Yuan Zou

Yuan Zou


Research Focus & Metrics

Academic Career Length

18Years (2009-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 September 2015 in IEEE Transactions on Industrial Electronics
Verified
Journal Article
Closed access
TLTeng Liu
Teng Liu
YZYuan Zou
Yuan Zou
DLDexing Liu
Dexing Liu
FSFengchun Sun
Fengchun Sun
A reinforcement learning-based adaptive energy management (RLAEM) is proposed for a hybrid electric tracked vehicle (HETV) in this paper. A control oriented model of the HETV is first established, in which the state-of-charge (SOC) of battery and the speed of generator are the state variables, and the engine's torque is the control variable. Subsequently, a transition probability matrix is learned from a specific driving schedule of the HETV. The proposed RLAEM decides appropriate power split between the battery and engine-generator set (EGS) to minimize the fuel consumption over different driving schedules. With the RLAEM, not only is driver's power requirement guaranteed, but also the fuel economy is improved as well. Finally, the RLAEM is compared with the stochastic dynamic programming (SDP)-based energy management for different driving schedules. The simulation results demonstrate the adaptability, optimality, and learning ability of the RLAEM and its capacity of reducing the computation time.

12 March 2020 in IEEE Transactions on Vehicular Technology
Verified
Journal Article
Closed access
NGNingyuan Guo
Ningyuan Guo
Basilio LenzoBasilio Lenzo
Basilio Lenzo
Xudong ZhangXudong Zhang
Xudong Zhang
YZYuan Zou
Yuan Zou
RZRuiqing Zhai
Ruiqing Zhai
TZtao zhang
tao zhang
This paper proposes a real-time nonlinear model predictive control (NMPC) strategy for direct yaw moment control (DYC) of distributed drive electric vehicles (DDEVs). The NMPC strategy is based on a control-oriented model built by integrating a single track vehicle model with the Magic Formula (MF) tire model. To mitigate the NMPC computational cost, the continuation/generalized minimal residual (C/GMRES) algorithm is employed and modified for real-time optimization. Since the traditional C/GMRES algorithm cannot directly solve the inequality constraint problem, the external penalty method is introduced to transform inequality constraints into an equivalently unconstrained optimization problem. Based on the Pontryagin's minimum principle (PMP), the existence and uniqueness for solution of the proposed C/GMRES algorithm are proven. Additionally, to achieve fast initialization in C/GMRES algorithm, the varying predictive duration is adopted so that the analytic expressions of optimally initial solutions in C/GMRES algorithm can be derived and gained. A Karush-Kuhn-Tucker (KKT) condition based control allocation method distributes the desired traction and yaw moment among four independent motors. Numerical simulations are carried out by combining CarSim and Matlab/Simulink to evaluate the effectiveness of the proposed strategy. Results demonstrate that the real-time NMPC strategy can achieve superior vehicle stability performance, guarantee the given safety constraints, and significantly reduce the computational efforts.

22 April 2013 in Energies
Verified
Journal Article
Open access
PDF file
ZYZou Yuan
Zou Yuan
LTLiu Teng
Liu Teng
SFSun Fengchun
Sun Fengchun
HPHuei Peng
Huei Peng
This paper compares two optimal energy management methods for parallel hybrid electric vehicles using an Automatic Manual Transmission (AMT). A control-oriented model of the powertrain and vehicle dynamics is built first. The energy management is formulated as a typical optimal control problem to trade off the fuel consumption and gear shifting frequency under admissible constraints. The Dynamic Programming (DP) and Pontryagin’s Minimum Principle (PMP) are applied to obtain the optimal solutions. Tuning with the appropriate co-states, the PMP solution is found to be very close to that from DP. The solution for the gear shifting in PMP has an algebraic expression associated with the vehicular velocity and can be implemented more efficiently in the control algorithm. The computation time of PMP is significantly less than DP.

