Jointly dampening traffic oscillations and improving energy consumption with electric, connected and automated vehicles: A reinforcement learning based approach

Torque optimization control for electric vehicles with four in-wheel motors equipped with regenerative braking system

This paper introduces a novel approach for dynamically detecting the lowest speed threshold at which regenerative braking is effective in electric vehicles (EVs). The control approach is based on real-time sensing of the motor controller dc link current and disabling regenerative braking when current changes direction while the motor is operating as a generator. Various factors influencing the regenerative braking capability of EVs at low speed are discussed, and the simulation studies are carried out to illustrate the effect of each factor on the displacement of the low-speed threshold. Based on the results obtained from the simulation studies, a dynamic low-speed cutoff point (LSCP) detection method is proposed. This method requires no hardware modification to the vehicle braking architecture and can be implemented solely by modifying the brake controller. The proposed method is tested on an experimental EV test platform for a predetermined drive cycle. It is shown that in comparison to considering a constant low-speed threshold during braking, the amount of energy recaptured through the regenerative braking process can be improved by taking advantage of the proposed method.

Maximizing Regenerative Braking Energy Recovery of Electric Vehicles Through Dynamic Low-Speed Cutoff Point Detection

The driving motor of the electric vehicle (EV) can recover the kinetic energy during normal braking maneuvers by a regenerative function At the same time, its dynamic torque response proves to be accurate and fast for an emergency braking, namely an anti-lock braking, with the coordinated control of the frictional braking system However, vehicle transmission properties will deteriorate the control performance of the motor, especially in the anti-lock braking process A novel permanent magnet synchronous motor (PMSM) control method is proposed considering the transmission influence on this high-dynamic braking process of the pure EV First, the EV's dynamic model, which includes the PMSM field-oriented control model, the transmission dynamic model, and the hydraulic braking system, is built, and the influences of transmission elasticity and backlash non-linearity on the motor-braking torque are analyzed Then, based on the wheel slip ratio target of the anti-lock braking, the novel mode-switching method for the motor-torque control between the backlash sliding-mode compensation and the elasticity double-closed-loop PID compensation is put forward Two state-of-the-art anti-lock braking algorithms, which simplify the transmission properties, the slip ratio phase-plane theory, and the sliding-mode control, are compared with the proposed method Simulation and test-bench experiment results show that, on different test-road surfaces, the mode-switching PMSM control can effectively compensate for transmission effects and significantly improve the EV's anti-lock braking comfort, stability, and maneuverability with fast and accurate motor-torque regulating

Novel PMSM Control for Anti-Lock Braking Considering Transmission Properties of the Electric Vehicle

Dynamic state estimation is of considerable importance to the system monitoring, advanced control, and energy management of electrified vehicles (EVs). Among the dynamic states of various vehicle systems, the brake pressure is a key state that reflects the braking intent and maneuver of a driver and is highly correlated with the safety and energy performance of an EV. Thus, it is worth formulating a high-precision estimation algorithm for the brake pressure to better identify the braking intent of a driver and further enhance the multiperformance of the EVs. In this article, an integrated time-series model (TSM) based on multivariate deep recurrent neural networks (RNN) with long short-term memory (LSTM) units is developed for the dynamic estimation of the brake pressure of EVs. The naturalistic driving data are collected using a real electric vehicle under standard driving cycle scenarios. The signals of the vehicle and system states are measured using the controller area network (CAN) bus and preprocessed for model training and prediction. Next, a real-time multivariate LSTM-RNN model for brake pressure estimation is constructed based on the integrated speed estimation model. The real-time scheme iteratively estimates the future velocity and integrates this signal with other vehicle states to estimate a precise value of the braking pressure. The proposed integrated TSM approach is compared with several existing baseline methods to demonstrate the advantage of the method. The testing results indicate that the proposed integrated TSM method can achieve a more reliable multistep prediction with a higher accuracy compared to that of the other methods, which demonstrates the feasibility and effectiveness of the proposed approach.

Dynamic State Estimation for the Advanced Brake System of Electric Vehicles by Using Deep Recurrent Neural Networks

Recycling braking energy is significant to improve the total energy efficiency of electric vehicles (EVs). Moreover, braking safety must be maintained under complex conditions. As the actuator, the electric traction motor has much better features than the internal combustion engine, e.g., faster torque response and capability for energy feedback. From the perspective of energy efficiency and safety, highlighting regenerative braking is a meaningful but challenging problem. In this paper, a braking system using only electric motors/generators as the actuators is investigated, in which the energy may be potentially fed back to the onboard energy storage system (ESS) as much as possible. The energy that may be recovered to the ESS is analyzed. To maintain the stability and to improve the performance of the regenerative braking in unknown tire–road conditions, a knowledge-based methodology in a hierarchical control structure is proposed, where the maximum adhesion force and the motor reference torque (MRT) are determined online. The proposed methodology avoids the complex determination of the optimum slip ratio, while acquiring nearly the optimum antiskid braking performance. Simulation and experiment were carried out to validate the effectiveness.

Fully Electrified Regenerative Braking Control for Deep Energy Recovery and Maintaining Safety of Electric Vehicles

The utility model relates to a hub assembly. The hub assembly comprises a hub motor and a brake, wherein an inner stator of the hub motor is connected with an inner side supporting member; the outer side of an outer rotor of the hub motor is connected with an outer side supporting member; the center of the outer side supporting member is connected with one end of a central shaft; the other end of the central shaft passes through a central hole of the inner stator and the inner side supporting member; a rotary element of the brake is fixedly connected with the end of the central shaft which passes through the inner side supporting member; the inner side supporting member is fixedly connected with a corresponding structure of an electric automobile frame by a motor connecting piece; an internal space for properly accommodating the rotary element is formed in the motor connecting piece; a braking element of the brake is fixedly arranged at a corresponding position of the motor connecting piece; and a power line channel which is suitable for a motor power line to pass is formed at a corresponding position of the inner side supporting member. The utility model provides one hub assembly which can be conveniently provided with the brake and can bear relatively large shearing force and an electric automobile rear axle with the hub assembly.

Xinye Zhang

Papers

Fully Electrified Regenerative Braking Control for Deep Energy Recovery and Maintaining Safety of Electric Vehicles

Hub assembly and electric automobile rear axle with same