21 May 2024 in Wind Energy
This study introduces a constrained many‐objective optimization approach for the optimal design of 20 MW direct drive (DD) permanent magnet synchronous generators (PMSGs). Designing a high‐performance, competitive DD‐PMSG requires considering the generator's performance as well as its weight and material cost. Therefore, we focus on four main characteristics as our design objectives: (1) specific power (power per weight), (2) power‐per‐cost, (3) efficiency, and (4) power factor. To achieve this, we apply an advanced constrained nondominated sorting genetic algorithm III (NSGA‐III), a many‐objective optimization method utilizing evolutionary computation, capable of optimizing four or more objectives with constraints. Additionally, the electromagnetic finite element method is employed to evaluate the generator's characteristics. Through our proposed design process, we optimize three distinct 20 MW DD‐PMSG configurations: a 320‐pole/300‐slot, a 350‐pole/300‐slot, and a 350‐pole/336‐slot topology. Following this optimization, we perform additional multiphysics simulations (covering electromagnetic, structural, overload, and thermal aspects) and control response simulations on four selected models from the Pareto‐optimal solutions to validate their effectiveness as preliminary DD‐PMSG designs. Finally, we conduct a comprehensive analysis of all simulation results.
22 February 2023 in IEEE Access
In permanent magnet motors, the stator resistance and magnetic flux of the magnet change as the temperature increases. These changes result in a change in the maximum torque point per unit ampere (MTPA) of the motor. Without adequate compensation, this leads to a decrease in output torque. For this reason, look-up table (LUTs) are prepared over the temperature range and used for interpolation. This paper proposes a method to compensate for the output torque reduction due to a temperature increase using only a single LUT prepared at a base temperature. First, an estimation of the magnetic flux linkage and the output torque using a single LUT is performed. Second, the problem is modeled as a limited optimization problem to minimize the loss due to the torque reduction. The magnetic flux linkage and output torque are calculated in real time through the fundamental active power. The compensation value is calculated using the Lagrange multiplier method, an optimization technique, using the estimated magnetic flux linkage and output torque. The proposed method is verified by comparing it with other algorithms through simulation and experiment.
25 July 2025 in Journal of Electrical Engineering & Technology
3 June 2024 in Journal of Electrical Engineering & Technology
12 November 2025 in IEEE Transactions on Industrial Electronics
This article proposes a hybrid approach that combines magneto-quasi-static finite element analysis (MQS-FEA) with analytical formulas to efficiently estimate ac copper losses in an electric vehicle propulsion motor with hairpin windings. The method accurately accounts for both skin and proximity effect losses, while substantially reducing computation time. Skin effect losses caused by both the sinusoidal current and pulse width modulation (PWM) harmonics are calculated using a reactance-limited loss equation, which effectively captures current redistribution and accelerates loss evaluation. For proximity effect losses, MQS-FEA is first used to compute the slot leakage flux and PM fields under sinusoidal excitation. The frozen permeability method is then applied to estimate PWM-induced slot leakage flux. To improve the accuracy of proximity loss estimation, a probabilistic approach is employed. The representative external fields are defined by selecting harmonic components based on kernel density estimation of the continuous probability density function of element-wise flux densities. The resulting eddy current losses are evaluated using the reactance-limited formulation, incorporating PWM-induced fields. Compared with using only transient FEA, it also facilitated rapid efficiency map construction. Finally, experimental validation using a 150 kW target motor confirmed the accuracy of the proposed method.