Few-Shot Transfer Learning with Attention Mechanism for High-Voltage Circuit Breaker fault diagnosis

Abstract

Data-driven artificial intelligence methods, especially convolutional neural networks (CNNs), have achieved excellent performance in high-voltage circuit breaker (HVCB) fault diagnosis. However, CNN relies heavily on massive data. When the amount of data decreases, the fault diagnosis performance drops severely. To settle these problems, a few-shot transfer learning (FSTL) with attention mechanism to realize the mechanical fault diagnosis of HVCBs is proposed. First, a one-dimensional CNN (1DCNN) with attention mechanism (AM) is used to extract the fault features of HVCBs. The introduction of the AM makes CNN pay more attention to the interesting part of the fault signal to extract effective key features. Then, domain adaptive transfer learning (DATL) is used to realize the deployment and application of 1DCNN constructed under a large amount of low-voltage level data to small samples of ultra-high voltage (UHV), so as to realize reliable diagnosis of UHV circuit breakers in small samples. The proposed DATL can consider the marginal and conditional distributions of the two data simultaneously to achieve better feature matching. Experimental results show that the FSTL proposed can achieve highly accurate and robust fault diagnosis of HVCBs with few-shot on site. Compared with the traditional methods, the FSTL is obvious and provides a reliable reference for the diagnosis of HVCBs.