Porcelain Insulator Crack Location and Surface States Pattern Recognition Based on Hyperspectral Technology

A porcelain insulator is an important part to ensure that the insulation requirements of power equipment can be met. Under the influence of their structure, porcelain insulators are prone to mechanical damage and cracks, which will reduce their insulation performance. After a long-term operation, crack expansion will eventually lead to breakdown and safety hazards. Therefore, it is of great significance to detect insulator cracks to ensure the safe and reliable operation of a power grid. However, most traditional methods of insulator crack detection involve offline detection or contact measurement, which is not conducive to the online monitoring of equipment. Hyperspectral imaging technology is a noncontact detection technology containing three-dimensional (3D) spatial spectral information, whereby the data provide more information and the measuring method has a higher safety than electric detection methods. Therefore, a model of positioning and state classification of porcelain insulators based on hyperspectral technology is proposed. In this model, image data were used to extract edges to locate cracks, and spectral information was used to classify the surface states of porcelain insulators with EfficientNet. Lastly, crack extraction was realized, and the recognition accuracy of cracks and normal states was 96.9%. Through an analysis of the results, it is proven that the crack detection method of a porcelain insulator based on hyperspectral technology is an effective non-contact online monitoring approach, which has broad application prospects in the era of the Internet of Things with the rapid development of electric power.

[1]  Chengzhi Deng,et al.  Orthogonal Nonnegative Matrix Factorization Combining Multiple Features for Spectral–Spatial Dimensionality Reduction of Hyperspectral Imagery , 2016, IEEE Transactions on Geoscience and Remote Sensing.

[2]  Zhenbing Zhao,et al.  Insulator Fault Detection Based on Spatial Morphological Features of Aerial Images , 2018, IEEE Access.

[3]  L. Zhang,et al.  Non-destructive detection and classification of in-shell insect-infested almonds based on multispectral imaging technology , 2018, The Journal of Agricultural Science.

[4]  Bin Wang,et al.  A Novel Spatial–Spectral Similarity Measure for Dimensionality Reduction and Classification of Hyperspectral Imagery , 2014, IEEE Transactions on Geoscience and Remote Sensing.

[5]  Paul Geladi,et al.  Hyperspectral Image Data Conditioning and Regression Analysis , 2007 .

[6]  Shiming Xiang,et al.  Efficient edge-guided full-waveform inversion by Canny edge detection and bilateral filtering algorithms , 2016 .

[7]  Yao Degui,et al.  Inverse application of charge simulation method in detecting faulty ceramic insulators and processing influence from tower , 2006, IEEE Transactions on Magnetics.

[8]  Ming-Der Yang,et al.  Integrating MNF and HHT Transformations into Artificial Neural Networks for Hyperspectral Image Classification , 2020, Remote. Sens..

[9]  Jie Yang,et al.  Convolutional neural network in network (CNNiN): hyperspectral image classification and dimensionality reduction , 2019, IET Image Process..

[10]  Quoc V. Le,et al.  EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks , 2019, ICML.

[11]  Kemal Akyol,et al.  Plant leaf disease classification using EfficientNet deep learning model , 2021, Ecol. Informatics.

[12]  Sukhan Lee,et al.  Extracting Major Lines by Recruiting Zero-Threshold Canny Edge Links along Sobel Highlights , 2015, IEEE Signal Processing Letters.

[13]  Xiaojun Shen,et al.  A Novel Method for Live Detection of Faulty Direct Current Insulators , 2008, IEEE Transactions on Power Delivery.

[14]  Yuxiang Zhang,et al.  Deep Metric Learning with Online Hard Mining for Hyperspectral Classification , 2021, Remote. Sens..

[15]  Kai Liu,et al.  Surface Roughness Detection of Roof Insulator Based on Hyperspectral Technology , 2020, IEEE Access.

[16]  Antonio Plaza,et al.  Low–High-Power Consumption Architectures for Deep-Learning Models Applied to Hyperspectral Image Classification , 2019, IEEE Geoscience and Remote Sensing Letters.

[17]  Jong Rak Yoon,et al.  Acoustic Fault Detection Technique for High-Power Insulators , 2017, IEEE Transactions on Industrial Electronics.

[18]  Shiqi Huang,et al.  Locality Preserving Projection Based on Endmember Extraction for Hyperspectral Image Dimensionality Reduction and Target Detection , 2016, Applied spectroscopy.

[19]  Baojun Zhao,et al.  Spectral–spatial classification of hyperspectral remote sensing image based on capsule network , 2019, The Journal of Engineering.

[20]  Xiuqin Rao,et al.  Quality and safety assessment of food and agricultural products by hyperspectral fluorescence imaging. , 2012, Journal of the science of food and agriculture.

[21]  Noël Richard,et al.  Hyperspectral crack detection in paintings , 2015, 2015 Colour and Visual Computing Symposium (CVCS).

[22]  K. Moon,et al.  Discriminating the origin of basil seeds (Ocimum basilicum L.) using hyperspectral imaging analysis , 2020 .

[23]  Xian Tao,et al.  Detection of Power Line Insulator Defects Using Aerial Images Analyzed With Convolutional Neural Networks , 2020, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[24]  L. Sharma,et al.  AVIRIS-NG hyperspectral data analysis for pre- and post-MNF transformation using per-pixel classification algorithms , 2020, Geocarto International.

[25]  Antonio Plaza,et al.  Entropy-Based Convex Set Optimization for Spatial–Spectral Endmember Extraction From Hyperspectral Images , 2020, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[26]  Jon Y. Hardeberg,et al.  Path Opening for Hyperspectral Crack Detection of Cultural Heritage Paintings , 2018, 2018 14th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS).

[27]  Yakoub Bazi,et al.  Classification of Remote Sensing Images Using EfficientNet-B3 CNN Model With Attention , 2021, IEEE Access.

[28]  L. Persson,et al.  Ultrasonic inspection of line pin post insulators and solid core insulators in switch gear stations , 1993 .

[30]  Zhao Baojun,et al.  Compressed spatial–spectral feature representation for hyperspectral ground classification , 2019 .

[31]  Haifang Wen,et al.  Partial discharge occurrence induced by crack defect on GIS insulator operated at 1100 kV , 2016, IEEE Transactions on Dielectrics and Electrical Insulation.

[32]  Oubong Gwun,et al.  Apple Defects Detection Using Principal Component Features of Multispectral Reflectance Imaging , 2018, Science of Advanced Materials.

[33]  Wilfried Philips,et al.  Feature Extraction of Hyperspectral Images With Semisupervised Graph Learning , 2016, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[34]  Bo Du,et al.  A Novel Semisupervised Active-Learning Algorithm for Hyperspectral Image Classification , 2017, IEEE Transactions on Geoscience and Remote Sensing.