Power transmission network physically connects the power generators to the electric consumers extending over hundreds of kilometers. There are many components in the transmission infrastructure that requires a proper inspection to guarantee flawless performance and reliable delivery, which, if done manually, can be very costly and time taking. One of the essential components is the insulator, where its failure could cause the interruption of the entire transmission line or widespread power failure. Automated fault detection of insulators could significantly decrease inspection time and its related cost. Recently, several works have been proposed based on convolutional neural networks to deal with the issue mentioned above. However, the existing studies in the literature focus on specific types of fault for insulators. Thus, in this study, we introduce a two-stage model in which we first segment insulators from the background images and then classify its state into four different categories, namely: healthy, broken, burned, and missing cap. The test results show that the proposed approach can realize the effective segmentation of insulators and achieve high accuracy in detecting several types of faults.
View on arXiv