On-Site Identification of Zero Resistance Insulator Based on Infrared Thermal Image and Weights-Direct-Determination Neural Network

2013 ◽  
Vol 441 ◽  
pp. 417-420
Author(s):  
Tang Bing Li ◽  
Lei Gong ◽  
Jian Gang Yao ◽  
Yan Jun Kuang ◽  
Bin Bin Rao
Keyword(s):  
Neural Network ◽  
Transmission Lines ◽  
Direct Determination ◽  
Thermal Image ◽  
Absolute Deviation ◽  
Thermal Images ◽  
Zero Resistance ◽  
Infrared Thermal Images ◽  
Site Identification ◽  
The Relationship

A method using infrared thermal images and weights-direct-determination neural network (WDDNN) to identify the zero resistance insulators on-site is presented. The basic procedures were as follows: the infrared thermal image were denoised, intensified, segmented, and a rectangular which was regarded as object was intercepted in the insulators chain; in view of the relationship between gray value of infrared thermal images and temperature of object surface, four parameters which stand for standard deviation, absolute deviation, quartiles and range of gray value, were extracted directly; these four parameters were used as the input of WDDNN to train the model, which could be used identifing the zero resistance insulators after being trained. This method can effectively avoid the interference of transmission lines, and can meet the real-time require when identifying on-site. Experimental results verify the feasibility and effectiveness of this method.

First Order Statistical Features Thermal Images for Surge Arrester Fault Classification

2016 ◽  
Vol 818 ◽  
pp. 91-95
Author(s):  
Novizon ◽  
Zulkurnain Abdul-Malek
Keyword(s):  
Neural Network ◽  
Extraction Method ◽  
Thermal Image ◽  
Image Features ◽  
Fault Classification ◽  
Contact Method ◽  
Health States ◽  
Thermal Images ◽  
First Order ◽  
Condition Diagnosis

— Thermal imaging technique is a very convenient, versatile and non-contact method which has been used for fault condition diagnosis of electrical equipment. The fault condition diagnosis is composed with data acquisition, data pre-processing, data analysis and decision making. Some important features contain in thermal image can be extracted for equipment condition monitoring and fault diagnosis. This paper attempts to extract some important features from the zinc oxide (ZnO) surge arrester using first order statistical histogram extraction to classify the fault condition using neural network. The experimental work was carried out to capture thermal image of 120 kV rated ZnO surge arrester. The thermal images were segmented and plotted histogram using dedicated software. Some features such as the maximum, minimum, mean, standard deviation, and variance were extracted using the extraction method, classification of aging was carried out using the neural network based on the leakage current values. The health states consist of normal, defection and faulty. The results show that the thermal image features extracted using the extraction method can be used to classify the fault condition of the ZnO surge arresters

scholarly journals Online Identification of Shearer Cutting State Using Infrared Thermal Images of Cutting Unit

2018 ◽  
Vol 8 (10) ◽  
pp. 1772 ◽  
Author(s):  
Lei Si ◽  
Zhongbin Wang ◽  
Yiwen Liu ◽  
Chao Tan
Keyword(s):  
Thermal Image ◽  
Support Vector ◽  
Temporal Context ◽  
Accurate Identification ◽  
Thermal Images ◽  
Tracking Method ◽  
Online Identification ◽  
Spatio Temporal ◽  
Infrared Thermal Images ◽  
Cutting Unit

In order to achieve accurate identification of a shearer cutting state, infrared thermal images were creatively adopted in this paper. As the position of a shearer cutting unit is constantly changing, and the temperature in the vicinity is obviously distinct, mathematical morphology theory was used to detect the cutting unit in an infrared thermal image. Furthermore, a target tracking method is put forward to achieve cutting unit tracking based on the combination of morphology and a spatio-temporal context (STC) algorithm. Then, the temperature field features of this tracking area were extracted, and an intelligent classifier based on a support vector machine (SVM) was constructed to identify the cutting state of the shearer. Some experiments are presented, and the results indicate the feasibility and superiority of the proposed method.

Correlation between Third Harmonic Leakage Current and Thermography Image of Zinc Oxide Surge Arrester for Fault Monitoring Using Artificial Neural Network

2014 ◽  
Vol 554 ◽  
pp. 598-602 ◽  
Author(s):  
Yusuf Novizon ◽  
Abdul Malek Zulkurnain ◽  
Abdul Malek Zulkurnain
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Leakage Current ◽  
Thermal Image ◽  
Critical Parameters ◽  
Thermal Images ◽  
Third Harmonic ◽  
Surge Arresters ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

The ageing level of ZnO materials in gapless surge arresters can be determined by using either the traditional leakage current measurements or recently introduced thermal images of the arrester. However, a direct correlation between arrester thermal images and its leakage current (and hence the ageing level) is yet to be established. This paper attempts to find such a correlation using an artificial neural network (ANN). Experimental work was carried out to capture both the thermal images and leakage current of 120kV rated polymeric housed gapless arresters. Critical parameters were then extracted from both the thermal image and the leakage current, before being exported into the artificial neural network tool. Using the leakage current level, the conditions of the arrester are classified as normal, caution, and faulty. The ANN correctly classifies the ageing level using only the thermal image information with an accuracy of 97%, which is highly encouraging.

