ELM-based driver torque demand prediction and real-time optimal energy management strategy for HEVs
- PDF / 3,060,946 Bytes
- 19 Pages / 595.276 x 790.866 pts Page_size
- 26 Downloads / 191 Views
(0123456789().,-volV)(0123456789(). ,- volV)
EXTREME LEARNING MACHINE AND DEEP LEARNING NETWORKS
ELM-based driver torque demand prediction and real-time optimal energy management strategy for HEVs Jiangyan Zhang1,2
•
Fuguo Xu3 • Yahui Zhang3 • Teilong Shen3
Received: 3 January 2019 / Accepted: 9 May 2019 Ó Springer-Verlag London Ltd., part of Springer Nature 2019
Abstract In hybrid electric vehicles, the energy economy depends on the coordination between the internal combustion engine and the electric machines under the constraint that the total propulsion power satisfies the driver demand power. To optimize this coordination, not only the current power demand but also the future one is needed for real-time distribution decision. This paper presents a prediction-based optimal energy management strategy. Extreme learning machine algorithm is exploited to provide the driver torque demand prediction for realizing the receding horizon optimization. With an industrial used traffic-in-the-loop powertrain simulation platform, an urban driving route scenario is built for the source data collection. Both of one-step-ahead and multi-step-ahead predictions are investigated. The prediction results show that for the three-step-ahead prediction, the 1st step can achieve unbiased estimation and the minimum root-mean-square error can achieve 100, 150 and 160 of the 1st, 2nd and 3rd steps, respectively. Furthermore, integrating with the learning-based prediction, a real-time energy management strategy is designed by solving the receding horizon optimization problem. Simulation results demonstrate the effect of the proposed scheme. Keywords Hybrid electric vehicle Energy optimization Extreme learning machine Connected vehicles Driver demand prediction
1 Introduction The hybrid electric powertrain technology is recently spotlighted as a high efficient vehicular propulsion system. The advantage of the hybrid electric powertrain is to use the freedom in assigning the driver demand power into different power sources, mainly the internal combustion engine and electric machines, such that the energy consumption is much less than in conventional combustion engine-powered vehicles. In a hybrid powertrain, the power supplied by the different power sources effects not only the current vehicle states but also the future behaviors of the & Jiangyan Zhang [email protected] 1
College of Mechanical and Electronic Engineering, Dalian Minzu University, Dalian 116600, China
2
State Key Laboratory of Automotive Simulation and Control, Changchun 130025, China
3
Department of Engineering and Applied Sciences, Sophia University, Tokyo 102-8554, Japan
vehicle due to the mechanical inertia. In this case, not only the instantaneous energy efficiency but also the total energy consumption over a driving time interval or a targeted driving route can be optimized with efficient energy management strategies. In the past two decades, a lot of researches on hybrid electric vehicle (HEV) optimal energy management have been driven by this pot
Data Loading...
