Investigation of energy management strategy for a novel electric-hydraulic hybrid vehicle: Self-adaptive electric-hydraulic ratio

Abstract

The innovation and development of energy management strategies attract more and more attention as a key technology in hybrid electric vehicles. This paper focuses on a novel type of electric-hydraulic hybrid vehicle with multiple working modes and zero emissions, which offers a deeper potential for energy efficiency. Steady-state simulation with a rule-based mode switching strategy verifies that the electric-hydraulic ratio in the hybrid driving mode can interfere with energy management performance. Committed to filling the literature gap on the electric-hydraulic ratio, this paper proposes the idea of combining deep reinforcement learning with a rule-based control strategy and employs the Twin Delayed Deep Deterministic Policy Gradient to control the electric-hydraulic ratio. Thereafter, an energy management strategy framework based on the self-adaptive electric-hydraulic ratio was developed. Offline training and online test can demonstrate that the proposed energy management strategy enables the self-adaptive electric-hydraulic ratio under various driving cycles and a significant reduction in the energy consumption rate. The research findings in this paper are the crystallization of traditional control strategy and advanced algorithm, which has stronger practical value and development prospects. This is the first time that the self-adaptive electric-hydraulic ratio is applied to the establishment of energy management strategies.