Safety-constrained Bayesian-optimized fuzzy regenerative braking control for a front-wheel-drive battery electric vehicle

Regenerative braking is a key technology for improving the energy efficiency of battery electric vehicles. For front-wheel-drive battery electric vehicles, the drive motor is mounted on the front axle, so regenerative braking must be coordinated with hydraulic braking while satisfying front–rear braking-force distribution, tire-adhesion, motor-torque, and battery charging-power constraints. To reduce the dependence of conventional fuzzy controllers on empirically selected membership-function parameters, this study proposes a safety-constrained Bayesian-optimized fuzzy regenerative braking strategy. A Mamdani fuzzy controller uses braking intensity, battery state of charge (SOC) and vehicle speed as inputs and the front-axle regenerative braking ratio as the output. A dimensionless multi-cycle objective combines normalized SOC depletion, braking-opportunity-normalized recovered energy, demand-normalized force-transition characteristics, and normalized command-to-executable regenerative-force mismatch. The final controller is obtained after 300 Bayesian-optimization evaluations and is assessed on six optimization cycles together with independent low-SOC, high-braking-intensity, unseen-cycle and repeated-braking validations. Across NEDC, WLTC, FTP-72, FTP-75, CLTC-P, and NYCC, the mean of the six cycle-wise recovered-energy improvements is 25.48%, while the mean of the six cycle-wise reductions in specific net battery-energy consumption is 12.13% relative to the original fuzzy controller. Without retuning, recovered energy on the unseen HWFET and US06 cycles increases by 40.03% and 30.11%, respectively, with specific energy-consumption reductions of 8.31% and 9.79%. Low-SOC and high-intensity tests satisfy the prescribed force, motor and battery-power constraints, and dynamic threshold-crossing tests show continuous total front-axle braking demand during regenerative-to-hydraulic redistribution. Repeated-braking simulations further show that the energy-recovery benefit is accompanied by increased battery electrical stress, highlighting an energy-recovery/electrical-stress trade-off.

Authors

Institutions

Publication Details

Journal
Proceedings of the Institution of Mechanical Engineers Part D Journal of Automobile Engineering
Published
2026-11-16
DOI
https://doi.org/10.1177/09544070261506522
Primary Topic
Electric and Hybrid Vehicle Technologies
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Safety-constrained Bayesian-optimized fuzzy regenerative braking control for a front-wheel-drive battery electric vehicle

牛联波, Haibo Zhang, Zhiqiang Xi, Shixuan Chen et al.
1 links
Proceedings of the Institution of Mechanical Engineers Part D Journal of Automobile Engineering
Electric and Hybrid Vehicle Technologies
article

Safety-constrained Bayesian-optimized fuzzy regenerative braking control for a front-wheel-drive battery electric vehicle

牛联波, Haibo Zhang, Zhiqiang Xi, Shixuan Chen, Tianhang Gao
article en

Abstract

Regenerative braking is a key technology for improving the energy efficiency of battery electric vehicles. For front-wheel-drive battery electric vehicles, the drive motor is mounted on the front axle, so regenerative braking must be coordinated with hydraulic braking while satisfying front–rear braking-force distribution, tire-adhesion, motor-torque, and battery charging-power constraints. To reduce the dependence of conventional fuzzy controllers on empirically selected membership-function parameters, this study proposes a safety-constrained Bayesian-optimized fuzzy regenerative braking strategy. A Mamdani fuzzy controller uses braking intensity, battery state of charge (SOC) and vehicle speed as inputs and the front-axle regenerative braking ratio as the output. A dimensionless multi-cycle objective combines normalized SOC depletion, braking-opportunity-normalized recovered energy, demand-normalized force-transition characteristics, and normalized command-to-executable regenerative-force mismatch. The final controller is obtained after 300 Bayesian-optimization evaluations and is assessed on six optimization cycles together with independent low-SOC, high-braking-intensity, unseen-cycle and repeated-braking validations. Across NEDC, WLTC, FTP-72, FTP-75, CLTC-P, and NYCC, the mean of the six cycle-wise recovered-energy improvements is 25.48%, while the mean of the six cycle-wise reductions in specific net battery-energy consumption is 12.13% relative to the original fuzzy controller. Without retuning, recovered energy on the unseen HWFET and US06 cycles increases by 40.03% and 30.11%, respectively, with specific energy-consumption reductions of 8.31% and 9.79%. Low-SOC and high-intensity tests satisfy the prescribed force, motor and battery-power constraints, and dynamic threshold-crossing tests show continuous total front-axle braking demand during regenerative-to-hydraulic redistribution. Repeated-braking simulations further show that the energy-recovery benefit is accompanied by increased battery electrical stress, highlighting an energy-recovery/electrical-stress trade-off.

Proceedings of the Institution of Mechanical Engineers Part D Journal of Automobile Engineering
Henan University of Science and Technology (CN), Xinxiang University (CN)
Affordable and clean energy, Industry, innovation and infrastructure
Electric and Hybrid Vehicle Technologies
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon