Detecting surface discharge faults in switchgear by using hybrid model

Abstract

<span>Switchgear plays a crucial role in power systems, providing protection and control over electrical equipment. However, tracking (surface discharge) can lead to insulation degradation and switchgear failure, necessitating reliable and effective identification of tracking defects. In this paper, we propose a hybrid one-dimension convolutional neural network long short-term memory networks (1D-CNN-LSTM) model as a solution to this problem. Data from both time domain analysis (TDA) and frequency domain analysis (FDA) are utilized for model evaluation. The model achieved error-free accuracy of 100% in both TDA and FDA during the training, validation, and testing phases. The model's performance is further assessed using performance measures and the visualization of accuracy and loss curves. The results show that the hybrid 1D-CNN-LSTM model works well to accurately find and classify surface discharge tracking defects in switchgear. The model offers precise and dependable fault identification, which has the potential to significantly enhance switchgear functionality. By enabling proactive maintenance and timely intervention, the proposed model contributes to the overall reliability and performance of switchgear in power systems. The findings of this research provide valuable insights for the design and implementation of advanced fault detection systems in switchgear applications.</span>

Chicken tracking for location mapping of lameness chickens using YOLOv8 and deep learning-based tracking algorithm

“…This allows for early detection of any disease-related symptoms in the chicken [21]. The object detection process based on deep learning has many benefits that can be used for many things, such as traffic light detection using faster-CNN [22], detection of switchgear removal errors using CNN-long short-term memory (LSTM) [23], you only look once, version 5 (YOLOv5) for image and video-based criminal detection [24], you only look once, version 3 (YOLOv3)-based distance detection in public spaces during COVID-19 [25], classifying yoga poses using CNN [26], analyzing human activity using CNN [27], designing a robot design for assisting the elderly using CNN [28], estimating the age of pedestrians using CNN [29], carrying out automatic surveillance at night using CNN [30], identifying human emotions for assistant robots using CNN [31], deep learning can also be used for sound event detection using CNN [32].…”