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

2019 ◽  
Vol 9 (10) ◽  
pp. 2009 ◽  
Author(s):  
Jiaming Han ◽  
Zhong Yang ◽  
Qiuyan Zhang ◽  
Cong Chen ◽  
Hongchen Li ◽  
...  
Keyword(s):  
Fault Detection ◽  
High Voltage ◽  
Transmission Lines ◽  
Ground Truth ◽  
Aerial Images ◽  
Aerial Image ◽  
Detection Methods ◽  
Convolutional Network ◽  
High Voltage Transmission ◽  
The Impact

Insulator faults detection is an important task for high-voltage transmission line inspection. However, current methods often suffer from the lack of accuracy and robustness. Moreover, these methods can only detect one fault in the insulator string, but cannot detect a multi-fault. In this paper, a novel method is proposed for insulator one fault and multi-fault detection in UAV-based aerial images, the backgrounds of which usually contain much complex interference. The shapes of the insulators also vary obviously due to the changes in filming angle and distance. To reduce the impact of complex interference on insulator faults detection, we make full use of the deep neural network to distinguish between insulators and background interference. First of all, plenty of insulator aerial images with manually labelled ground-truth are collected to construct a standard insulator detection dataset ‘InST_detection’. Secondly, a new convolutional network is proposed to obtain accurate insulator string positions in the aerial image. Finally, a novel fault detection method is proposed that can detect both insulator one fault and multi-fault in aerial images. Experimental results on a large number of aerial images show that our proposed method is more effective and efficient than the state-of-the-art insulator fault detection methods.

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

2021 ◽  
Vol 11 (10) ◽  
pp. 4647
Author(s):  
Chuanyang Liu ◽  
Yiquan Wu ◽  
Jingjing Liu ◽  
Zuo Sun ◽  
Huajie Xu
Keyword(s):  
Fault Detection ◽  
High Voltage ◽  
Transmission Lines ◽  
Aerial Images ◽  
Multiple Faults ◽  
Complex Background ◽  
Feature Pyramid ◽  
High Voltage Transmission ◽  
S Model ◽  
Deep Learning Model

Insulator fault detection is one of the essential tasks for high-voltage transmission lines’ intelligent inspection. In this study, a modified model based on You Only Look Once (YOLO) is proposed for detecting insulator faults in aerial images with a complex background. Firstly, aerial images with one fault or multiple faults are collected in diverse scenes, and then a novel dataset is established. Secondly, to increase feature reuse and propagation in the low-resolution feature layers, a Cross Stage Partial Dense YOLO (CSPD-YOLO) model is proposed based on YOLO-v3 and the Cross Stage Partial Network. The feature pyramid network and improved loss function are adopted to the CSPD-YOLO model, improving the accuracy of insulator fault detection. Finally, the proposed CSPD-YOLO model and compared models are trained and tested on the established dataset. The average precision of CSPD-YOLO model is 4.9% and 1.8% higher than that of YOLO-v3 and YOLO-v4, and the running time of CSPD-YOLO (0.011 s) model is slightly longer than that of YOLO-v3 (0.01 s) and YOLO-v4 (0.01 s). Compared with the excellent object detection models YOLO-v3 and YOLO-v4, the experimental results and analysis demonstrate that the proposed CSPD-YOLO model performs better in insulator fault detection from high-voltage transmission lines with a complex background.

scholarly journals OZONE CONCENTRATION VARIATIONS NEAR HIGH‐VOLTAGE TRANSMISSION LINES/OZONO KONCENTRACIJOS KITIMAS TIES AUKŠTOSIOS ĮTAMPOS TIEKIMO LINIJOMIS/ИЗМЕНЕНИЯ КОНЦЕНТРАЦИИ ОЗОНА ВБЛИЗИ ВЫСОКОВОЛЬТНЫХ ЛИНИЙ ЭЛЕКТРОПЕРЕДАЧ

2009 ◽  
Vol 17 (1) ◽  
pp. 28-35 ◽  
Author(s):  
Vaida Valuntaitė ◽  
Vaida Šerevičienė ◽  
Raselė Girgždienė
Keyword(s):  
High Voltage ◽  
Ozone Concentration ◽  
Transmission Lines ◽  
Passive Sampler ◽  
Passive Samplers ◽  
Real Concentration ◽  
Concentration Changes ◽  
High Voltage Transmission ◽  
The Difference ◽  
The Impact