5 March 2019 in IEEE Transactions on Industrial Informatics
Verified
Journal Article
Closed access
TLTeng Liu
Teng Liu
Xiaosong HuXiaosong Hu
Xiaosong Hu
WHWeihao Hu
Weihao Hu
YZYuan Zou
Yuan Zou
This paper proposes a heuristic planning energy management controller, based on a Dyna agent of reinforcement learning (RL) approach, for real-time fuel saving optimization of a plug-in hybrid electric vehicle (PHEV). The presented method is referred to as the Dyna-H algorithm, which is a model-free online RL algorithm. First, as a case study, a detailed vehicle powertrain modeling of the Chevrolet Volt is built, where all the control components have been experimentally validated. Four traction operation modes are allowed by managing the states of two clutches and one brake. Furthermore, the Dyna-H algorithm is introduced via incorporating a heuristic planning strategy into a Dyna agent. This is the first time to apply the Dyna-H algorithm in the energy management field of PHEVs. Finally, a comparative analysis of the one-step Q-learning, Dyna, and Dyna-H algorithms is conducted in simulations. Numerous testing results indicate that the proposed algorithm leads to definite improvements in equiv-alent fuel economy and computational speed.

4 June 2021 in IEEE Transactions on Transportation Electrification
Verified
Journal Article
Closed access
NGNingyuan Guo
Ningyuan Guo
Xudong ZhangXudong Zhang
Xudong Zhang
YZYuan Zou
Yuan Zou
Basilio LenzoBasilio Lenzo
Basilio Lenzo
GDGuodong Du
Guodong Du
TZtao zhang
tao zhang
A supervisory control strategy, including dynamic control supervisor, handling-stability controller, energy efficiency controller, and coordinated torque allocator, is proposed for distributed drive electric vehicles to coordinate vehicle handling, lateral stability, and energy economy performance. In the dynamic control supervisor, first, the phase plane analysis is implemented to accurately define the vehicle stability boundary so that the lookup table of bounds can be established for online applications. Subsequently, based on the feedback drive conditions and vehicle states, the identified boundary is dynamically quantified by the designed varying weight factor (VWF) in real time. In the handling-stability controller, a unified yaw rate reference of VWF is developed to simultaneously guarantee vehicle maneuverability and lateral stabilization. Then, a novel integral triple-step method is proposed to calculate the proper direct yaw moment for the desired vehicle motion. In the energy efficiency controller, the interaxle torque distribution map is optimized for optimal vehicle energy economy. In the coordinated torque allocator, a torque increment allocation problem is formulated and optimized to realize the desired forces, meanwhile, based on VWF to minimize energy consumption and tire workload usage. The validations of the proposed strategy are conducted under various maneuvers, yielding comprehensive improvements in terms of vehicle handling, lateral stability, and energy performance.

1 January 2019 in IEEE Transactions on Vehicular Technology
Verified
Journal Article
Closed access
SWShouyang Wei
Shouyang Wei
YZYuan Zou
Yuan Zou
Xudong ZhangXudong Zhang
Xudong Zhang
TZtao zhang
tao zhang
XLXiaoliang Li
Xiaoliang Li
A control framework adopting the on-board radar sensor and vehicle-to-vehicle (V2V) communication has been developed to fulfill the automated vehicle following in the longitudinal and lateral directions. First, a linear feedforward and feedback controller constrained by the string stability is designed to follow the velocity of the preceding vehicle and ensure a safe inter-vehicle distance. Then, a path estimation method is proposed to calculate the trajectory of the preceding vehicle based on its historical movement data transmitted by V2V. The model predictive control method is applied to regulate the steering angle of the front wheel. Furthermore, the robustness and adaptability of the proposed method are validated by simulations and tests under several driving conditions. The results indicate that the proposed method shows the reliable performance to realize the longitudinal and lateral vehicle following only by radar and V2V, independent of high-accuracy positioning system and road marking, and is promising to expand available areas of automated vehicle platooning.