Industrial electrical automation fault detection is a guarantee for the stable operation of industrial systems. Focusing on issues of low detection accuracy and insufficient depth perception ability in the current research, this paper establishes a multimetric stereo vision measurement model of electrical equipment, and stereo-corrects the images of electrical equipment. Then a two-channel convolutional neural network (CNN) is designed to capture global and local characteristics of the electrical equipment image. Finally, the YOLOv8 approach was adopted as the baseline model to optimize the design of the feature fusion part of the network. The recognition head network was superseded by Dyhead dynamic recognition head. The loss function part is redesigned using Focaler-IoU to solve the fitting problem caused by sample imbalance. Experimental outcome indicates that the proposed technique boosts the mean Average Precision (mAP) by no less than 5.42%, which significantly improves the detection efficiency and reliability.
BabayigitBAbubakerM. Industrial internet of things: a review of improvements over traditional scada systems for industrial automation. IEEE Syst J2023; 18: 120–133.
2.
MuttaqiKMAghaeiJGanapathyV, et al.Technical challenges for electric power industries with implementation of distribution system automation in smart grids. Renew Sustain Energy Rev2015; 46: 129–142.
3.
ChengY. Thermal fault detection and severity analysis of mechanical and electrical automation equipment. International Journal of Heat & Technology2022; 40: 15–22.
4.
MaRKareemSWKalraA, et al.Optimization of electric automation control model based on artificial intelligence algorithm. Wireless Commun Mobile Comput2022; 20: 62–77.
5.
HanJ-HYangSLeeB-U. A novel 3-D color histogram equalization method with uniform 1-D gray scale histogram. IEEE Trans Image Process2010; 20: 506–512.
6.
WangLWangBZhangJ, et al.An intelligent detection method for approach distances of large construction equipment in substations. Electronics2023; 12: 35–43.
7.
DangDLiuYLeeS-K. State evaluation of electrical equipment in substations based on data mining. Appl Sci2024; 14: 48–56.
8.
LuoLMaRLiY, et al.Image recognition technology with its application in defect detection and diagnosis analysis of substation equipment. Sci Program2021; 2: 21–30.
9.
RenYZhengDYangY, et al.A cross-condition fault disentangling matching network for industrial early fault enhancement. IEEE Trans Ind Electron2024; 72: 7585–7594.
10.
ZhangJZhuW. Research on algorithm for improving infrared image defect segmentation of power equipment. Electronics2023; 12: 15–28.
11.
ZuoWZhangLSongC, et al.Gradient histogram estimation and preservation for texture enhanced image denoising. IEEE Trans Image Process2014; 23: 2459–2472.
12.
Ke-ChenSYun-HuiYWen-HuiC. Research and perspective on local binary pattern. Acta Autom Sin2013; 39: 730–744.
13.
Van NoordNPostmaE. Learning scale-variant and scale-invariant features for deep image classification. Pattern Recogn2017; 61: 583–592.
14.
JeongS-HParkJ-WKimH-S. Deep neural network-based lifetime diagnosis algorithm with electrical capacitor accelerated life test. J Power Sources2024; 599: 23–41.
15.
NaeemSAliAAnamS, et al.An unsupervised machine learning algorithms: comprehensive review. International Journal of Computing and Digital Systems2023; 4: 71–78.
16.
ManikondaSKGaonkarDN. Islanding detection method based on image classification technique using histogram of oriented gradient features. IET Gener Transm Distrib2020; 14: 2790–2799.
17.
UllahIKhanRUYangF, et al.Deep learning image-based defect detection in high voltage electrical equipment. Energies2020; 13: 39–40.
18.
TangZJianX. Thermal fault diagnosis of complex electrical equipment based on infrared image recognition. Sci Rep2024; 14: 47–55.
19.
ZhangQChangXMengZ, et al.Equipment detection and recognition in electric power room based on faster R-CNN. Procedia Comput Sci2021; 183: 324–330.
20.
ThomasJBChaudhariSGShihabudheenK, et al.CNN-based transformer model for fault detection in power system networks. IEEE Trans Instrum Meas2023; 72: 1–10.
21.
YoonD-HYoonJ. Development of a real-time fault detection method for electric power system via transformer-based deep learning model. Int J Electr Power Energy Syst2024; 159: 12–25.
22.
BellouEPisicaIBanitsasK. Aerial inspection of high-voltage power lines using YOLOv8 real-time object detector. Energies2024; 17: 25–35.
23.
TianXLiuRWangZ, et al.High quality 3D reconstruction based on fusion of polarization imaging and binocular stereo vision. Inf Fusion2022; 77: 19–28.
24.
TangZVon GioiRGMonasseP, et al.A precision analysis of camera distortion models. IEEE Trans Image Process2017; 26: 2694–2704.
25.
MaSLuHLiuJ, et al.Layn: lightweight multi-scale attention yolov8 network for small object detection. IEEE Access2024; 12: 29294–29307.
26.
WuTDongY. YOLO-SE: improved YOLOv8 for remote sensing object detection and recognition. Appl Sci2023; 13: 12–27.
27.
VakiliEKarimianGShoaranM, et al.Valid-IoU: an improved IoU-based loss function and its application to detection of defects on printed circuit boards. Multimed Tool Appl2024; 2: 21–24.
28.
WuZHeS. Improvement of the AlexNet networks for large-scale recognition applications. Iran J Sci Technol Trans Electr Eng2021; 45: 493–503.
29.
TamminaS. Transfer learning using vgg-16 with deep convolutional neural network for classifying images. International Journal of Scientific and Research Publications (IJSRP)2019; 9: 143–150.
30.
XuWFuY-LZhuD. ResNet and its application to medical image processing: research progress and challenges. Comput Methods Progr Biomed2023; 240: 10–16.
LiuMWangHDuL, et al.Bearing-detr: a lightweight deep learning model for bearing defect detection based on rt-detr. Sensors2024; 24: 1–14.
33.
ZhouLYangSWangC, et al.QCF-YOLO: a light weight model of surface defect detection for quick-connect fittings. IEEE Sens J2024; 25: 1716–1731.
34.
ShenLLangBSongZ. Infrared object detection method based on DBD-YOLOv8. IEEE Access2023; 11: 145853–145868.
35.
HuaWChenQChenW. A new lightweight network for efficient UAV object detection. Sci Rep2024; 14: 13–19.
36.
LiZHuCNaiK, et al.Siamese target estimation network with AIoU loss for real-time visual tracking. J Vis Commun Image Represent2021; 77: 10–21.
37.
VermaAKNagpalSDesaiA, et al.An efficient neural-network model for real-time fault detection in industrial machine. Neural Comput Appl2021; 33: 1297–1310.
