Regenerative Braking Algorithm for Parallel Hydraulic Hybrid Vehicles Based on Fuzzy Q-Learning

Abstract

The use of regenerative braking systems is an important approach for improving the travel mileage of electric vehicles, and the use of an auxiliary hydraulic braking energy recovery system can improve the efficiency of the braking energy recovery process. In this paper, we present an algorithm for optimizing the energy recovery efficiency of a hydraulic regenerative braking system (HRBS) based on fuzzy Q-Learning (FQL). First, we built a test bench, which was used to verify the accuracy of the hydraulic regenerative braking simulation model. Second, we combined the HRBS with the electric vehicle in ADVISOR. Third, we modified the regenerative braking control strategy by introducing the FQL algorithm and comparing it with a fuzzy-control-based energy recovery strategy. The simulation results showed that the power savings of the vehicle optimized by the FQL algorithm were improved by about 9.62% and 8.91% after 1015 cycles and under urban dynamometer driving schedule (UDDS) cycle conditions compared with a vehicle based on fuzzy control and the dynamic programming (DP) algorithm. The regenerative braking control strategy optimized by the fuzzy reinforcement learning method is more efficient in terms of energy recovery than the fuzzy control strategy.

Regenerative Braking of Electric Vehicles Based on Fuzzy Control Strategy

“…In order to compare the energy saving efficiency of regenerative braking mor prehensively, 21 previous studies on regenerative braking are listed in In order to compare the energy saving efficiency of regenerative braking more comprehensively, 21 previous studies on regenerative braking are listed in [27] electric vehicles fuzzy Q-learning UDDS 8.91% Zhao et al [28] hybrid electric vehicles fuzzy optimization NEDC 1.22% Li et al [70] electric vehicles fuzzy control method NEDC 9.12% Wu et al [92] dual-motor EVs genetic algorithm self-defined braking 22.8% Yin et al [93] hybrid electric vehicles Q-learning network self-defined braking 7.4% Zhang et al [106] designed a Sugeno fuzzy logic controller which has three inputs, the driver's braking requirements, vehicle speed, and battery SOC, and one output, regenerative braking force. They indicate that in the UDDS drive cycle, the energy saving efficiency reaches 22.29%.…”

“…A dual-layer, multi-parameter regenerative braking control technique was put forward by Geng et al [26], and it was shown to considerably increase the ability of vehicles to recover energy. A fuzzy control technique was developed by Ning et al [27] with a 5.4% increase in the effective recovery rate of regenerative braking energy. Fuzzy optimization algorithms were utilized by Zhao et al [28] to reduce battery usage by 1.22%.…”

“…10 21,21-26,70,92-105]. It can be seen that the energy recovery efficiency of He et al[10 et al [11], Jiang et al[21], Geng et al[26], Ning et al[27], Zhao et al[28], Li et Yin et al[93], Chen et al[94], Shang et al[98], Chang et al[99], Chun et al[100] al [101],. Heydari et al[102], and Gang et al[105] was less than 15%.…”

A Logic Threshold Control Strategy to Improve the Regenerative Braking Energy Recovery of Electric Vehicles

“…Geng et al [26] proposed a dual-layer multi parameter control strategy for braking energy recovery, which significantly improves the energy recovery efficiency of the vehicle. Ning et al [27] proposed an energy recovery efficiency optimization algorithm based on fuzzy Q-learning. Under the conditions of the UDDS cycle, the energy recovery efficiency was improved by approximately 9%.…”