Changes and distribution of ozone concentration in the area of high‐voltage transmission lines were investigated. The investigation on ozone concentration changes was performed with application of two methods: by using an ozone analyser and by passive samplers. The role of an accumulating element was performed by a glass‐fiber filter installed in a passive sampler. It was impregnated with a 1.2‐di(4‐pyridyl)ethylene and acetate acid solution. The impact of meteorological parameters on the passive sampler efficiency and ozone concentration variation is discussed. These parameters can increase or decrease the real concentration value in comparison with the concentration obtained by co‐located continuously running ozone analyser. Ozone concentration near high‐voltage lines varied from 10 to 51 ppb, and “background” ozone concentration changed from 3 to 50 ppb during the investigation period. The average concentrations were 28.1 and 27.5 ppb near the lines and “background” during the whole experiment period. The wind direction from “background” location to the high‐voltage lines prevailed during the experiment. The obtained results by different methods demonstrated good agreement; the difference between ozone concentrations was from 1 to 24% for individual cases. Santrauka Tirta ozono koncentracijos kitimas ir pasiskirstymas ties aukštosios įtampos perdavimo linijomis. Ozono koncentracija matuota dviem metodais – ozono analizatoriumi ir pasyviaisiais kaupikliais. Pasyviajame kaupiklyje kaip kaupiantysis elementas buvo naudojamas stiklo pluošto filtras, impregnuotas 1,2-di(4-pyridyl)etileno ir acetatinės rūgšties tirpalu. Vėjo greitis, vėjo kryptis, UV spinduliuotė, temperatūra ir santykinė oro drėgmė gali turėti įtakos pasyviųjų kaupiklių efektyvumui bei ozono koncentracijos pasiskirstymui, todėl kartu tirti ir meteorologiniai parametrai (temperatūra, santykinė oro drėgmė, vėjo greitis ir kryptis). Tyrimo laikotarpiu ozono koncentracija ties aukštosios įtampos tiekimo linijomis kito nuo 10 iki 51 ppb, o nutolusioje per 222 m vietovėje, kuri buvo traktuojama kaip foninė, – nuo 3 iki 50 ppb. Išmatuota vidutinė ozono koncentracija foninėje vietoje buvo 27,5 ppb, o ties linijomis – 28,1 ppb. Eksperimento metu vyravo pietryčių krypties vėjas, t. y. nuo foninės vietos – aukštosios įtampos tiekimo linijų link. Nustatant ozono koncentraciją skirtingais metodais duomenys pakankamai sutapo, pavieniais atvejais nesutapimas svyravo nuo 1 iki 24 %. Резюме Исследовалось изменение и распределение концентрации озона в районе высоковольтных линий электропередач. Концентрация озона измерялась двумя методами: анализаторами озона УФ-поглощения непрерывного действия и с использованием пассивных сорбентов. В качестве сорбента использовался фильтр из стекловолокна, пропитанный 1,2-ди(4-пиридил)этиленом и уксусной кислотой. Параллельно непрерывно измерялась температура и относительная влажность воздуха, скорость и направление ветра. Исследования показали, что концентрация озона в течение эксперимента изменялась в интервале от 10 до 51 ррb у линии и от 3 до 50 ррb на «фоновой» точке, удаленной от линий электропередач на расстояние 222 м. В течение эксперимента почти половину времени преобладал боковой ветер по отношению к высоковольтным линиям со стороны фоновой точки. Средние измеренные концентрации озона составляли 27,5 ррb на «фоновой» точке и 28,1 ррb – у линий. Результаты измерения концентрации озона как анализаторами непрерывного действия, так и по методике с использованием пассивных сорбентов показали хорошее совпадение: разница составляла 2–15% и лишь в отдельных случаях 24%.

scholarly journals EU-Net: An Efficient Fully Convolutional Network for Building Extraction from Optical Remote Sensing Images

2019 ◽  
Vol 11 (23) ◽  
pp. 2813 ◽  
Author(s):  
Wenchao Kang ◽  
Yuming Xiang ◽  
Feng Wang ◽  
Hongjian You
Keyword(s):  
Remote Sensing ◽  
High Resolution ◽  
Ground Truth ◽  
Aerial Image ◽  
Optical Remote Sensing ◽  
Building Extraction ◽  
Remote Sensing Images ◽  
Convolutional Network ◽  
Practical Applications ◽  
The Impact

Automatic building extraction from high-resolution remote sensing images has many practical applications, such as urban planning and supervision. However, fine details and various scales of building structures in high-resolution images bring new challenges to building extraction. An increasing number of neural network-based models have been proposed to handle these issues, while they are not efficient enough, and still suffer from the error ground truth labels. To this end, we propose an efficient end-to-end model, EU-Net, in this paper. We first design the dense spatial pyramid pooling (DSPP) to extract dense and multi-scale features simultaneously, which facilitate the extraction of buildings at all scales. Then, the focal loss is used in reverse to suppress the impact of the error labels in ground truth, making the training stage more stable. To assess the universality of the proposed model, we tested it on three public aerial remote sensing datasets: WHU aerial imagery dataset, Massachusetts buildings dataset, and Inria aerial image labeling dataset. Experimental results show that the proposed EU-Net is superior to the state-of-the-art models of all three datasets and increases the prediction efficiency by two to four times.

Sign in / Sign up

Export Citation Format

Share Document