Visual inspection of fault type and zone prediction in electrical grids using interpretable spectrogram-based CNN modeling. (30th December 2022)

• Record Type: Journal Article
• Authors: Ardito, Carmelo; Deldjoo, Yashar; Noia, Tommaso Di; Sciascio, Eugenio Di; Nazary, Fatemeh
• Is Part Of: Expert systems with applications. Volume 210(2022)
• Publication Date: 2022-12-30
• Subjects: 00-01 -- 99-00; Fault diagnosis -- Visual explanation -- Smart grids -- Interpretability; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2022.118368
• Languages: English
• ISSNs: 0957-4174

Abstract

Abstract: In electrical grids, fault diagnosis (fault type and fault location classifications) are critical due to their economic and important implications. Numerous smart grid applications have embraced data-driven methodologies. While the majority of the work in this topic has been on increasing the predicted accuracy of machine-learning model for fault diagnosis, one important aspect that has received less attention is the interpretability of these systems. We advocate for a complementary perspective. To represent faulty signals, we propose a spectrogram–convolutional neural network based representation of the electrical signals where pre-trained models such as GoogleNet and SqueezeNet are trivially used. We then perform multiple fault classification tasks and offer a visual interpretation of the collected findings. The suggested approach makes the model more transparent through the use of Gradient-weighted Class Activation Mapping (Grad-CAM), which visualizes regions in the input spectrogram that are more relevant for predictions, assisting the end-user in the understanding and interpreting the results. We explore the merits of the suggested technique in terms of increasing the transparency of the black-box machine learning system, which is a critical requirement for designing modernized smart grids. Highlights: Visual representation of electrical signal by using spectrogram-based CNN modeling. Building a visually interpretable fault type and zone classification system. A highly accurate system able to provide individual or joint FTC or FZC. Comparison with a large number of baselines using DFT or DWT.