Power-split Hybrid Electric Bus Research Articles

Data-Driven FMPC Based Dynamic Coordination Control Strategy for Power-Split Hybrid Electric Bus

Since no engine clutch exists in the power-split system of the hybrid electric bus, the torque variations of the power sources (i.e., the engine, motor, and generator) are easy to cause system shock during mode switching. To yield a better control effect, the model predictive control (MPC) based dynamic coordination control strategy (DCCS) is considered as an effective solution to guarantee the drivability and reliability of the system. However, the existing MPC-based DCCS still have the challenge of model accuracy and computational complexity. Therefore, to solve the problem, a data-driven Fast-MPC(FMPC) based DCCS is proposed for a power-split hybrid electric bus in this paper. Firstly, to ensure the accuracy of the engine dynamic model, a piecewise data fitting method is proposed by analyzing the historical data of the engine. Then, considering the high dimension of the control model (based on the dynamics model of the power-split system), a fast solving method for the quadratic optimization problem of MPC is proposed with respect to the proper assumption and simplification. Finally, to verify the effectiveness of the proposed control strategy, offline simulation and hardware-in-the-loop (HIL) simulation experiments are carried out. Simulation results show that good driving comfort and real-time performance have been achieved. This research is expected to promote the application of MPC in the DCCS and further improve the dynamic performance of the power-split system.

A real time multi-objective optimization Guided-MPC strategy for power-split hybrid electric bus based on velocity prediction

A real time multi-objective optimization Guided-MPC strategy for power-split hybrid electric bus based on velocity prediction

Coordinated control strategy for mode switching of power-split hybrid electric bus

In the dynamic process of mode switching of the power-split hybrid electric bus, the vehicle will have longitudinal shock due to the drastic change of the two motors’ torque and the engine’s slow response. To solved this problem, this paper will focus on the process of switching from pure electric mode to hybrid drive mode, considered the operational state changes before and after engine ignition, limited the torque fluctuation transmitted from the front planetary set to the output shaft based on the idea of motor compensation, and calculated the motor compensation torque of the rear planetary set to compensate the torque fluctuation of the output shaft, to reduce the jerk. Firstly, the dynamic models of the transmission system before and after the engine ignition are established, respectively, and then the dynamic torque of the engine is estimated by XGBoost. The estimated value is input into the model predictive controller (MPC) to track the engine speed and calculate the torque fluctuation generated by the front planetary set on the output shaft. Then, according to the estimated value of the engine torque and the predicted value of the engine’s speed, the compensation torque is calculated by the sliding mode controller (SMC). Finally, the vehicle model is built with AVL CRUISE and MATLAB/Simulink software to verify the mode switching control effect of hybrid electric bus under typical urban conditions in China. The results showed that this control strategy significantly reduces the jerk of the mode switching process.

MPC-Based Coordinated Control of Gear Shifting Process for a Power-split Hybrid Electric Bus with a Clutchless AMT

Two-speed clutchless automated manual transmission (AMT) has been widely implemented in electric vehicles for its simple structure and low cost. In contrast, due to the complex response characteristics of powertrain, utilizing clutchless AMT in a hybrid power system comes with complex coordination control problems. In order to address these issues, a power-split hybrid electric bus with two-speed clutchless AMT is studied in this paper, and a coordinated control method based on model predictive control (MPC) is used in gear shifting control strategy (GSCS) to improve gear shifting quality and reduce system jerk. First, the dynamic model of power sources and other main powertrain components including a single planetary gear set and AMT are established on the basis of data-driven and mechanism modeling methods. Second, the GSCS is put forward using the segmented control idea, and the shifting process is divided into five phases, including (I) unloading of drive motor, (II) shifting to neutral gear, (III) active speed synchronization by drive motor, (IV) engaging to new gear, and (V) resuming the drive motor’s power, among which the phases I and V have evident impact on the system jerk. Then, the MPC-based control method is adopted for these phases, and the fast compensation of driving torque is realized by combining the prediction model and quadratic programming method. The simulation results show that the proposed GSCS can effectively reduce shift jerk and improve driving comfort. This research proposes a coordinated control strategy of two-speed clutchless AMT, which can effectively improve the smoothness of gear shifting and provides a reference for the application of two speed clutchless AMT in power-split hybrid powertrains.

