A novel adversarial transfer learning in deep convolutional neural network for intelligent diagnosis of gas‐insulated switchgear insulation defect

Abstract

Recently, numerous data-driven fault diagnosis methods have been developed, and the tasks involving the same distribution of training and test data have been well solved. However, considering the particularity of gas-insulated switchgear (GIS), collecting massive data, especially with the same distribution, is difficult. Therefore, existing fault diagnosis methods hardly achieve satisfactory insulation defect diagnosis with small datasets. Aiming at solving this problem, a novel domain adversarial transfer convolutional neural network (DATCNN) is proposed, realising the diagnosis of GIS insulation defects on small samples. First, a residual CNN is built to learn feature representations from the source and target domains. Second, the domain adversarial training strategy is used for feature transfer, where a conditional adversarial mechanism is introduced, and the joint distribution of features and labels is improved to a random linear combination, which realises the simultaneous adaptation of features and labels. Finally, the Nesterov accelerated gradient descent optimisation algorithm is used to speed up the gradient convergence. DATCNN has 99.15% and ≥89.5% diagnosis accuracy for GIS insulation defects in the laboratory and on-site, respectively. Comprehensive experiment results show the effectiveness and superiority of the proposed method in diagnosing GIS insulation defects with small samples.

A novel 1DCNN and domain adversarial transfer strategy for small sample GIS partial discharge pattern recognition

“…To verify the advantages of DATL in pattern recognition with small samples in the field, domainless adaptation 1DCNN, fine-tuning TL (FTL) [27], maximum mean discrepancy (MMD) domain adaptation TL (MTL) [28], conventional DATL (TDATL) [29], and the proposed DATL were compared. In all migration experiments, half of the data were used for training, and the other half for testing.…”

Characterization of internal discharge shock waves of gas‐insulated switchgears using shadowgraphy

“…Gas‐insulated switchgears (GISs) are widely used in power grids owing to their small size, long service intervals, and high reliability [1]. However, defects such as conductive particles and burrs inevitably appear inside GISs, which are caused during their manufacturing process, transport, assembly, and long‐term operation.…”

Bird pecking damage risk assessment of UHV transmission line composite insulators based on deep learning

“…Wavelet transform enlarges the smaller damage features, and SVM is used to classify and identify the health state of insulators. Convolution Neural Networks (CNNs) combined with adversarial transfer learning are used for diagnosis of gas‐insulated switchgear insulation defects [13]. The performance of CNNs for insulators defect detection is improved by data enhancement.…”