Online Predictive Maintenance Monitoring Adopting Convolutional Neural Networks

Thermal, electrical and mechanical stresses age the electrical insulation systems of high voltage (HV) apparatuses until the breakdown. The monitoring of the partial discharges (PDs) effectively assesses the insulation condition. PDs are both the symptoms and the causes of insulation aging and—in the long term—can lead to a breakdown, with a burdensome economic loss. This paper proposes the convolutional neural networks (CNNs) to investigate and analyze the aging process of enameled wires, thus predicting the life status of the insulation systems. The CNNs training does not require any kind of assumption of how the factors (e.g., voltage, frequency and temperature) contribute to the life model. The experiments confirm that the proposal obtains better estimations of the life status of twisted pair specimens concerning existing solutions, which are based on strong hypotheses about the life model dependency on the factors.

A Novel Diagnosis Method for Void Defects in HVDC Mass-Impregnated PPLP Cable Based on Partial Discharge Measurement

Mass Impregnated PPLP cable, which is applied to various high-voltage direct current (HVDC) projects due to its excellent dielectric and temperature properties, has a problem wherein voids are formed inside the butt-gap due to cavitation. However, there has been no previous research into technology for void defect identification and insulation diagnosis on HVDC MI-PPLP cables. In this paper, to propose an insulation diagnosis method for void defects in HVDC MI-PPLP cable, the direct current (DC) void discharge patterns were analyzed according to the specimen temperature and the magnitude of applied voltage using the pulse sequence analysis method. In addition, to confirm the pre-symptoms of dielectric breakdown in MI-PPLP cable due to DC void discharge, partial discharge patterns were analyzed continuously until dielectric breakdown occurred. From the experimental results, DC void discharge patterns of the same shape were obtained regardless of the specimen temperature and the magnitude of applied voltage. In addition, it was confirmed that new insulation aging patterns were generated as electrical and thermal aging occurred due to the continuous DC void discharge. Therefore, it is demonstrated that identification and insulation diagnosis of void defects in HVDC MI-PPLP cable is possible through the obtained DC void discharge and insulation aging patterns.

Numerical simulation of heat dissipation of surface mounted permanent magnet synchronous hub motor

Due to the insulation aging, demagnetization and other problems of the permanent magnet and insulating material in the permanent magnet synchronous hub motor under high temperature, the numerical simulation of the heat dissipation of surface mounted permanent magnet synchronous hub motor is proposed. According to the heat transfer of hub motor, the effect degree of heat conduction, heat convection and heat radiation is obtained, the heat transfer coefficient of each part is calculated, and the influence of motor insulation material on temperature rise is analyzed. The experimental results show that the heat dissipation of hub motor under natural cooling condition is poor, and the internal oil cooling method can effectively improve the heat dissipation of hub motor and reduce the temperature difference. When operating at high speed, this reduces the potential safety hazard.