A predictive energy management strategy for multi-mode plug-in hybrid electric vehicles based on multi neural networks

Abstract

Online optimal energy management of plug-in hybrid electric vehicles has been continually investigated for better fuel economy. This paper proposed a predictive energy management strategy based on multi neural networks for a multi-mode plug-in hybrid electric vehicle. To attain it, firstly, the offline optimal results prepared for knowledge learning are derived by dynamic programming and Pontryagin's minimum principle. Then, the mode recognition neural network is trained based on the optimal results of dynamic programming and the recurrent neural network is firstly exploited to realize online co-state estimation application. Consequently, the velocity prediction-based online model predictive control framework is established with the co-state correction and slacked constraints to solve the real-time optimal control sequence.A series of numerical simulation results validate that the optimal performance yielded from global optimal strategy can be exploited online to attain the satisfied cost reduction, compared with equivalent consumption minimum strategy, with the assistance of estimated real time co-state and slacked reference. In addition, the computation duration of proposed algorithm decreases by 23.40%, compared with conventional Pontryagin's minimum principle-based model predictive control scheme, thereby proving its online application potential.

Review article: A comprehensive review of energy management strategies for hybrid electric vehicles

“…The PMP-based EMS mainly achieves global optimization control of HEVs by solving the minimum value of the Hamiltonian. The Hamiltonian function is obtained by combining parameters such as the SOC, fuel consumption, and demanded power with a mathematical model of the HEV, and the optima global solution can be obtained according to the driving conditions (Wu, 2018). A flow chart of the PMPbased EMS is shown in Fig.…”

“…In Zhao and Antonio (2016), a PMP-based EMS was proposed and optimized using selective Hamiltonian minimization: a parameter analysis model was used to establish selective Hamiltonian minimization, and the selective Hamiltonian minimization was adopted to select the possible optimal control mode. In Hadj-Said et al (2017, 2018, considering the discrete variables and continuous variables for PMP-based EMSs, the energy management problem was solved using an analytical method. The power distribution of the ICE and EM, the transmission ratio, and the start-stop process of the ICE were taken as the optimization variables.…”

“…The EMS realized the identification of driving cycles through the sample learning and feature extraction of the NN and used it as the input for the fuzzy logic controller to optimize the MF. In Wu et al (2020), an EMS based on multi-NNs was proposed. The global optimization results were obtained using DP, the condition recognition NN was trained by the calculation results, and the online co-state estimation was realized using RNN, which was used as the initial value of battery power optimization.…”

Data-driven based eco-driving control for plug-in hybrid electric vehicles

“…The powertrain energy allocation is optimized according to the result of velocity optimization. Apparently, it is a standard optimal control problem which has been widely investigated in previous research [40]. Furthermore, since the driving speed profile is preplanned, and can be reckoned as the prior knowledge, the global optimization performance is guaranteed.…”

Real-time optimization of plug-in hybrid electric vehicles based on Pontryagin’s minimum principle

“…Although this strategy does not yield a globally optimal solution, its easiness allows simple implementation without any prior information about driving cycles. A broad range of research is done on MPC-based approaches to plan the battery SOC trajectory based on real-time previewed information and then optimize power distribution over a receding horizon (Wu et al 2020). Xie et al (2019a) have created the SOC reference trajectory based on the optimal depth of discharge in the prediction horizon.…”