Design of non-electrical protection device for 300Mvar-class large-scale phase-regulating units

Abstract

Abstract This study investigates the role of non-electrical protective devices in forecasting hazards for large 300Mvar class phase shifter units, which face overvoltage and overcurrent stresses under severe faults, distorting their internal magnetic fields. Utilizing migration learning, the research extracts target and auxiliary data to train autoencoders with sparse constraints. A deep learning-based DSAE-BP online recognition network is constructed using a backpropagation neural network. This network predicts potential safety hazards in large-scale phase-regulating units by analyzing data signals from connected sensors. Experimental results show delay time errors of less than 20ms and ripple rates between 1.40%-1.65% across varied current and voltage conditions, demonstrating the device’s accuracy and stability in fault prediction.