Deep reinforcement learning-based energy management strategies for energy-efficient driving of hybrid electric buses

The fuel economy of hybrid electric vehicles is inextricably linked to the energy management strategy (EMS). In this study, a practicality-oriented learning-based EMS for a power-split hybrid electric bus (HEB) is presented, which combines the generative adversarial imitation learning (GAIL) and deep reinforcement learning (DRL). Considering the regular and fixed route of the HEB, optimal control samples that are not affected by the cost function can be obtained by the boundary-line dynamic programing (B-DP) method. On this basis, the samples are dynamically fitted using the GAIL method to inverse derive the reward function that can explain the B-DP control behavior. Concurrently, the proximal policy optimization DRL algorithm will regulate the energy distribution of the vehicle in real time and continuously optimize the energy management capability based on the reward feedback from GAIL. Finally, the feasibility and effectiveness of the proposed EMS is verified by simulation. The results show that the proposed strategy exhibits near-optimal control performance under both the China heavy-duty commercial vehicle cycle-bus and China city bus cycle.

Battery health-aware and naturalistic data-driven energy management for hybrid electric bus based on TD3 deep reinforcement learning algorithm

Energy management is critical to reduce energy consumption and extend the service life of hybrid power systems. This article proposes an energy management strategy based on deep reinforcement learning with awareness of battery health for an urban power-split hybrid electric bus. In this article, a specific driving cycle of the test bus route is constructed through a naturalistic data-driven method to evaluate the practical operating costs of the hybrid electric bus accurately. Furthermore, an energy management strategy based on twin delayed deep deterministic policy gradient algorithm considering battery health is innovatively designed to minimize the total operating cost with a tradeoff between fuel consumption and battery degradation. Finally, the superiority of the proposed strategy over other state-of-the-art deep reinforcement learning-based strategies including deep deterministic policy gradient and double deep Q-learning is validated. Simulation results show that the constructed driving cycle can effectively reflect the real traffic conditions of the test bus route, and the proposed strategy can reduce the total operating cost while extending the battery life efficiently. This article makes contribution to the reliable evaluation of the practical operating costs and the extension of the battery life for urban hybrid electric buses through deep reinforcement learning methods.

Online Optimal Control Strategy Methodology for Power-Split Hybrid Electric Bus Based on Historical Data

An online optimal control strategy methodology on the basis of historical data for a power-split hybrid electric bus (HEB) is proposed in this study. This approach aims to fully utilize the fuel-saving capability of power-split HEB under real operating cycles and provide an effective way for solving the optimal calibration problem in the application promotion. Firstly, a procedure for synthesizing real-world driving cycles based on cluster analysis and Markov chain method is constructed. Subsequently, dynamic programming (DP) control algorithm is performed to explore the fuel economy potential. Moreover, a DP-based rule control strategy with an automated implementation foundation is introduced to achieve online approximate optimal effect. Finally, offline simulation and hardware-in-the-loop test are conducted. Simulation results validate that the proposed online optimal control strategy methodology has similar fuel-saving performance to DP optimal results and good real-time application conditions.

Hierarchical optimal intelligent energy management strategy for a power-split hybrid electric bus based on driving information

Although hybrid electric buses (HEB) has fixed route condition, there are differences upon daily driving conditions affected by traffic, weather and so on. Thus, the rule-based strategy is difficult to get the best energy-saving result under this circumstance. To improve strategy adaptability and optimality, the paper presents a hierarchical optimization control strategy based on driving information. Driving information is first deeply explored and utilized from the history and future two dimensions, including typical cycle construction and future driving prediction. The upper control strategy adopts global optimization to plan SOC trajectory by using typical cycle construction from the overall perspective, determining the proportions of electric and hybrid modes, and realizing the rational use of electric energy. Low-level control realizes real-time optimal torque distribution based on the prediction of driving condition, which adapts to different driving conditions from the local real-time perspective. Finally, simulation and hardware-in-loop tests are performed under an actual bus route. In contrast to rule-based strategy, the hierarchical optimal intelligent strategy nearly achieves the global optimization results with 9.02% fuel efficiency. Therefore, the proposed optimization strategy improves the driving condition adaptability and fuel economy of fixed-route HEBs from global and local dimensions.

