Search

Summary: Fault diagnosis is vital for detecting the type of fault and rapid restoration of the electric power supply. The existing machine learning‐based classification method for detecting fault shows better performance. But these methods require manual pre‐processing steps and feature engineering, which makes them unreliable and time‐consuming for the complex and multi‐bus system. In this paper, a fully automated approach based on a deep learning framework has been proposed for the multi‐classification of faults in a grid network. The deep learning framework provides a better incentive to predict the type of fault directly using raw data as input. For this intended task of fault diagnosis, a fully convolutional network is designed and implemented to provide better performance with less trainable parameters. The proposed scheme is tested on the large number of simulated data generated from an IEEE 30 bus system. The performance for fault classification is validated through 10‐fold cross‐validation and numerous performance metrics like accuracy, recall, precision, specificity, and F1 score are evaluated. The performance of the different models with parameter variation is compared to obtain better performance with optimal trainable parameters. It has also been compared with some existing methods and shows promising result for fault classification in the large or multi‐bus system. [ABSTRACT FROM AUTHOR]

Summary: With growth of a defect on the gear tooth surface, vibration response of the geared rotor system changes, which can be quantified using a health indicator. Based on the health indicator, identification of an accurate health stage or categorization is crucial so that the pitting severity classification can be done precisely. In all the prior reported works, the fault severity classification approaches are applied to the seeded pitting fault, and hence, exact state change point is known in advance. However, in the real life, the gear tooth surface is subjected to a natural pitting progression, and exact state change point of the gear is not known a priori. This study presents a binary segmentation methodology for identification of multiple degradation stages such as initial pitting, medium pitting, and severe pitting in a spur gear subjected to natural pitting progression. The gear damage progression is represented by a correlation coefficient‐based degradation parameter extracted from the residual vibration signal. Based on the change in distributional properties such as mean and variance of the degradation parameter with time progression, three degradation stages of the gear are identified. A flexible miniature inspection camera is used to access and assess the actual physical damage on the gear tooth surface. Based on the visual inspection pictures, actual damage area at the identified degradation stages is quantified. Performance of the binary segmentation methodology is validated through six run‐to‐failure accelerated gear pitting experiments. [ABSTRACT FROM AUTHOR]