In this study, the effects of the ratio of a motor’s axial length to its pole pitch on efficiency, magnetic flux density distribution, torque, torque/weight, and motor volume were investigated in an outer-rotor (hub) brushless direct current motor. The weight and volume of an electrical machine affects the output power, efficiency and output torque, and it is advantageous to design an electric motor at an appropriate power and high efficiency with an appropriate weight and volume. Therefore, the aim of this study was to optimize the motor’s axial length and stator outer diameter, which affects the motor volume. Initially, the axial-length-to-pole-pitch ratio of the hub BLDC motor was taken at 0.75. According to this ratio, the dimensions of the rotor outer diameter, rotor inner diameter, stator outer diameter, stator inner diameter, slot height, motor axial length, and magnet thickness were optimally determined. Then, the axial-length-to-pole-pitch ratio was considered as 1, 1.50, 2, and 3, respectively. The effects of the change in the motor’s axial-length-to-pole-pitch ratio on the efficiency, torque, speed, torque/volume, torque/weight, and cogging torque were examined in a simulation environment. According to the motor’s axial-length-to-pole-pitch ratio, the torque value in the final state was 28.65% higher than the torque value in the initial state. In the last part, the motor axial length and the stator outer diameter were defined as variables in a genetic algorithm procedure and optimized. The number of poles and the number of slots were fixed parameters. Simulation studies were carried out using the finite element method via AN-SYS/Maxwell software.

Advances in semiconductor technologies, particularly in power transistors and switching diodes, have enabled higher switching frequencies and converter efficiency, renewing interest in Switched Reluctance Motors (SRMs) for electric vehicles. This work presents a data-driven approach utilizing a Long Short-Term Memory (LSTM) network capable of effectively managing temporal dependencies for estimating rotor position without sensors in SRMs. The motor investigated was custom-designed, subsequently manufactured as a prototype. The LSTM was trained and validated with experimental data collected at various speeds and load conditions. The outcomes demonstrate the model’s strong performance, with a mean squared error (MSE) of ${1.77}^{{°}^2}$, a mean absolute error (MAE) of 1.09°, and 97.35% accuracy. Compared to typical estimation methods such as back-electromotive force (EMF)-based techniques, fuzzy logic, model predictive control, feed-forward neural networks (FFNNs), and back-propagation neural networks (BPNNs), the LSTM stands out as one of the most effective and widely used models. Previous neural networks (NN)-based studies typically report ±5° accuracy, whereas LSTM keeps the error about 1° in this study. This strategy eliminates position sensors, reduces cost and complexity, and enables reliable real-time SRM control. Results indicate that the method has significant potential for electric motor drives, particularly for SRMs.

This study presents a comparison of Double Stator Single Rotor Axial Flux Inner Rotor North–South (DSSR AFIR NS) and Double Stator Single Rotor Axial Flux Inner Rotor North–North (DSSR AFIR NN) configurations based on the magnetic equivalent circuit (MEC) approach. In the first stage, a magnetic equivalent circuit model of the DSSR AFIR NS topology was developed, and the mathematical formulations of the air-gap reluctance, stator tooth reluctance, stator yoke reluctance, and rotor core reluctance constituting the magnetic flux path were derived. Considering the motor’s geometric and electromagnetic characteristics, the magnetic flux and flux density distributions in each region were analytically evaluated. The obtained results were then validated through finite element analysis (FEA). In the second stage, the DSSR AFIR NN topology was investigated using the same methodology, and the electromagnetic performances of the two machines with identical slot numbers, pole numbers, and physical dimensions were compared to determine their respective advantages and limitations. Numerical analyses show the AFIR-NN topology yields higher torque (26.53 Nm) than AFIR-NS (19.43 Nm). Conversely, AFIR-NS exhibits superior magnetic characteristics, with higher back-EMF (34.73 V vs. 19.37 V) and air-gap flux density (0.89 T vs. 0.46 T).