Degradation Stage Division and Identification of AC Contactor’s Contact System

Abstract

The stage division and state recognition during ac contactor degradation process is an important prerequisite for realizing its self-perception. In the recognition of its degradation state, the traditional method cannot effectively identify similar and overlapping degradation states, which makes it impossible to make accurate judgments when evaluating the health state of ac contactor. To solve the above problems, a method of ac contactor’s contact degradation stage division and state recognition based on boundary detection and temporal convolutional network-transformer–bidirectional gated recurrent unit (TCN-Transformer–BiGRU) was proposed in this article. First, the characteristic parameters related to the degradation of the ac contactor were obtained through the full life test, and the kernel principal component analysis (KPCA) was introduced to fuse the characteristic parameters. Then, the degradation trend of the contact system was characterized, and the boundary detection method was used to divide the ac contactor degradation stage. Finally, the TCN-Transformer–BiGRU classification prediction model was used to accurately identify the degradation state of the ac contactor. Taking other samples of the same type of ac contactor as examples, it is verified that the method has good universality and high accuracy.