☆ 4.4 Review

Insulator defect detection with deep learning: A survey

IET GENERATION TRANSMISSION & DISTRIBUTION (2023)

Related references

Note: Only part of the references are listed.

Article Engineering, Electrical & Electronic

Hybrid-YOLO for classification of insulators defects in transmission lines based on UAV

Bruno Jose Souza et al.

Summary: This paper proposes a method of using UAV-captured photos of failed components to perform power system inspection. By using a hybrid model based on You Only Look Once (YOLO) and ResNet-18 classifier, faults can be identified faster and more reliably. Experimental results demonstrate that the proposed method outperforms other benchmark models in both object detection and multiclassification tasks.

INTERNATIONAL JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS (2023)

Add to Collection

Article Engineering, Multidisciplinary

Effective IoT-based deep learning platform for online fault diagnosis of power transformers against cyberattacks and data uncertainties

Mahmoud Elsisi et al.

Summary: This paper introduces a method that integrates Internet of Things (IoT) architecture with deep learning for online monitoring of power transformer status and protection against cyberattacks. Experimental results confirm the effectiveness of the proposed method.

MEASUREMENT (2022)

Add to Collection

Article Chemistry, Analytical

Semi-ProtoPNet Deep Neural Network for the Classification of Defective Power Grid Distribution Structures

Stefano Frizzo Stefenon et al.

Summary: This paper proposes the Semi-ProtoPNet deep learning model for classifying defective structures in power distribution networks. The model achieves high accuracy through low quantity image analysis and negative reasoning process, outperforming other similar models.

SENSORS (2022)

Add to Collection

Article Energy & Fuels

Uncertainty-aware accurate insulator fault detection based on an improved YOLOX model

Zhiyong Dai

Summary: The paper proposes a novel deep learning-based methodology called YOLOD to address the uncertainty issue in insulator detection. By applying a Gaussian prior to the detection heads of YOLOX, the proposed method achieves higher accuracy and robustness compared to benchmark models.

ENERGY REPORTS (2022)

Add to Collection

Article Engineering, Electrical & Electronic

FINet: An Insulator Dataset and Detection Benchmark Based on Synthetic Fog and Improved YOLOv5

Zheng-De Zhang et al.

Summary: In this research, a dataset and benchmark model for insulator defect detection are introduced, and the detection performance is improved through the optimization of a synthetic fog algorithm.

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT (2022)

Add to Collection

Article Energy & Fuels

Online Monitoring Method for Insulator Self-explosion Based on Edge Computing and Deep Learning

Baoquan Wei et al.

Summary: This paper proposes a fault detection scheme for insulator self-explosion based on edge computing and deep learning to solve the problems of traditional centralized cloud computing. By designing a lightweight target recognition network and utilizing a multimodal fusion algorithm, the self-explosion fault detection of overhead transmission lines is achieved, with the advantages of low latency and high diagnostic accuracy.

CSEE JOURNAL OF POWER AND ENERGY SYSTEMS (2022)

Add to Collection

Article Engineering, Electrical & Electronic

An Outdoor Support Insulator Surface Defects Segmentation Approach via Image Adversarial Reconstruction in High-Speed Railway Traction Substation

Xuemin Lu et al.

Summary: This article proposes a universal framework for segmenting surface defects of outdoor support insulators, achieving pixel-level segmentation. The framework accurately locates insulators using a robust network, reconstructs nondefect insulators using a reconstruction network, and segments defective areas based on a decision strategy.

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT (2022)

Add to Collection

Article Engineering, Electrical & Electronic

Bidirection-Fusion-YOLOv3: An Improved Method for Insulator Defect Detection Using UAV Image

Zhanshe Yang et al.

Summary: This study proposes a new type of insulator detection model based on the YOLOv3 network, which improves efficiency while ensuring detection speed, and applies the latest EIoU and loss functions to achieve significant progress.

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT (2022)

Add to Collection

Article Computer Science, Information Systems

Pollution Severity Monitoring of High Voltage Transmission Line Insulators Using Wireless Device Based on Leakage Current Bursts

Osamae Gouda et al.

Summary: The article introduces a smart wireless online device for monitoring the severity of contaminated insulators in high voltage transmission networks. The device continuously senses the magnitudes of leakage current bursts and calculates the average root-mean-square value to determine the likelihood of a power outage. It sends an alarm signal and warning message if necessary. The device is low-cost, easy to handle and calibrate, has a high degree of safety, and is designed to be simple.

IEEE ACCESS (2022)

Add to Collection

Article Computer Science, Information Systems

Reliable Deep Learning and IoT-Based Monitoring System for Secure Computer Numerical Control Machines Against Cyber-Attacks With Experimental Verification

Minh-Quang Tran et al.

Summary: This paper presents a new intelligent integration between an IoT platform and deep learning neural network (DNN) algorithm for monitoring the cutting process of CNC machines. By installing a force sensor and designing an IoT architecture and improved DNN model, the system accurately captures and classifies cutting conditions and helps to enhance product quality.

