The Experts below are selected from a list of 1119 Experts worldwide ranked by ideXlab platform
Jin Liju - One of the best experts on this subject based on the ideXlab platform.
-
Identification of Insulator Contamination Grade Combining Color Features of Visual Image with Support Vector Machine
High Voltage Apparatus, 2015Co-Authors: Jin LijuAbstract:In respect that the high risk of flashover may cause power outage, it is urgent to realize the safe and accurate monitoring of Insulator Contamination severity to prevent flashover and ensure operation of power system. In this paper, a method based on visible image features of contaminated Insulators and support vector machine is put forward by establishing a mapping between the Contamination grade and the color features for the identification purpose of Insulator Contamination grade. Firstly, the improved image segmentation method based on the seed region growing method is adopted to achieve the discal surfaces of the red porcelain Insulators with different Contamination grades in the transformer substations in Shenzhen City. Then, thirty-six Contamination features are extracted in RGB and HSV color space of the contaminated Insulator images and the mean and median of S are selected as the feature values for the Insulator Contamination grade according to the Fisher criterion. Finally, a multi-class SVM for classification decision is designed. Experimental results show that the identification accuracy of the proposed method reaches 96.67%.
-
research of Insulator Contamination grades recognition methodology based on visual image
Computer Simulation, 2014Co-Authors: Jin LijuAbstract:In order to realize the non-contact measurement of Insulator Contamination grades, a method based on feature level fusion of information from RGB and HSI color spaces was proposed. Mathematical morphology improved optimal entropic threshold(OET) segmentation algorithm was adopted to segment Insulator surface. Features of RGB and HSI color spaces were calculated separately. And then, feature selection based on Fisher criterion was carried out to obtain features which have ability to distinguish the Contamination grades efficiently. Kernel principal component analysis(KPCA) was adopted to realize the feature level fusion of information from RGB and HSI color spaces and obtain three-dimensional fused features. A BP neural network with particle swarm optimization(PSO) was used to recognize the Contamination grades. The experimental results indicate that the feature level fusion of image color information based on KPCA has capability to characterize the Contamination grades comprehensively. Compared with recognition using RGB or HSI features solely, the proposed method can improve the accuracy rate significantly and realize the Contamination grades recognition effectively. A new method for the prevention of pollution flashover is presented.
Lijun Jin - One of the best experts on this subject based on the ideXlab platform.
-
Condition Evaluation of the Contaminated Insulators by Visible Light Images Assisted With Infrared Information
IEEE Transactions on Instrumentation and Measurement, 2018Co-Authors: Lijun Jin, Zhiren Tian, Yingyao Zhang, Kai GaoAbstract:Pollution flashover is harmful and has caused huge economic losses. Thus, it is important to evaluate the Contamination condition of Insulators to prevent the pollution flashover. The objective of this paper is to discriminate the Insulator Contamination grades by the noncontact method. In this paper, a method of visible light images assisted with infrared information is proposed. The proposed method evaluates the Contamination condition using the visible light images, and is corrected by the infrared information in the wet environment. A mathematical model is established to study the relationship between the equivalent salt deposit density (ESDD) (mg/cm2) and the color features. The influences of illumination L and relative humidity (RH) on the color features are analyzed and their eliminated methods are proposed. The infrared image information is proposed to assist the visible light image method when RH ≥ 60%. In the experiment, the visible light images of the artificial polluted Insulators are acquired by a digital camera under different illuminations L and RHs, and the average value of V component $V_{ave}$ in the YUV color space is selected for the discrimination of Contamination grades. In the test, the proposed method gives an 84% accuracy rate when RH < 60% and gives an 89% accuracy rate when RH ≥ 60%. Finally, naturally polluted Insulators were tested. The general test error of ESDD is about 0.0119 mg/cm2. Therefore, it might be concluded the condition of naturally polluted Insulators could be evaluated by the proposed method of visible light images assisted with infrared information.
-
Discrimination of transmission line Insulator Contamination grades using visible light images
2016 IEEE 16th International Conference on Environment and Electrical Engineering (EEEIC), 2016Co-Authors: Zhiren Tian, Lijun Jin, Chenyi Peng, Wei Duan, Kai GaoAbstract:Flashover occurs more easily on contaminated transmission line Insulators, which causes great economic losses and has bad effects on power system stability. An accurate and safe detection of Insulator Contamination grades is required. In this paper, a new method is proposed to discriminate Insulator Contamination grades using visible light images. Firstly, ZSW-10/4 Insulators are smeared in different Contamination grades, and their visible light images are shot under illumination ranges from 10,000lux to 100,000lux. Secondly, both software methods and hardware methods are adopted and compared to eliminate the effects of illumination. After image processing, Insulator surface color features in several color spaces are calculated. Results of Fisher criterion shows that hardware methods work better in eliminating illumination effects, and mean value of V component in YUV color space is selected for discriminating Contamination grades. Finally, BP (Back Propagation) neural networks are established, whose testing accuracy rates are over 90% in discriminating Contamination grades. Further, a general formula between mean value of V component and ESDD (Equivalent Salt Deposit Density) is obtained.
