The heat loss and cooling modes of a permanent magnet synchronous motor (PMSM) directly affect the its temperature rise. The accurate evaluation and prediction of stator winding temperature is of great significance to the safety and reliability of PMSMs. In order to study the influencing factors of stator winding temperature and prevent motor insulation ageing, insulation burning, permanent magnet demagnetization and other faults caused by high stator winding temperature, we propose a computer model for PMSM temperature prediction. Ambient temperature, coolant temperature, direct-axis voltage, quadrature-axis voltage, motor speed, torque, direct-axis current, quadrature-axis current, permanent magnet surface temperature, stator yoke temperature, and stator tooth temperature are taken as the input, while the stator winding temperature is taken as the output. A deep neural network (DNN) model for PMSM temperature prediction was constructed. The experimental results showed the prediction error of the model (MAE) was 0.1515, the RMSE was 0.2368, the goodness of fit (R²) was 0.9439 and the goodness of fit between the predicted data and the measured data was high. Through comparative experiments, the prediction accuracy of the DNN model proposed in this paper was determined to be better than other models. This model can effectively predict the temperature change of stator winding, provide technical support to temperature early warning systems and ensure safe operation of PMSMs.

This article proposes a sensorless speed control approach of Induction motor (IM) applying full-order terminal sliding-mode (FOTSM) control theory. The speed control system consists of three feedback control loops, i.e., the speed-, flux-, and current-loops. The related controllers in these three feedback loops are designed using FOTSM to enhance the robustness and dynamic performance, eliminate the singularity, and attenuate the chattering. The virtual control technique is utilized in the outer-loop speed controller to compensate unmatched uncertainties in the system, such as load disturbance and some parameter variations. The integral-type continuous control law with gain adaptation algorithm guarantees that the current references are smooth. In the inner-loop controllers, the actual voltage control signals can force the tracking errors of the currents to converge to its equilibrium point within finite time. Meanwhile, the FOTSM observer is designed for estimating the flux and speed of the motor simultaneously. Finally, the experiment results have demonstrated the effectiveness and feasibility of the proposed sliding-mode controllers and observers for the sensorless speed control of IM.

In order to study the problem of the high temperature reached by the end windings, caused by the high current in the armature windings of permanent magnet synchronous motors (PMSM), a 560 kW gas and liquid cooling PMSM used for a compressor is analyzed. The heat source is obtained by a two-dimensional numerical analysis of the electromagnetic field. A three-dimensional fluid-solid coupling heat transfer model is established. Under the action of the cooling medium, one-quarter of the PMSM structure is numerically simulated. The temperature distribution of the 560 kW PMSM is studied, including rotor rotation. The temperature distribution of the PMSM armature winding and the distribution of fluid around the winding under different inlet air flow speeds are analyzed. The calculated values of the end winding temperature at different currents are compared with the experimentally measured values. The rationality of the three-dimensional fluid-solid coupling heat transfer model and the correctness of the calculation method are verified. This paper provides both the analysis and the computation scheme of the fluid-solid heat transfer of the PMSM.

Since the structure of a large capacity turbogenerator is complex in the end region, accurate calculation about the leakage magnetic field becomes a key factor in the design. In this paper, a 330-MW level turbogenerator is electromagnetically analyzed and investigated with different metal screens in the end region. Its nonlinear transient electromagnetic field and eddy current loss were calculated by using the time step finite-element method (FEM). The influences of metal screen materials on the electromagnetic field and eddy current loss were compared and analyzed. All of these will contribute to the turbogenerator engineering design. Using the loss gained by the magnetic field calculation as a heat source, the thermal field of the end region with a copper screen was calculated. Compared with the test data, the calculated temperature results match well with the measured data.

Eddy current analysis is a key issue for large turbine generators. The finite-element method (FEM) is a computational tool for obtaining the electromagnetic characteristics of electrical machines. In this article, we propose a computer model of the eddy current losses of metal fasteners in the rotor slots of a large turbine generator. The electromagnetic properties of the rotor fasteners and the outer diameter of the rotor are taken as the input, and the eddy current loss of the rotor fasteners is taken as the output. A prediction model is constructed using the FEM and deep learning. The analysis results show that compared with the independent finite-element analysis, this method reduces the design cycle time and improves the design efficiency for a large-capacity turbine generator. Compared with other machine learning models, the error is smaller and the accuracy is higher. This method provides a new way to accurately predict the eddy current loss of a generator under complex nonlinear conditions.

With increased turbogenerator capacity and electromagnetic load, overheating of the complex end parts has become one of the main problems affecting safe and stable turbogenerator operation. In this research, a flow network was built representing the structural and ventilation characteristics of a 330-MW turbogenerator. The fan inlet velocity and pressures (boundary conditions) of each end-region outlet were obtained by the flow network method. The 3-D transient electromagnetic field in the turbogenerator end was calculated, and the eddy current losses (heat sources) of the end parts were obtained by the finite-element method. To study the surface heat-transfer coefficient distribution on the stator-end winding surface, fluid and thermal mathematical and geometric models of the whole turbogenerator end region were given. Using the finite-volume method, the surface heat-transfer coefficient distribution on the complex 3-D stator-end winding surface, fluid-flow distribution, and temperature distribution of the end parts were investigated under rated-load conditions. The calculated temperature results match well with measured data. This research can provide a theoretical basis for calculating the heat-transfer coefficients of the outer surfaces of large turbogenerators.