IEEE ACCESS (2022)

Add to Collection

Article Engineering, Electrical & Electronic

Box-Point Detector: A Diagnosis Method for Insulator Faults in Power Lines Using Aerial Images and Convolutional Neural Networks

Xinyu Liu et al.

Summary: The proposed Box-Point Detector is a novel method for intelligent diagnosis of insulators based on deep learning, which efficiently locates fault regions and estimates insulator endpoints. It provides a new representation for insulator faults, enhancing the diagnosis capability by offering detailed and correlated information, with high accuracy in diagnosing high-voltage insulator faults under various conditions. Compared to previous methods like Faster R-CNN and SSD, the Box-Point Detector shows competitive capabilities in accuracy and robustness.

IEEE TRANSACTIONS ON POWER DELIVERY (2021)

Add to Collection

Article Energy & Fuels

MTI-YOLO: A Light-Weight and Real-Time Deep Neural Network for Insulator Detection in Complex Aerial Images

Chuanyang Liu et al.

Summary: The study proposes the MTI-YOLO network for insulator detection in complex aerial images, achieving improved accuracy through techniques such as multi-scale feature detection and spatial pyramid pooling. Experimental results show that the proposed network outperforms traditional methods in both complex backgrounds and bright illumination conditions.

ENERGIES (2021)

Add to Collection

Article Chemistry, Analytical

Deep Learning-Based Industry 4.0 and Internet of Things towards Effective Energy Management for Smart Buildings

Mahmoud Elsisi et al.

Summary: The IoT technology enables intelligent decision-making and signal control between different machines, using deep learning methods to reduce energy consumption of air conditioners. The people detection system and YOLOv3 algorithm help optimize the management of air conditioning operations in smart buildings.

SENSORS (2021)

Add to Collection

Article Chemistry, Analytical

Deep Learning Approaches on Defect Detection in High Resolution Aerial Images of Insulators

Qiaodi Wen et al.

Summary: Two deep learning methods based on Faster R-CNN, Exact R-CNN and CME-CNN, are proposed in this study. Exact R-CNN improves target detection accuracy by incorporating advanced techniques, while CME-CNN enhances performance by generating insulator mask images for defect detection using Exact R-CNN.

SENSORS (2021)

Add to Collection

Article Chemistry, Multidisciplinary

Insulator Faults Detection in Aerial Images from High-Voltage Transmission Lines Based on Deep Learning Model

Chuanyang Liu et al.

Summary: Insulator fault detection is crucial for high-voltage transmission lines, and a modified YOLO model, CSPD-YOLO, outperformed YOLO-v3 and YOLO-v4 in accuracy. By enhancing feature reuse and propagation, the CSPD-YOLO model demonstrated improved performance in detecting insulator faults in aerial images with complex backgrounds.

APPLIED SCIENCES-BASEL (2021)

Add to Collection

Article Computer Science, Information Systems

Improved YOLOv3 Network for Insulator Detection in Aerial Images with Diverse Background Interference

Chuanyang Liu et al.

Summary: In this study, a deep learning method based on YOLOv3-dense network was proposed for detecting insulators of different sizes from aerial images with complex backgrounds. Experimental results showed that the proposed method achieved high accuracy and performance in insulator detection.

ELECTRONICS (2021)

Add to Collection

Article Computer Science, Information Systems

Towards Secured Online Monitoring for Digitalized GIS Against Cyber-Attacks Based on IoT and Machine Learning

Mahmoud Elsisi et al.

Summary: This paper introduces a novel IoT architecture based on machine learning techniques for online monitoring the status of gas-insulated switchgear (GIS) in power stations. The proposed architecture effectively detects defects and cyber-attacks in GIS through different test scenarios and features extraction of partial discharge pulse sequences.

IEEE ACCESS (2021)

Add to Collection

Article Engineering, Electrical & Electronic

An Insulator in Transmission Lines Recognition and Fault Detection Model Based on Improved Faster RCNN

Wenqing Zhao et al.

Summary: This article proposes an insulator recognition and fault detection model using techniques such as faster region convolutional neural network and feature pyramid networks to address the problem of insulator recognition in complex backgrounds. Experimental results show that the model achieves high accuracy and mean average precision in accurately recognizing and detecting faults in glass and composite insulators.

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT (2021)

Add to Collection

Article Computer Science, Information Systems

Experimental Setup for Online Fault Diagnosis of Induction Machines via Promising IoT and Machine Learning: Towards Industry 4.0 Empowerment

Minh-Quang Tran et al.

Summary: The utilization of IoT and CPS has been expanding in industrial settings, but cybersecurity remains a major challenge. This paper proposes a new IoT architecture utilizing machine learning techniques for reliable and secure online monitoring of induction motor status, visually recognizing faults and cyber-attacks. Advanced machine learning techniques are deployed to accurately detect and visualize cyber-attacks and motor status, showcasing its effectiveness in enhancing decision-making processes regarding motor status under industrial conditions.