-
Contamination Grades Recognition of Ceramic Insulators Using Fused Features of Infrared and Ultraviolet Images
Energies, 2015Co-Authors: Lijun Jin, Da ZhangAbstract:In order to realize the non-contact measurement of ceramic Insulator Contamination severity, a method based on feature level fusion of infrared (IR) and ultraviolet (UV) image information is proposed in this paper. IR and UV images of artificially polluted Insulators were obtained from high voltage experiments at 80%, 85% and 90% RH. After the preprocessing of images, IR and UV features were calculated, respectively. Then, feature selection based on Fisher criterion was adopted to gain features, which have the ability to distinguish different Contamination grades effectively. In feature level fusion section, kernel principal component analysis (KPCA) was applied to the dimensionality reduction fusion of IR and UV features and obtain three-dimensional fused features. A particle swarm optimized back propagation neural network (PSO-BPNN) classifier was constructed and trained to recognize the Contamination grades. Experimental results indicate that the feature level fusion of IR and UV information based on KPCA has capability to characterize the Contamination grades comprehensively. Compared with recognition using IR or UV features separately, recognition based on the feature level fusion is more accurate and effective. This study provides a new methodology for the measurement of Insulator Contamination severity at working condition
-
Discrimination of Insulator Contamination grades using information fusion of multi-light images
2015 IEEE 11th International Conference on the Properties and Applications of Dielectric Materials (ICPADM), 2015Co-Authors: Zhiren Tian, Lijun Jin, Yingyao Zhang, Chenyi Peng, Wei DuanAbstract:Flashover occurs more easily on contaminated Insulators, which causes great economic losses and has bad effects on power system stability. A new method is introduced to discriminate the Contamination grades of high voltage Insulators, using information fusion of visible images and infrared images of the Insulators. Firstly, three heating models of running Insulators—No Dry Band, Dry Band and Dry Band Arc are established and solved by numerical analysis method to find out the differences in temperature rise under different running states. Secondly, we smear 10kV Insulators in different Contamination grades. Then we take their visible images by camera and infrared images by infrared thermal imager after applying the rated AC voltage for hours in artificial fog chamber in different relative humidity. After image processing, we extract 36 disk color features from the visible images and 7 disk temperature features from the infrared images, and screen out the best features using Fisher discrimination. Then, two BP (Back Propagation) neural networks are trained, one of which takes the selected visible image features as the inputs while another uses the selected infrared image features and relative humidity. Furthermore, we fuse the information of visible images and infrared images on feature level, which raises the accuracy in identifying the sample images. This method may provide effective information for Insulator cleaning and flashover prevention.
Da Zhang - One of the best experts on this subject based on the ideXlab platform.
-
Intelligent Recognition of Insulator Contamination Grade Based on the Deep Learning of Ultraviolet Discharge Image Information
Energies, 2020Co-Authors: Da Zhang, Shuailin ChenAbstract:In order to achieve the noncontact detection of the Contamination grade of Insulators and to provide guidance for preventing the Contamination flashover of Insulators based on the pollution state, we propose a Contamination grade recognition method based on the deep learning of ultraviolet discharge images using a sparse autoencoder (SAE) and a deep belief network (DBN). Under different humidity conditions, we filmed and preprocessed the ultraviolet discharge images of Insulators at different Contamination grades and we obtained the ultraviolet spot area sequence as original data for Contamination grade recognition. A double-layer sparse autoencoder was used to extract sparse features that could characterize different Contamination grades from the ultraviolet spot area sequence. Using the extracted features, a DBN composed of three layers of restricted Boltzmann machine was trained to provide Contamination grade recognition. To verify the effectiveness of the method proposed in this paper, high-voltage experiments were performed on contaminated Insulators at relative humidity levels of 80%, 85%, and 90%, and ultraviolet images were recorded. The proposed SAE–DBN method was used to identify the ultraviolet images of the Insulators with different Contamination grades. The recognition accuracy rates at the three humidity levels were 91.25%, 93.125%, and 92.5%. The experimental results showed that this method could accurately recognize the Contamination grade of the Insulator and provide guidance for the prevention of Contamination flashover based on the pollution severity.
