Aiming at the impact of heat generation and temperature rise on the driving performance of a permanent magnet (PM) motor, taking the PM in-wheel motor (IWM) for electric vehicles as an object, research is conducted into the temperature distribution of the electromagnetic–thermal effect and cooling structure optimization. Firstly, the electromagnetic–thermal coupling model considering electromagnetic harmonics is established using the subdomain model and Bertotti’s iron loss separation theory. Combined with the finite element (FE) simulation model established by Ansoft Maxwell software platform, the winding copper loss, stator core loss and PM eddy current loss under the action of complex magnetic flux are analyzed, and the transient temperature distribution of each component is obtained through coupling. Secondarily, the influence of the waterway structure parameters on the heat dissipation effect of the PM-IWM is analyzed by the thermal-fluid coupled relationship. On the basis, the optimization design of waterway structure parameters is carried out to improve the heat dissipation effect of the cooling system based on the proposed chaotic mapping ant colony algorithm with metropolis criterion. The comparison before and after optimization shows that the temperature of key components is significantly improved, the average convection heat transfer coefficient (CHTC) is increased by 23.57%, the peak temperature of stator is reduced from 95.47 °C to 82.73 °C, and the peak temperature of PM is decreased by 14.26%, thus the demagnetization risk in the PM is improved comprehensively. The research results can provide some theoretical and technical support for the structural optimization of water-cooled dissipation in the PM motor.

Reinforcement learning (RL) has the capability to discover optimal interactions with the surrounding environment, with the advantage that nearly all required computations can be performed offline. Nevertheless, the lack of explainability for RL-based solutions may prevent their large-scale application in industrial autonomous vehicle tasks. Furthermore, the RL method tends to be unsafe and brittle to scenarios not encountered in training. Conversely, the optimization-based method offers a substantial level of explainability, and through the explicit inclusion of safety constraints, it can guarantee the system’s safety. In this context, building upon RL framework, a fusion algorithm that combines the advantage of the RL-based scheme and optimization-based scheme is proposed. Specifically, unlike traditional RL-based solutions which directly executes from perception to control using only neural network maps, this work introduces a mechanism of uncertainty-aware interval prediction to compute the set of states that can be reached over the planning time horizon. On this basis, a robust control framework is presented, which guarantees system safety while considering the worst-case performance scenarios. To validate the proposed algorithm, the task of an autonomous vehicle merging on to a highway from an on-ramp is simulated in SUMO. The results show that the proposed motion planning and control method combines the advantages of RL and optimization-based methods and achieves balanced performance in smoothness, computational efficiency, explainability and robustness.

This paper presents a novel integrated permanent magnet (PM) in-wheel motor (IWM) driving system for electric vehicles (EVs), in order to overcome the disadvantages of electromagnetic vibration and cogging torque in the topology scheme, on the basis of maintaining high output torque. Firstly, the transient magnetic field of the integrated PM motor is analyzed using the improved analytical subdomain model and finite element (FE) model. The harmonic component of magnetic force density (MFD) is obtained with no-load condition. Furthermore, the vertical dynamic model for the dynamic vibration absorber is established to investigate the influence of the magnetic force harmonic on the vibration response of the stator and rotor. On this basis, the multi-objective optimization design of the pole–slot structure parameters is carried out by using the adaptive weighted particle swarm optimization (AWPSO) algorithm. Finally, the optimization results are compared and verified by FE analysis. The investigation shows that the unbalanced magnetic force and cogging torque is significantly reduced by the adjustment of the pole-arc coefficient, PM thickness, stator slot width and slot opening width.

The permanent magnet (PM) of synchronous motors is susceptible to factors such as high temperature, reverse magnetic field, and impact vibration, resulting in demagnetization faults that directly affect the operational performance of machine. To address the prediction problem of time-dependent demagnetization, an improved subdomain analytical model is proposed and reapplied to predict magnetic fields considering demagnetization effects. The degree and distribution of demagnetization are innovatively described and defined using orthogonal design and statistical methods. Taking the 20/24 PM in-wheel motor (IWM) as an object, the variation of magnetic field and back electromotive force (EMF) under different demagnetization cases and degrees are compared and analyzed according to the Maxwell’s theory and field-circuit coupling time-stepping finite element (FE) method. And the evolution rules and reconstruction characteristics of unbalanced electromagnetic force (UEF), cogging torque, and output torque are explored. The results demonstrate that the improved model predictions agree well with that of simulation results, and the amplitude of flux density and back EMF in demagnetized region are significantly lower compared to healthy conditions. Under the uniform demagnetization, the waveform of UEF, cogging torque, and output torque generated by the residual magnetic field is almost consistent with the healthy condition, with relatively lower peaks. In other cases, with the expansion of demagnetization degrees and demagnetized PM’s numbers, the resulting UEF increases in a stepped pattern, and the cogging torque and output torque both increase to varying degrees.