Research on Vibration Data-Driven Fault Diagnosis for Iron Core Looseness of Saturable Reactor in UHVDC Thyristor Valve Based on CVAE-GAN and Multimodal Feature Integrated CNN

Abstract

The imbalance of data samples and fluctuating operating conditions are the two main challenges faced by vibration data-driven fault diagnosis for the iron core looseness of saturable reactors in UHVDC thyristor valves. This paper proposes a vibration data-driven saturable reactor iron core looseness fault diagnosis strategy named CVG-MFICNN based on CVAE-GAN and MFICNN to overcome the two challenges. This strategy uses a novel 1-D CVAE-GAN model to produce generated samples and expand the training set based on imbalanced training samples. An MFICNN model structure is designed to allow the simultaneous processing of multimodal features such as the SST time-frequency spectrum, time-domain vibration sequence, frequency-domain power spectrum sequence, and time-domain statistics. Using these multimodal features and the MFICNN model, the hidden fault information in vibration data can be effectively mined. An experiment is conducted to collect vibration data of saturable reactors with different faults. Models based on the proposed strategy and other methods are trained and tested using the collected data. The comparison results show that the performance of the proposed CVG-MFICNN approach is significantly superior to that of single-feature CNNs, traditional machine learning methods, and classical image classification CNNs in the application of UHVDC thyristor valve saturable reactor iron core looseness fault diagnosis.

Research on the fault diagnosis method of AC power supply in substations based on a synchronous digital sampling technology

“…In the process of detecting the fault state of the substation AC power supply based on D-S evidence theory, it will keep the substation AC power supply in the ideal working state as much as possible. Therefore, it is necessary to add a special state and uncertain state information to the total set to make it close to the ideal measurement case and form a complete set [10][11][12][13][14][15]. In this study, the detected AC power failure set is set as F and expressed as F = {F0, F1, F2, F3, θ}, where F0 represents the normal operation of the power supply, F1 represents the insulation damage of the stator winding, F2 represents the short circuit of the rotor coil, F3 represents the short circuit of the converter, and θ represents the criterion set of uncertainty.…”