23 January 2025 in IEEE Transactions on Industry Applications
This paper proposes a flux saturation model of synchronous reluctance machines (SynRMs) using an artificial neural network. The proposed ANN model is structured with current as the input and flux as the output, and supervised learning is conducted using the current and flux data. Considering test conditions of motor drive systems, flux data were acquired through two methods based on the voltage equation. For the first one, flux data were obtained in a stationary state using hysteresis current control. In the other, flux data were acquired in a rotating state. Since the acquired data are influenced by sensor noise and inverter non-linearity, data preprocessing was performed through cleansing and normalization. Furthermore, the model was designed to be light-weighted for applications in motor drive systems. To verify the feasibility of two ANN models which were trained with different datasets, the outputs of the ANN models were compared with the current-flux data obtained in the rotating state. Moreover, the proposed ANN models were verified using model-based sensorless drives in a 1.5 kW SynRM.
15 January 2026 in IEEE Transactions on Industry Applications
This paper proposes a control algorithm for the Maximum Torque per Ampere (MTPA) operation of Interior Permanent Magnet Synchronous Motors (IPMSMs) that consider temperature variations using an Artificial Neural Network (ANN). As the temperature increases, the residual magnetic flux density of the permanent magnets decreases, leading to a reduction in the magnitude of the magnetic flux. Furthermore, even at the same temperature, the d-q axis fluxes vary depending on the current operating points due to magnetic flux saturation. These nonlinear d-q axis flux variations result in nonlinear torque variations at current operating points. ANNs are well-suited for modeling nonlinear correlations and have been widely applied across various fields. Hence, ANN is applied to MTPA operation, effectively representing the nonlinear relationship between the d axis flux and MTPA operating point variations. The proposed method utilizes a Frequency-Adaptive Observer (FAO) to estimate the d-axis flux under the present temperature. Using the ANN, the MTPA operating point is adjusted by accounting for the d-axis flux variations caused by temperature changes and magnetic flux saturation. The proposed algorithm was validated through experiments on an 11 kW IPMSM.