Current regenerative braking systems in electric vehicles have several problems, such as complex structures, too many control parameters, and inconsistent braking responses. To solve these problems, a control algorithm with multidisciplinary design optimization (MDO) is proposed based on the novel regenerative–mechanical coupled brake-by-wire system. A dynamic model of the novel regenerative braking system was established to analyze the mechanism of coupled braking and propose a braking torque distribution strategy. To realize a better balance between the optimum braking stability and the maximum regenerative energy recovery based on the braking torque distribution strategy and sample points, the MDO mathematical model was developed to optimize the control parameters with the collaborative optimization algorithm. The finite sample points comprising the vehicle speed, battery state-of-charge, and braking severity were obtained through an optimal Latin hypercube design and represent the overall design space. A network was established based on the sample points and the optimization results. Using this network, the in-depth characteristics of the sample points and the optimization results were obtained through supervised learning to develop the control algorithm for vehicle braking. A simulation was performed using the normal braking condition, and the simulation results demonstrated that the control algorithm has higher control precision than conventional methods and better real-time performance than online optimization.

To improve the accuracy and actual road equivalence of vehicle performance testing using test benches, a double-drum test bench that meets the test requirements of vehicle control system prototypes and in-use vehicles was designed. Dynamic models of the single-wheel test bench and the vehicle test bench were established, and mechanisms were theoretically analyzed for single-wheel variable adhesion and vehicle load transfer for equivalent testing using the variable placement angle. The mechanism of electromechanical inertia compensation was studied to realize stepless simulation of vehicle inertia and simulate dynamic load while braking. The simulation model of the vehicle test bench system was established based on MATLAB/Simulink. Simulations were carried out to verify the anti-lock braking system (ABS) performance test functionality of the test bench under high adhesion, bisectional, and low adhesion conditions. Referring to the simulation conditions, ABS tests under actual test bench and road conditions were carried out. Results demonstrated that the mechanism of variable load transfer simulation by electromechanical inertia compensation improves the equivalent accuracy compared to that of its road test equivalent, verifying the feasibility of the simulation mechanism. This study could help further improve the accuracy and reduce the cost of vehicle performance testing, thus greatly benefitting the vehicle development and testing industry.