-
Contamination Grades Recognition of Ceramic Insulators Using Fused Features of Infrared and Ultraviolet Images
Energies, 2015Co-Authors: Lijun Jin, Da ZhangAbstract:In order to realize the non-contact measurement of ceramic Insulator Contamination severity, a method based on feature level fusion of infrared (IR) and ultraviolet (UV) image information is proposed in this paper. IR and UV images of artificially polluted Insulators were obtained from high voltage experiments at 80%, 85% and 90% RH. After the preprocessing of images, IR and UV features were calculated, respectively. Then, feature selection based on Fisher criterion was adopted to gain features, which have the ability to distinguish different Contamination grades effectively. In feature level fusion section, kernel principal component analysis (KPCA) was applied to the dimensionality reduction fusion of IR and UV features and obtain three-dimensional fused features. A particle swarm optimized back propagation neural network (PSO-BPNN) classifier was constructed and trained to recognize the Contamination grades. Experimental results indicate that the feature level fusion of IR and UV information based on KPCA has capability to characterize the Contamination grades comprehensively. Compared with recognition using IR or UV features separately, recognition based on the feature level fusion is more accurate and effective. This study provides a new methodology for the measurement of Insulator Contamination severity at working condition
Hdhl Electrical - One of the best experts on this subject based on the ideXlab platform.
-
Analysis of Visual Angle Influence on Infrared Thermal Image Detecting of Insulator Contamination Grades
High Voltage Engineering, 2008Co-Authors: Liu Yun-peng, Hdhl ElectricalAbstract:In order to improve the accuracy of detecting Insulator Contamination grade by infrared imaging,a method to determine the best visual angle using comparative analysis of pollution grade classification features Abstracted from Insulator infrared images is proposed. The image region of the ceramic piece surface of Insulator is intercepted manually after the contrast of the original thermal image was enhanced by histogram equalization. The intercepted image is binarizated according to the segmentation threshold extracted from the histogram envelope line. The ceramic piece surface image of Insulator is extracted through morphological filtering on the binarizated image. From which ten pollution grade classification features are extracted statistically,such as the highest temperature,the lowest temperature,the mean temperature,the temperature variance of the Insulator surface. The Fisher criterion is applied to comparative analysis. The analytical result of porcelain Insulator infrared thermal image from artificial pollution test indicates that the thermal field of Insulator surface significantly changes with the angle of view,and the features of lower surface have better classification performance than the uppers. It is recommended that the visual angle should aim at the lower surface for detecting Insulator Contamination grades by infrared imaging.
-
Infrared Thermal Image Detecting of High Voltage Insulator Contamination Grades Based on Support Vector Machine
Automation of electric power systems, 2005Co-Authors: He Hong-ying, Hdhl ElectricalAbstract:This paper presents a new method that integrates infrared thermal image technique with support vector machine (SVM) classifiers to check the Contamination grades of high voltage Insulators. Firstly, a self-adaptive smooth filter based on gradient information is used to remove the noise of the original image. Secondly, the OTSU segmentation method is adopted to segment the target area from the above filtered image. Four features are then extracted from the surface of the Insulator, viz. maximum temperature, contrast ratio between maximum and minimum temperatures, and standard deviation of Insulator surface temperatures, and ratio between the top 10% brightness pixels and the total pixels. Finally, a multi-class SVM is designed for Insulator Contamination grades detecting Experimental results indicate that four Insulator infrared features selected in this paper can represent the Contamination degree of an Insulator effectively and the multi-class SVM is of high efficiency with merely small samples. Thus it further shows the new approach proposed is feasible.
Shuailin Chen - One of the best experts on this subject based on the ideXlab platform.
-
Intelligent Recognition of Insulator Contamination Grade Based on the Deep Learning of Ultraviolet Discharge Image Information
Energies, 2020Co-Authors: Da Zhang, Shuailin ChenAbstract:In order to achieve the noncontact detection of the Contamination grade of Insulators and to provide guidance for preventing the Contamination flashover of Insulators based on the pollution state, we propose a Contamination grade recognition method based on the deep learning of ultraviolet discharge images using a sparse autoencoder (SAE) and a deep belief network (DBN). Under different humidity conditions, we filmed and preprocessed the ultraviolet discharge images of Insulators at different Contamination grades and we obtained the ultraviolet spot area sequence as original data for Contamination grade recognition. A double-layer sparse autoencoder was used to extract sparse features that could characterize different Contamination grades from the ultraviolet spot area sequence. Using the extracted features, a DBN composed of three layers of restricted Boltzmann machine was trained to provide Contamination grade recognition. To verify the effectiveness of the method proposed in this paper, high-voltage experiments were performed on contaminated Insulators at relative humidity levels of 80%, 85%, and 90%, and ultraviolet images were recorded. The proposed SAE–DBN method was used to identify the ultraviolet images of the Insulators with different Contamination grades. The recognition accuracy rates at the three humidity levels were 91.25%, 93.125%, and 92.5%. The experimental results showed that this method could accurately recognize the Contamination grade of the Insulator and provide guidance for the prevention of Contamination flashover based on the pollution severity.