IEEE ACCESS (2021)

Add to Collection

Article Engineering, Electrical & Electronic

Cap-Count Guided Weakly Supervised Insulator Cap Missing Detection in Aerial Images

Chunxue Shi et al.

Summary: This article proposes a vision-based method for detecting cap missing on insulators in aerial images, using cap-count guided weakly supervised learning and automatically generating cap annotations based on insulator bounding box annotations. The method simultaneously detects insulator strings and caps using a deep learning model, and finally designs an efficient cap missing detection strategy based on geometric constraints. The proposed approach achieves competitive detection results with high precision and recall rates.

IEEE SENSORS JOURNAL (2021)

Add to Collection

Article Energy & Fuels

Search Like an Eagle: A Cascaded Model for Insulator Missing Faults Detection in Aerial Images

Jiaming Han et al.

ENERGIES (2020)

Add to Collection

Article Automation & Control Systems

Detection of Power Line Insulator Defects Using Aerial Images Analyzed With Convolutional Neural Networks

Xian Tao et al.

IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS (2020)

Add to Collection

Article Engineering, Electrical & Electronic

IN-YOLO: Real-Time Detection of Outdoor High Voltage Insulators Using UAV Imaging

Diana Sadykova et al.

IEEE TRANSACTIONS ON POWER DELIVERY (2020)

Add to Collection

Article Engineering, Electrical & Electronic

Detection Method Based on Automatic Visual Shape Clustering for Pin-Missing Defect in Transmission Lines

Zhenbing Zhao et al.

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT (2020)

Add to Collection

Proceedings Paper Automation & Control Systems

A Multi-feature Fusion-based Deep Learning for Insulator Image Identification and Fault Detection

Xinlei Huang et al.

PROCEEDINGS OF 2020 IEEE 4TH INFORMATION TECHNOLOGY, NETWORKING, ELECTRONIC AND AUTOMATION CONTROL CONFERENCE (ITNEC 2020) (2020)

Add to Collection

Article Energy & Fuels

High precision detection algorithm based on improved RetinaNet for defect recognition of transmission lines

Jun Liu et al.

ENERGY REPORTS (2020)

Add to Collection

Article Computer Science, Information Systems

Insulator Defect Recognition Based on Global Detection and Local Segmentation

Xuefeng Li et al.

IEEE ACCESS (2020)

Add to Collection

Article Computer Science, Information Systems

Detection of Insulator Defects With Improved ResNeSt and Region Proposal Network

Shuqing Wang et al.

IEEE ACCESS (2020)

Add to Collection

Article Computer Science, Information Systems

An Automatic Detection Method of Bird's Nest on Transmission Line Tower Based on Faster_RCNN

Fan Li et al.

IEEE ACCESS (2020)

Add to Collection

Article Chemistry, Multidisciplinary

A Method of Insulator Faults Detection in Aerial Images for High-Voltage Transmission Lines Inspection

Jiaming Han et al.

APPLIED SCIENCES-BASEL (2019)

Add to Collection

Proceedings Paper Computer Science, Hardware & Architecture

Insulator Faults Detection Based on Deep Learning

Mohamed Witti Adou et al.

PROCEEDINGS OF 2019 IEEE 13TH INTERNATIONAL CONFERENCE ON ANTI-COUNTERFEITING, SECURITY, AND IDENTIFICATION (IEEE-ASID'2019) (2019)

Add to Collection

Article Computer Science, Information Systems

Semantic Segmentation of Transmission Lines and Their Accessories Based on UAV-Taken Images

Longjun Wang et al.

IEEE ACCESS (2019)

Add to Collection

Article Computer Science, Information Systems

A Recognition Technology of Transmission Lines Conductor Break and Surface Damage Based on Aerial Image

Ye Zhang et al.

IEEE ACCESS (2019)

Add to Collection

Article Computer Science, Information Systems

Deep Learning-Based System for Automatic Recognition and Diagnosis of Electrical Insulator Strings

Carlos Sampedro et al.

IEEE ACCESS (2019)

Add to Collection

Article Computer Science, Information Systems

Insulator Detection in Aerial Images for Transmission Line Inspection Using Single Shot Multibox Detector

Xiren Miao et al.

IEEE ACCESS (2019)

Add to Collection

Article Computer Science, Information Systems

Insulator Fault Detection in Aerial Images Based on Ensemble Learning With Multi-Level Perception

Hao Jiang et al.

IEEE ACCESS (2019)

Add to Collection

Article Computer Science, Information Systems

Insulator Fault Detection Based on Spatial Morphological Features of Aerial Images

Yongjie Zhai et al.

IEEE ACCESS (2018)

Add to Collection

Article Computer Science, Information Systems

Fault detection of insulator based on saliency and adaptive morphology

Yongjie Zhai et al.

MULTIMEDIA TOOLS AND APPLICATIONS (2017)

Add to Collection

Article Engineering, Electrical & Electronic

A Texture Segmentation Algorithm Based on PCA and Global Minimization Active Contour Model for Aerial Insulator Images

Qinggang Wu et al.

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING (2012)

Add to Collection

© Peeref 2019-2024. All rights reserved.