scholarly journals Double Thresholding with Sine Entropy for Thermal Image Segmentation

2021 ◽  
Vol 38 (6) ◽  
pp. 1713-1718
Author(s):  
Manikanta Prahlad Manda ◽  
Daijoon Hyun
Keyword(s):  
Image Segmentation ◽  
Shannon Entropy ◽  
Thermal Image ◽  
Image Databases ◽  
Misclassification Error ◽  
Average Sensitivity ◽  
Thermal Images ◽  
Range Correlation ◽  
Infrared Thermal Images ◽  
State Of Art

Traditional thresholding methods are often used for image segmentation of real images. However, due to distinct characteristics of infrared thermal images, it is difficult to ensure an optimal image segmentation using the traditional thresholding algorithms, and therefore, sometimes this can lead to over-segmentation, missing object information, and/or spurious responses in the output. To overcome these issues, we propose a new thresholding technique that makes use of the sine entropy-based criterion. Moreover, we build a double thresholding technique that makes use of two thresholds to get the final image thresholding result. Besides, we introduce the sine entropy concept as a supplement of the Shannon entropy in creating threshold-dependent criterion derived from the grayscale histogram. We found that the sine entropy is more robust in interpreting the strength of the long-range correlation in the gray levels compared to the Shannon entropy. We have experimented with our method on several infrared thermal images collected from standard image databases to describe the performance. On comparing with the state-of-art methods, the qualitative results from the experiments show that the proposed method achieves the best performance with an average sensitivity of 0.98 and an average misclassification error of 0.01, and second-best performance with an average sensitivity of 0.99 and an average specificity of 0.93.

scholarly journals Fully Automated DCNN-Based Thermal Images Annotation Using Neural Network Pretrained on RGB Data

Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1552
Author(s):  
Adam Ligocki ◽  
Ales Jelinek ◽  
Ludek Zalud ◽  
Esa Rahtu
Keyword(s):  
Neural Network ◽  
Large Scale ◽  
Thermal Image ◽  
Training Dataset ◽  
Small Scale ◽  
Thermal Images ◽  
Data Annotation ◽  
The Neural Network ◽  
Improved Performance ◽  
Image Datasets

One of the biggest challenges of training deep neural network is the need for massive data annotation. To train the neural network for object detection, millions of annotated training images are required. However, currently, there are no large-scale thermal image datasets that could be used to train the state of the art neural networks, while voluminous RGB image datasets are available. This paper presents a method that allows to create hundreds of thousands of annotated thermal images using the RGB pre-trained object detector. A dataset created in this way can be used to train object detectors with improved performance. The main gain of this work is the novel method for fully automatic thermal image labeling. The proposed system uses the RGB camera, thermal camera, 3D LiDAR, and the pre-trained neural network that detects objects in the RGB domain. Using this setup, it is possible to run the fully automated process that annotates the thermal images and creates the automatically annotated thermal training dataset. As the result, we created a dataset containing hundreds of thousands of annotated objects. This approach allows to train deep learning models with similar performance as the common human-annotation-based methods do. This paper also proposes several improvements to fine-tune the results with minimal human intervention. Finally, the evaluation of the proposed solution shows that the method gives significantly better results than training the neural network with standard small-scale hand-annotated thermal image datasets.

scholarly journals Automatic Detection of Linear Thermal Bridges from Infrared Thermal Images Using Neural Network

2021 ◽  
Vol 11 (3) ◽  
pp. 931
Author(s):  
Changmin Kim ◽  
Jae-Sol Choi ◽  
Hyangin Jang ◽  
Eui-Jong Kim
Keyword(s):  
Neural Network ◽  
Detection Method ◽  
Early Stage ◽  
Thermal Anomaly ◽  
Building Envelopes ◽  
Subjective Judgment ◽  
Thermal Images ◽  
Thermal Bridge ◽  
Thermal Bridges ◽  
Infrared Thermal Images

Detecting thermal bridges in building envelopes should be a priority to improve the thermal performance of buildings. Recently, thermographic surveys are being used to detect thermal bridges. However, conventional methods of detecting thermal bridges from thermal images rely on the subjective judgment of audits. Research has been conducted to automatically detect thermal bridges from thermal images to improve problems caused by such subjective judgment, but most of these studies are still in the early stage. Therefore, this study proposes a linear thermal bridge detection method based on image processing and machine learning. The proposed method includes thermal anomaly area clustering, feature extraction, and an artificial-neural-network-based thermal bridge detection. The proposed method was validated by detecting the thermal bridges in actual buildings. As a result, the average precision, recall, and F-score were 89.29%, 87.29, and 87.63%, respectively.

Sign in / Sign up

Export Citation Format

Share Document