Abstract
Partial discharge (PD) is not only an important symptom for monitoring the imperfections in the insulation system of a gas-insulated switchgear (GIS), but also the factor that accelerates the degradation. At present, monitoring ultra-high-frequency (UHF) signals induced by PDs is regarded as one of the most effective approaches for assessing the insulation severity and classifying the PDs. Therefore, in this paper, a deep learning-based PD classification algorithm is proposed and realized with a multi-column convolutional neural network (CNN) that incorporates UHF spectra of multiple resolutions. First, three subnetworks, as characterized by their specified designed temporal filters, frequency filters, and texture filters, are organized and then intergraded by a fully-connected neural network. Then, a long short-term memory (LSTM) network is utilized for fusing the embedded multi-sensor information. Furthermore, to alleviate the risk of overfitting, a transfer learning approach inspired by manifold learning is also present for model training. To demonstrate, 13 modes of defects considering both the defect types and their relative positions were well designed for a simulated GIS tank. A detailed analysis of the performance reveals the clear superiority of the proposed method, compared to18 typical baselines. Several advanced visualization techniques are also implemented to explore the possible qualitative interpretations of the learned features. Finally, a unified framework based on matrix projection is discussed to provide a possible explanation for the effectiveness of the architecture.
Highlights
Gas-insulated switchgears (GISs) are widely used as the major control and protection equipment in medium to ultra-high voltage substations, due to their superior compactness, high reliability, strong dielectric strength, and maintenance-free properties
It is imperative to assess the potential correlation between the Partial discharge (PD) patterns and the defect types, so that corresponding maintenance activities can be taken before a complete breakdown
Inspired by the phenomenon that the PD spectrograms of different resolutions can capture the information of different patterns, both multi-resolution and multi-sensor fusion algorithms are proposed
Summary
Gas-insulated switchgears (GISs) are widely used as the major control and protection equipment in medium to ultra-high voltage substations, due to their superior compactness, high reliability, strong dielectric strength, and maintenance-free properties. Considering the stochastic nature of PDs, machine learning has long been the mainstream method for the diagnosis of UHF signals. The recent advances in deep learning make it possible to extract high-level features automatically from high-dimensional sensory data, and they demonstrate dramatic success in various areas such as natural language processing, image classification, and auto-driving, of which the Convolutional Neural Network (CNN) has been designed for vision-related tasks [27,28]. We propose a deep multi-column architecture that incorporates multi-resolution information for the recognition of UHF signals with specified temporal filters, frequency filters, and texture filters. Six types of artificial insulation defect models in the oil, air, and paper-fiber interface.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
