supervisory module, time reference generator and rolling optimization. Firstly, considering the off-road terrain characteristic, the safety supervisory module analysis the vehicle stability performance under different road conditions, and thus the driving safety on off-road terrain with low adhesion coefficient, high curvature and heavy grade can be guaranteed. Secondly, the time reference generator is designed to ensure vehicle mobility. With only a prior knowledge of distance to destination, the time reference generator can generate the reference time in prediction horizon fast and effectively. Finally, model predictive control is employed to construct the multi-objective eco-driving problem, with an ameliorated particle swarm optimization to minimize the fuel consumption while tracking the reference time and ensuring driving safety. Simulations are conducted to validate the effectiveness of the proposed strategy. The results exhibit that the fuel economy and vehicle mobility can be improved by 10.13% and 5.77% over practical strategy in the premise of ensuring driving safety under the 5 km off-road terrain scenario. Moreover, a hardware-in-loop test is implemented to verify the real-time ability of the proposed strategy.

A comparative study of deep reinforcement learning based energy management strategy for hybrid electric vehicle

Energy management strategies (EMSs) are essential for hybrid electric vehicles (HEVs), as they can further exploit the potential of HEVs to save energy and reduce emissions. Research on deep reinforcement learning (DRL)-based EMSs is developing rapidly. However, most studies have ignored the impact of uniform test benchmarks on the performance of DRL-based EMS and focus too much on fuel economy improvement resulting in a single optimization objective. In this study, four DRL-based EMSs are designed for HEVs with a multi-objective optimization reward function that considers battery health furtherly. The optimal learning rates and weight coefficients of the four EMSs are determined first. Based on this, the monetary cost, fuel cost, and battery health of each EMS are intensively studied under nine driving cycles. The EMSs perform better in high-speed conditions and worse in suburban conditions are initially concluded. A comparative analysis under unlearned mixed driving cycles validates this conclusion and shows that the SAC-based EMS achieves a fuel consumption of 4.218L per 100 km and 99.96 % battery health, which are the lowest of the four EMSs. This paper can provide a theoretical basis for the parametric and driving cycle study of DRL-based EMSs.

A hierarchical eco-driving strategy for hybrid electric vehicles via vehicle-to-cloud connectivity

The emergence of the intelligent transportation system and cloud computing technology has brought the available traffic information and increasing computing power, which lead to a significant improvement in driving performance. In order to enhance energy economy and mobility simultaneously, a hierarchical eco-driving strategy is proposed in this paper, which is comprised of the cloud-level controller and the vehicle-level controller. The dynamic programming-based cloud-level controller optimizes the velocity and battery state-of-charge utilizing the global traffic information obtained from the intelligent transportation system. However, the global traffic information suffers from uncertainties, which deteriorates the effectiveness of the cloud-level controller. The vehicle-level controller is constructed on the model predictive control framework, aiming to cope with the uncertainties, improve fuel economy and reduce travel time. Besides, a transfer learning-based particle swarm optimization algorithm is presented for solving the optimization problem in model predictive control, which can achieve great control performance utilizing the knowledge from the cloud-level controller. To validate the effectiveness of the proposed strategy, simulation tests are conducted. The results demonstrate that the proposed strategy can achieve near-global-optimal performance in fuel economy and mobility. Moreover, the real-time performance of the proposed strategy is validated through the hardware-in-loop test.

A deep reinforcement learning approach to energy management control with connected information for hybrid electric vehicles

Considering the importance of the energy management strategy for hybrid electric vehicles, this paper is aiming at addressing the energy optimization control issue using reinforcement learning algorithms. Firstly, this paper establishes a hybrid electric vehicle power system model. Secondly, a hierarchical energy optimization control architecture based on networked information is designed, and a traffic signal timing model is used for vehicle target speed range planning in the upper system. More specifically, the optimal vehicle speed is optimized by a model predictive control algorithm. Thirdly, a mathematical model of vehicle speed variation in connected and unconnected states is established to analyze the effect of vehicle speed planning on fuel economy. Finally, three learning-based energy optimization control strategies, namely Q-learning, deep Q network (DQN), and deep deterministic policy gradient (DDPG) algorithms, are designed under the hierarchical energy optimization control architecture. It is shown that the Q-learning algorithm is able to optimize energy control; however, the agent will meet the ”dimension disaster” once it faces a high-dimensional state space issue. Then, a DQN control strategy is introduced to address the problem. Due to the limitation of the discrete output of DQN, the DDPG algorithm is put forward to achieve continuous action control. In the simulation, the superiority of the DDPG algorithm over Q-learning and DQN algorithms in hybrid electric vehicles is illustrated in terms of its robustness and faster convergence for better energy management purposes.

