Energy management method for plug-in hybrid electric vehicles based on SOC reference trajectory

Abstract

The invention discloses an SOC (state of charge) reference trajectory based energy management method for plug-in hybrid electric vehicles. The SOC reference trajectory based energy management method includes the following steps: predicating the vehicle speeds, planning time-dependent SOC trajectories of the plug-in hybrid electric vehicles, and introducing model predication control for SOC trajectory constraints. The SOC reference trajectory based energy management method has the advantages that a long short term memory neural network, as a variant of a recurrent neural network, inherits the advantages of the recurrent neural network in processing time series, and has an additional long-term prediction ability; the correspondence relationship between SOC reference trajectories and the vehicle speeds is established, the method can well adapt to the influences of the change of the traveling speeds in different time periods on SOC declining trajectories, the calculation of the reference trajectories is accurate, and accordingly, optimization results are accurate; the optimization algorithm based on the SOC reference trajectories has higher implementability than a global optimization algorithm.

Description

technical field [0001] The present invention is directed to a plug-in hybrid electric vehicle (PHEV, Plug-in hybrid electric vehicle) energy management system, in particular to a plug-in hybrid electric vehicle energy based on a battery state of charge (SOC, State of Charge) reference trajectory management method. Background technique [0002] The current PHEV control strategies mainly include rule-based control strategies, optimization model-based control strategies, and model prediction-based control strategies. Among them, the rule-based management strategy is the most widely used, but its dynamic characteristics are poor and it is difficult to achieve the optimal dynamic system. Matching; optimization-based energy management strategies are further divided into global planning control strategies and instantaneous control strategies. Among them, it is generally believed that the global planning can achieve the theoretical optimal value of the entire working condition, but ...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the problem that the current SOC reference trajectory calculation method cannot adapt to changes in vehicle speed or working conditions, the present invention proposes a plug-in based on SOC reference trajectory that can adapt to real-time changes in vehicle driving conditions and obtain energy-saving effects close to the global optimum. Energy management method for hybrid electric vehicles

Images