Thermal Fault Diagnosis of Electrical Equipment in Substations Using Lightweight Convolutional Neural Network

Real-time equipment condition monitoring is crucial to ensure the regular operation of the electric system. However, the deployed heavy convolutional neural networks (CNNs) are defective for edge computation and offline diagnosis. The purpose of this article is to present a system for detecting over...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on instrumentation and measurement 2023, Vol.72, p.1-9
Main Authors: Zhou, Shuaijie, Liu, Jiefeng, Fan, Xianhao, Fu, Qi, Goh, Hui Hwang
Format: Article
Language:English
Subjects:
Artificial neural networks
Coders
Condition monitoring
Convolution
Convolutional neural network (CNN)
Convolutional neural networks
Datasets
Decoding
Edge computing
Electric equipment
electrical equipment monitoring
Electronic devices
Fault detection
Fault diagnosis
Fault location
Image segmentation
infrared images
Infrared imaging
Interpolation
Kernel
Lightweight
Overheating
Reliability analysis
Substations
U-Net-based segmentation network
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Real-time equipment condition monitoring is crucial to ensure the regular operation of the electric system. However, the deployed heavy convolutional neural networks (CNNs) are defective for edge computation and offline diagnosis. The purpose of this article is to present a system for detecting overheating faults of substation equipment using infrared photos and U-Net deep learning techniques. First, a stepwise encoder employs a lightweight CNN (LCNN) based on inverted residuals with depthwise separable convolution. The fault location is then decoded in the decoder using stepwise upsampling and nearest-neighbor interpolation. We additionally incorporate low-level detail feature information from the encoder to include additional fault data. Finally, testing findings on our dataset demonstrated the proposed method's superior reliability and efficiency under a variety of evaluation metrics. Ultimately, we reached a lighter structure and leading estimation with a small training dataset, so our method is well-suited for deployment on mobile devices.
ISSN:0018-9456
1557-9662
DOI:10.1109/TIM.2023.3240210