Energy Management Strategy for Hybrid Electric Vehicle with Battery Thermal Health Constrained

Energy Management Strategy for Hybrid Electric Vehicle with Battery Thermal Health Constrained

Adaptive Starting Control Strategy for Hybrid Electric Vehicles Equipped with a Wet Dual-Clutch Transmission

To improve the starting performance of the P2.5 plug-in hybrid electric vehicles with a wet dual-clutch transmission, an adaptive starting control strategy is presented in this paper, which controls the two clutches simultaneously involved in the starting process. A fuzzy controller is designed to identify the starting intention and determine the target torque under different working conditions. The starting process is divided into five periods, and linear quadratic optimal control is adopted to obtain the reference torque trajectory for the third period, while the others are determined by adaptive control by changing the adjustment coefficients according to the starting conditions. The combined pressure feedback controller based on the PID algorithm is proposed to control the wet clutch torque to follow the reference torque trajectory. The MATLAB/Simulink software platform is used to simulate the control strategy. The results show that the proposed strategy can shorten the starting time and reduce the level of jerk. Moreover, with the first-gear starting, the friction work of the whole process and clutch C1 is, respectively, reduced by 1.68% and 4.62% for slowly starting and 23.37% and 23.6% for quickly starting, which can significantly prolong the service lifetime of the clutch compared with the traditional single-clutch starting strategy.

Publisher’s Note

Publisher’s Note

Multi-Objective Energy Management Strategy for Hybrid Electric Vehicles Based on TD3 with Non-Parametric Reward Function

The energy management system (EMS) of hybridization and electrification plays a pivotal role in improving the stability and cost-effectiveness of future vehicles. Existing efforts mainly concentrate on specific optimization targets, like fuel consumption, without sufficiently taking into account the degradation of on-board power sources. In this context, a novel multi-objective energy management strategy based on deep reinforcement learning is proposed for a hybrid electric vehicle (HEV), explicitly conscious of lithium-ion battery (LIB) wear. To be specific, this paper mainly contributes to three points. Firstly, a non-parametric reward function is introduced, for the first time, into the twin-delayed deep deterministic policy gradient (TD3) strategy, to facilitate the optimality and adaptability of the proposed energy management strategy and to mitigate the effort of parameter tuning. Then, to cope with the problem of state redundancy, state space refinement techniques are included in the proposed strategy. Finally, battery health is incorporated into this multi-objective energy management strategy. The efficacy of this framework is validated, in terms of training efficiency, optimality and adaptability, under various standard driving tests.

Practical application of energy management strategy for hybrid electric vehicles based on intelligent and connected technologies: Development stages, challenges, and future trends

The rapid development of intelligent and connected technologies is conducive to the efficient energy utilization of hybrid electric vehicles (HEVs). However, most energy management strategies (EMSs) with optimized, intelligent, and connected functions have not been directly applied to such vehicles because existing technical conditions cannot meet the theoretical requirements of complex EMSs. Therefore, based on the mapping relationship between the information decision-making ability and the energy management effect, this study is the first to propose four development stages of HEV energy management practical application as follows: energy management based on instantaneous driving cycles (Stage 1 or S1); energy management based on forward driving cycle prediction (Stage 2 or S2); energy management based on global driving cycle prediction (Stage 3 or S3); and energy management based on autonomous velocity planning (Stage 4 or S4). The key technologies of each development stage are not independent, i.e., they complement each other in the process of practical application development. Furthermore, realizing energy management practical applications not only requires novel algorithm models but also involves several challenges such as acquiring and processing multi-source information, predicting the vehicle power demand in the spatial–temporal domain during travel, and determining the vehicle control characteristics and ability. Finally, according to the development goals of energy management, this study proposes an implementation framework for HEV energy management in higher development stages, namely cooperative vehicle–edge–cloud for intelligent energy management, i.e., CVEC- IEM, which executes information decision tasks on different computing platforms and realizes interconnection and interaction to provide development directions and goals for the efficient utilization of energy and successful deployment of HEV practical applications.