The discrimination method as applied to a deteriorated porcelain insulator used in transmission lines on the basis of a convolution neural network

Liu, Yunpeng; Pei, Shaotong; Fu, Wei; Zhang, Kaiyuan; Ji, Xinxin; Yin, Zihui

doi:10.1109/tdei.2017.006840

Cited by 60 publications

(24 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The application of ANN [14] can even be used to automate the localisation of faults in transmission lines (TLs). Techniques based on the convolution neural network (CNN) are used for acoustic detection of failures in TL insulators [15]. The presented results show that the application of advanced techniques significantly improves the accuracy of the algorithm.…”

Section: Introductionmentioning

confidence: 99%

Analysis of training techniques of ANN for classification of insulators in electrical power systems

Stefenon

Branco

Nied

et al. 2020

IET Generation, Transmission & Distribution

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

Analysis of training techniques of ANN for classification of insulators in electrical power systems

Stefenon

Branco

Nied

et al. 2020

IET Generation, Transmission & Distribution

View full text Add to dashboard Cite

“…Insulators are widely used in many power applications such as transmission, distribution networks and substations, due to its excellent performance of electrical insulation and mechanical fixation [1]- [4]. Today, there are billions of insulators in service in China, among which porcelain insulators account for a considerable proportion.…”

Section: Introductionmentioning

confidence: 99%

Edge Detection of High-Voltage Porcelain Insulators in Infrared Image Using Dual Parity Morphological Gradients

Yin

Zhengxiong

et al. 2019

IEEE Access

View full text Add to dashboard Cite

A new edge detection operator based on dual parity morphological gradients is proposed, in order to accurately segment a porcelain insulator string in an infrared image before the identification and diagnosis of deteriorated insulators by the extracted thermal information. When applied to the doubleshed insulators, the proposed detector is capable of effectively eliminating the blurred region between the upper and lower sheds as well as preventing over-segmentation by combining both odd and even structural elements. Compared with the multiscale morphological gradient algorithm, this technique reduces the size of the maximum structural elements to optimize the computational complexity. A quantitative evaluation using PSNR, IoU, and FPR indexes shows that the new technique outperforms other common edge detectors. In addition, the experiments on thousands of real infrared images demonstrate the detector to be highly effective despite its low complexity. INDEX TERMS High-voltage porcelain insulators, infrared images, edge detection, dual parity morphological gradients, blurred region.

show abstract

“…When there are defects in the metal surface, it is necessary to replace the insulator layer and metal pipeline at the same time. Discriminating the defects in the insulator layer and metal surface is thus beneficial to take appropriate remedial measures to reduce maintenance cost and improve production efficiency [9]. It is a challenging work for conventional NDE technique and capacitive imaging (CI) technique has been proven to be a feasible technique in previous work [10][11][12][13].…”

Section: Introductionmentioning

confidence: 99%

Further Investigations into the Capacitive Imaging Technique Using a Multi-Electrode Sensor

Chen

et al. 2018

Applied Sciences

View full text Add to dashboard Cite

As a novel non-destructive testing technique, capacitive imaging (CI) has been used to detect defects within the insulation layer and metal surface of an insulated metallic structure, that is, pipe or vessel. Due to the non-linearity of the probing field, the defects at different depths in the insulation layer are difficult to compare accurately using the conventional CI sensor with a single pair of electrodes. In addition, the conventional CI sensor cannot provide adequate information to discriminate the defects in the insulation layer and metal surface. In order to solve the above-mentioned problems, the multi-electrode sensor is introduced. The multi-electrode sensor uses multiple quasi-static fringing electric fields generated by an array of coplanar electrodes to obtain extra information about the defects in the specimen. In this work, the feasibility of multiple quasi-static electric fields detecting the defects was demonstrated and the Measurement Sensitivity Distributions (MSDs) of the multi-electrode sensor detecting the defects were acquired using the FEM models. The simulation and experimental results show that the Dynamic Change Rates (DCRs) of the measured values obtained at the center of the defects in the insulator layer and metal surface present different variation patterns, which can be used to discriminate these two different kinds of defects. The reasons for the different variation patterns of DCRs were explained by the changing trends of MSDs with increased electrode separation. In addition, it was demonstrated that the different depths of the defects in the insulator layer can be compared accurately by comprehensive analysis of the detection results from all the electrode pairs.

show abstract

The discrimination method as applied to a deteriorated porcelain insulator used in transmission lines on the basis of a convolution neural network

Cited by 60 publications

References 10 publications

Analysis of training techniques of ANN for classification of insulators in electrical power systems

Analysis of training techniques of ANN for classification of insulators in electrical power systems

Edge Detection of High-Voltage Porcelain Insulators in Infrared Image Using Dual Parity Morphological Gradients

Further Investigations into the Capacitive Imaging Technique Using a Multi-Electrode Sensor

Contact Info

Product

Resources

About