Anthony Mark Phillips

Predictive energy management of a power-split hybrid electric vehicle

In this paper, a Model Predictive Control (MPC) strategy is developed for the first time to solve the optimal energy management problem of power-split hybrid electric vehicles. A power-split hybrid combines the advantages of series and parallel hybrids by utilizing two electric machines and a combustion engine. Because of its many modes of operation, modeling a power-split configuration is complex and devising a near-optimal power management strategy is quite challenging. To systematically improve the fuel economy of a power-split hybrid, we formulate the power management problem as a nonlinear optimization problem. The nonlinear powertrain model and the constraints are linearized at each sample time and a receding horizon linear MPC strategy is employed to determine the power split ratio based on the updated model. Simulation results over multiple driving cycles indicate better fuel economy over conventional strategies can be achieved. In addition the proposed algorithm is causal and has the potential for real-time implementation.

MPC-Based Energy Management of a Power-Split Hybrid Electric Vehicle

A power-split hybrid electric vehicle (HEV) combines the advantages of both series and parallel hybrid vehicle architectures by utilizing a planetary gear set to split and combine the power produced by electric machines and a combustion engine. Because of the different modes of operation, devising a near optimal energy management strategy is quite challenging and essential for these vehicles. To improve the fuel economy of a power-split HEV, we first formulate the energy management problem as a nonlinear and constrained optimal control problem. Then two different cost functions are defined and model predictive control (MPC) strategies are utilized to obtain the power split between the combustion engine and electrical machines and the system operating points at each sample time. Simulation results on a closed-loop high-fidelity model of a power-split HEV over multiple standard drive cycles and with different controllers are presented. The results of a nonlinear MPC strategy show a noticeable improvement in fuel economy with respect to those of an available controller in the commercial Powertrain System Analysis Toolkit (PSAT) software and the other proposed methodology by the authors based on a linear time-varying MPC.

Vehicle system controller design for a hybrid electric vehicle

As a way to meet the challenge of developing more fuel efficient and lower emission producing vehicles, auto manufacturers are increasingly looking toward revolutionary changes to conventional powertrain technologies as a solution. One alternative under consideration is that of hybrid electric vehicles (HEV). An HEV combines some of the benefits of electric vehicles (efficient and clean motive power supplied by an electric motor, regenerative braking) with the features of a conventional vehicle that consumers expect (convenient refueling, long driving range). However, these benefits come with increased complexity in the powertrain design. Instead of having one motive power source, there are two that can each act independently or in combination. The complexity of an HEV powertrain together with the vehicles many operating modes demand that a supervisory or hybrid controller be developed at the vehicle level to guarantee stable and consistent operation. Inherent in this controller is a logical structure to guide the vehicle through its various operating modes and a dynamic control strategy associated with each operating mode to specify the vehicle demands to each subsystem controller. Capturing all possible operating modes and guaranteeing smooth dynamic control transitions from one operating mode to the next are significant challenges in the controller design. A formal method for designing this supervisory controller has been developed. A description of the method and its application to an HEV will be presented.

Intelligent Hybrid Vehicle Power Control—Part II: Online Intelligent Energy Management

This is the second paper in a series of two that describe our research in intelligent energy management in a hybrid electric vehicle (HEV). In the first paper, we presented the machine-learning framework ML_EMO_HEV, which was developed for learning the knowledge about energy optimization in an HEV. The framework consists of machine-learning algorithms for predicting driving environments and generating the optimal power split of the HEV system for a given driving environment. In this paper, we present the following three online intelligent energy controllers: 1) IEC_HEV_SISE; 2) IEC_HEV_MISE ; and 3) IEC_HEV_MIME. All three online intelligent energy controllers were trained within the machine-learning framework ML_EMO_HEV to generate the best combination of engine power and battery power in real time such that the total fuel consumption over the whole driving cycle is minimized while still meeting the drivers demand and the system constraints, including engine, motor, battery, and generator operation limits. The three online controllers were integrated into the Ford Escape hybrid vehicle model for online performance evaluation. Based on their performances on ten test drive cycles provided by the Powertrain Systems Analysis Toolkit library, we can conclude that the roadway type and traffic congestion level specific machine learning of optimal energy management is effective for in-vehicle energy control. The best controller, IEC_HEV_MISE, trained with the optimal power split generated by the DP optimization algorithm with multiple initial SOC points and single ending point, can provide fuel savings ranging from 5% to 19%. Together, these two papers cover the innovative technologies for modeling power flow, mathematical background of optimization in energy management, and machine-learning algorithms for generating intelligent energy controllers for quasioptimal energy flow in a power-split HEV.

