Optimal Regenerative Braking Control Strategy for Electric Vehicles Based on Braking Intention Recognition and Load Estimation
Mingbin Tang, Xiangwen Zhang
Abstract
Regenerative braking technology plays a crucial role in recovering braking energy and extending the range of electric vehicles. To maximize energy recovery and ensure braking stability across various road conditions, loads, and braking intentions, an optimal regenerative braking control strategy is proposed. Firstly, the driver's braking intention is recognized using optimized modal features extracted from the brake pedal signal. Vehicle load estimation is then performed using a forgetting factor recursive least squares algorithm. Subsequently, an artificial bee colony optimization algorithm is employed to allocate optimal braking forces between the front and rear axles for different braking intentions and loads. Based on the obtained braking force distribution ratio, an optimal regenerative braking control strategy is developed, considering braking stability and energy recovery safety. The proposed strategy is validated on the dSPACE hard-in-loop platform under various simulated conditions, including different road conditions, braking intentions, and loads. The results demonstrate that braking intention, vehicle load, and road conditions all impact the regenerative braking process of electric vehicles. Moreover, the proposed regenerative braking control strategy significantly enhances the energy recovery rate and effectively reduces braking distance.