Extended Kalman filter–based and model predictive control–based dynamic coordinated control strategy for power-split hybrid electric bus

The power-split hybrid electric vehicle achieves excellent fuel economy because both the engine speed and the torque of this system are decoupled from the road load. However, for a power-split hybrid electric vehicle with multiple power sources, the inconsistency of the response characteristic of each power source seriously affects the stability control of the power system and riding comfort, so the coordinated control of the power system is particularly important. This article proposed a dynamic coordinated control strategy. First, extended Kalman filter is applied to realize robust online estimation of the engine dynamics. Then, an extended Kalman filter–based and model predictive control–based dynamic coordinated control strategy is designed to achieve accurate reference tracking in hybrid electric mode. Considering the real-time performance for the online application of the dynamic coordinated control strategy, a fast model predictive control solver is formed based on a reasonable assumption. Offline simulation results show that accurate reference tracking is achieved in hybrid electric mode. Hardware-in-the-loop simulation is also conducted to validate the real-time performance of the proposed dynamic coordinated control strategy. This study is expected to improve the performance and robustness of the dynamic coordinated control strategy in hybrid electric mode while reducing the calibration load.

Energy management for a power-split hybrid electric bus via deep reinforcement learning with terrain information

Due to the high mileage and heavy load capabilities of hybrid commercial vehicles, energy management becomes crucial in improving their fuel economy. In this paper, terrain information is systematically integrated into the energy management strategy for a power-split hybrid electric bus based on a deep reinforcement learning approach: the deep deterministic policy gradient algorithm. Specially, this energy management method is improved and capable of searching optimal energy management strategies in a discrete-continuous hybrid action space, which, in this work, consists of two continuous actions for the engine and four discrete actions for powertrain mode selections. Additionally, a Critic network with dueling architecture and a pre-training stage ahead of the reinforcement learning process are combined for efficient strategy learning with the adopted algorithm. Assuming the current terrain information was available to the controller, the deep reinforcement learning based energy management strategy is trained and tested on different driving cycles and simulated terrains. Simulation results of the trained strategy show that reasonable energy allocation schemes and mode switching rules are learned simultaneously. Its fuel economy gap with the baseline strategy using dynamic programming is narrowed down to nearly 6.4% while reducing the times of engine starts by around 76%. Further comparisons also indicate approximately 2% promotion in fuel economy is contributed by the incorporation of terrain information in this learning-based energy management. The main contribution of this study is to explore the inclusion of terrain information in a learning-based energy management method that can deal with large hybrid action spaces.

Optimal rule design methodology for energy management strategy of a power-split hybrid electric bus

The excellent fuel economy of power-split hybrid electric bus has facilitated its extensive promotion for applications. However, a conventional rule-based energy management strategy for this bus involves large numbers of calibration, which considerably increases the application cost. To solve this problem, this study proposes an optimal rule design method that combines fixed thresholds with local working probability. This method effectively extracts control rules to obtain near-optimal result of global optimization and reduce calibration workload. In addition, a charge-sustaining strategy based on a linear quadratic regulator is designed to ensure the robustness of the energy management strategy based on rule design methodology. Finally, a simulation and hardware-in-loop (HIL) test are conducted on the Chinese city bus cycle. In comparison with the compared to rule-based engine optimal control, the proposed local probability-based instantaneous optimal control strategy is closer to the global optimization results, with oil savings of 10.6%. The comparison of the results between HIL and offline simulations show that they are largely coincident. Therefore, the proposed rule design methodology can serve as a theoretical reference for extraction rules in engineering practices.

Continuous reinforcement learning of energy management with deep Q network for a power split hybrid electric bus

Reinforcement learning is a new research hotspot in the artificial intelligence community. Q learning as a famous reinforcement learning algorithm can achieve satisfactory control performance without need to clarify the complex internal factors in controlled objects. However, discretization state is necessary which limits the application of Q learning in energy management for hybrid electric bus (HEB). In this paper the deep Q learning (DQL) is adopted for energy management issue and the strategy is proposed and verified. Firstly, the system modeling of bus configuration are described. Then, the energy management strategy based on deep Q learning is put forward. Deep neural network is employed and well trained to approximate the action value function (Q function). Furthermore, the Q learning strategy based on the same model is mentioned and applied to compare with deep Q learning. Finally, a part of trained decision network is analyzed separately to verify the effectiveness and rationality of the DQL-based strategy. The training results indicate that DQL-based strategy makes a better performance than that of Q learning in training time consuming and convergence rate. Results also demonstrate the fuel economy of proposed strategy under the unknown driving condition achieves 89% of dynamic programming-based method. In addition, the technique can finally learn to the target state of charge under different initial conditions. The main contribution of this study is to explore a novel reinforcement learning methodology into energy management for HEB which solve the curse of state variable dimensionality, and the techniques can be adopted to solve similar problems.