Intelligent Hybrid Vehicle Power Control—Part I: Machine Learning of Optimal Vehicle Power

In this series of two papers, we present our research on intelligent energy management for hybrid electric vehicles (HEVs). These two papers cover the modeling of power flow in HEVs, the mathematical background of optimization in energy management in HEVs, a machine learning framework that combines dynamic programming (DP) with machine learning to learn about roadway-type- and traffic-congestion-level-specific energy optimization, machine learning algorithms, and real-time quasi-optimal control of energy flow in an HEV. This first paper presents our research on machine learning for optimal energy management in HEVs. We will present a machine learning framework ML_EMO_HEV developed for the optimization of energy management in an HEV, machine learning algorithms for predicting driving environments, and the generation of an optimal power split for a given driving environment. Experiments are conducted based on a simulated Ford Escape Hybrid vehicle model provided by Argonne National Laboratorys Powertrain Systems Analysis Toolkit (PSAT). Based on the experimental results on the test data, we can conclude that the neural networks trained under the ML_EMO_HEV framework are effective in predicting roadway type and traffic congestion levels, predicting driving trends, and learning optimal engine speed and optimal battery power from DP.

Intelligent Vehicle Power Control Based on Machine Learning of Optimal Control Parameters and Prediction of Road Type and Traffic Congestion

Previous research has shown that current driving conditions and driving style have a strong influence over a vehicles fuel consumption and emissions. This paper presents a methodology for inferring road type and traffic congestion (RT&TC) levels from available onboard vehicle data and then using this information for improved vehicle power management. A machine-learning algorithm has been developed to learn the critical knowledge about fuel efficiency on 11 facility-specific drive cycles representing different road types and traffic congestion levels, as well as a neural learning algorithm for the training of a neural network to predict the RT&TC level. An online University of Michigan-Dearborn intelligent power controller (UMD_IPC) applies this knowledge to real-time vehicle power control to achieve improved fuel efficiency. UMD_IPC has been fully implemented in a conventional (nonhybrid) vehicle model in the powertrain systems analysis toolkit (PSAT) environment. Simulations conducted on the standard drive cycles provided by the PSAT show that the performance of the UMD_IPC algorithm is very close to the offline controller that is generated using a dynamic programming optimization approach. Furthermore, UMD_IPC gives improved fuel consumption in a conventional vehicle, alternating neither the vehicle structure nor its components.

Optimally controlling Hybrid Electric Vehicles using path forecasting

The paper examines path-dependent control of Hybrid Electric Vehicles (HEVs). In this approach we seek to improve HEV fuel economy by optimizing charging and discharging of the vehicle battery depending on the forecasted vehicle route. The route is decomposed into a series connection of route segments with (partially) known properties. The dynamic programming is used as a tool to quantify the benefits offered by route information availability.

Power Smoothing Energy Management and Its Application to a Series Hybrid Powertrain

Energy management strategies in hybrid electric vehicles determine how much energy is produced/stored/used in each powertrain component. We propose an approach for energy management applied to a series hybrid electric vehicle that aims at improving the powertrain efficiency rather than the total fuel consumption. Since in the series configuration the engine is mechanically decoupled from the traction wheels, for a given power request the steady-state engine operating point is chosen to maximize the efficiency. A control algorithm regulates the transitions between different operating points by using the battery to smoothen the engine transients, thereby improving efficiency. Because of the constrained nature of the transient-smoothing problem, we implement the control algorithm by model predictive control. The control strategy feedback law is synthesized and integrated with the powertrain control software in the engine control unit. Simulations of the urban dynamometer driving schedule (UDDS) and US06 cycles using a complete vehicle system model and experimental tests of the UDDS cycle show improved fuel economy with respect to baseline strategies.

Nonlinear Model Predictive Control for power-split Hybrid Electric Vehicles

In this paper, a causal optimal controller based on Nonlinear Model Predictive Control (NMPC) is developed for a power-split Hybrid Electric Vehicle (HEV). The global fuel minimization problem is converted to a finite horizon optimal control problem with an approximated cost-to-go, using the relationship between the Hamilton-Jacobi-Bellman (HJB) equation and the Pontryagins minimum principle. A nonlinear MPC framework is employed to solve the problem online. Different methods for tuning the approximated minimum cost-to-go as a design parameter of the MPC are discussed. Simulation results on a validated high-fidelity closed-loop model of a power-split HEV over multiple driving cycles show that with the proposed strategy, the fuel economies are improved noticeably with respect to those of an available controller in the commercial Powertrain System Analysis Toolkit (PSAT) software and a linear time-varying MPC controller previously developed by the authors.

Engine power smoothing energy management strategy for a series hybrid electric vehicle

Hybrid electric vehicles exploit energy production and energy storage systems to achieve improved fuel economy with respect to conventional powertrains. In order to maximize such improvements, advanced control strategies are needed for deciding the amount of energy to be produced and stored. In this paper we propose an approach for energy management of a series hybrid electric vehicle (SHEV). This approach focuses on maximizing the pointwise powertrain efficiency, rather than the overall fuel consumption. For a given power request the steady state engine operating point is chosen to maximize the efficiency. A control algorithm regulates the transitions between different operating points, by using the battery to smoothen the engine transients. Due to the constrained nature of the transient smoothing problem, we implement the control algorithm by model predictive control. Experimental testing on the UDDS cycle shows improved fuel economy with respect to two baseline strategies.