Driving cycle prediction plays a key role in energy management strategy (EMS) for hybrid electric vehicles (HEVs). This paper studies a driving cycle prediction method based on convolutional neural network (CNN). Firstly, the k-shape clustering method is used to group the driving cycle data into six different types. Moreover, this method is compared with the k-means algorithm which is often used for clustering driving cycles. Secondly, CNN is adopted to predict the different types of the driving cycles based on the results of k-Shape clustering. Some basic features are selected to construct the input of the networks with no assistance of human experience. In the process of training neural networks, some high-level features which can describe the information of a driving cycle more accurately are extracted, and the deep neural networks are built, which are different from traditional experience-based driving cycle prediction methods. And then, the better performance of the proposed method is illustrated by making a comparison with the traditional machine learning method. Finally, an adaptive energy management strategy for plug-in hybrid electric buses (PHEB) based on deep learning is given, and simulation results prove the effectiveness of the proposed method. INDEX TERMS Plug-in hybrid electric bus, driving cycle prediction, energy management strategy, deep learning.
Vehicle-following operation is a typical scenario in the future intelligent transportation environment. Keeping a safe distance is the most important goal in the vehicle-following scenario. For a plug-in hybrid electric bus (PHEB) running in a specific urban route, the challenge will become how to realize the optimal power split in hybrid powertrain under the premise of maintaining driving safety. Considering the above issues, this paper proposes a stochastic model predictive control (SMPC) strategy for PHEBs during vehicle-following scenario. Firstly, Markov chain-based stochastic driving model is built using real-world bus driving condition data, which is applied to predict future demand torque over a finite receding horizon. And then, a sequential quadratic programming (SQP) algorithm is adopted to solve the rolling optimization problem. Meanwhile, brake specific fuel consumption and electric motor efficiency are fitted offline to match the SMPC strategy. Furthermore, a piecewise function is given to adjust the adaptive factor that balancing fuel economy and vehicle-following in the pre-set cost function. Finally, to verify the control performance of the proposed strategy, a nonlinear model predictive control strategy with dynamic programming optimization (DP-MPC) and a rule-based (RB) strategy are employed for comparison study. Results indicate that the proposed strategy is effectiveness to the given driving condition with excellent fuel economy and vehicle-following performance. Under the driving condition of Chongqing 303 bus line in China and China typical, the fuel consumption is reduced by 20.58% and 37.89% compared with RB strategy, respectively. It is closer to the fuel consumption reduction of 16.77% and 13.11 optimized by DP-MPC. Driving safety during vehicle-following also be demonstrated in the driving condition of Chongqing 303 bus line and China typical. INDEX TERMS Plug-in hybrid electric bus, energy management, vehicle-following, stochastic model predictive control, sequential quadratic programming optimization.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.