Stochastic Predictive Energy Management of Power Split Hybrid Electric Bus for Real-World Driving Cycles

The energy conversion efficiencies among different sources of power split hybrid electric vehicle rely on the energy management strategy. In this paper, the energy management of a power split hybrid electric bus (HEB) is described as the predictive control problem based on the linear control-oriented model of the HEB. In order to ensure that the engine can output the desired power, the fuzzy PI controller, which can realize the optimal engine speed tracking, is further designed. Two real-world driving cycles are analyzed and formulated to evaluate the vehicle fuel economy under transient practical conditions. On this basis, the driver torque demand and vehicle velocity in the prediction horizon are derived with the stochastic one-step Markov chain. Finally, the hardware-in-the-loop (HIL) simulation platform is built to explore the validity of the controller. Compared with the adaptive equivalent fuel consumption minimization strategy, HIL test results demonstrate the real-time capability and benefits of the proposed approach in optimizing the energy management of HEB.

LQR Based Battery Charge Sustaining Strategy for Hybrid Electric Vehicle

Rule-based near-optimal control strategy derived from global optimization results has the best real-time performance among current online optimal control strategies of the hybrid electric vehicle. However, the battery charge sustainability based on the rule-based near-optimal control strategy is not theoretically studied in current researches, which is important for robust control in complex driving conditions. In this paper, a deviation correction strategy based on linear quadratic regulator (LQR) is proposed for a power-split hybrid electric bus in order to sustain the battery’s state of charge (SOC). The LQR controller is designed according to an equivalent circuit model based on the state feedback control. Offline simulation is carried out to verify the proposed strategy under different driving cycles. Results show that, with the proposed strategy, the SOC can converge to a predefined value at the end of the optimization horizon.

Multi-factor integrated parametric design of power-split hybrid electric bus

The power-split hybrid electric system is currently the most promising hybrid system. This study proposes a multi-factor integrated parametric design method for a power-split hybrid electric bus (HEB). This method considers the power source efficiency (i.e. the engine, motor and generator), transmission efficiency, vehicle driving cycle requirements, and primary control strategy. The design method is then applied to a specified city bus. System efficiency is analyzed, and the control strategy is determined. Finally, the parametric design method is validated on the co-simulation platform of Matlab/Simulink and Cruise. Results show that the fuel economy of the power-split HEB that adopted the proposed parametric design is 36% better than that of the conventional city bus.

Predictive-model-based dynamic coordination control strategy for power-split hybrid electric bus

Parameter-matching methods and optimal control strategies of the top-selling hybrid electric vehicle (HEV), namely, power-split HEV, are widely studied. In particular, extant research on control strategy focuses on the steady-state energy management strategy to obtain better fuel economy. However, given that multi-power sources are highly coupled in power-split HEVs and influence one another during mode shifting, conducting research on dynamic coordination control strategy (DCCS) to achieve riding comfort is also important. This paper proposes a predictive-model-based DCCS. First, the dynamic model of the objective power-split HEV is built and the mode shifting process is analyzed based on the developed model to determine the reason for the system shock generated. Engine torque estimation algorithm is then designed according to the principle of the nonlinear observer, and the prediction model of the degree of shock is established based on the theory of model predictive control. Finally, the DCCS with adaptation for a complex driving cycle is realized by combining the feedback control and the predictive model. The presented DCCS is validated on the co-simulation platform of AMESim and Simulink. Results show that the shock during mode shifting is well controlled, thereby improving riding comfort.

Power Distribution and Coordinated Control for a Power Split Hybrid Electric Bus

The power distribution is proposed to determine the target operating points of the system components as the basis for maximal the efficiency of the overall system for a power split dual electric machine hybrid electric bus. The coordinated control is constructed on the basis of the power distribution. The basic coordinated control is implemented to satisfy the driver's power demand, in which both the dynamic characteristics of the engine and the dual electric machine are explicitly taken into account. Moreover, the improved coordinated control is suggested to suppress engine dynamic operation and rich fuel injection.