电工电气杂志社

用于电力设备异常诊断的图像配准及融合方法

来源：电工电气发布时间：2024-12-02 08:02浏览次数：181

用于电力设备异常诊断的图像配准及融合方法

周喜红¹，席亚宾¹，李中宝²

(1 广东粤电大亚湾综合能源有限公司，广东惠州 516000；

2 中国核工业二三建设有限公司，北京 101300)

摘要：近年来图像融合方法在电力设备热异常的诊断中所占比重逐渐增加，但是涉及到图像配准和融合统一考虑的方法很少。提出了一种最大迭代关联图像配准及区域特性判别的图像融合方法，用于辅助热异常的诊断。该方法通过构建约束函数计算源图像配准迭代次数，隶属度函数定义源图像的区域特性，已知区域特性的子图像根据电力设备热异常所重视的特征优先选择融合策略，以最大程度保留源图像中的纹理特征和热辐射特征。在自建的电力设备数据集上与其他方法对比显示，所提方法在保证源图像配准精度的前提下，还突出了红外图像的热辐射特征和可见光图像的纹理特征，能够满足电力设备热异常诊断的需要。

关键词： 图像融合；图像配准；电力设备；热异常诊断；约束函数；隶属度函数；热辐射

中图分类号：TM711 ；TP391 文献标识码：B 文章编号：1007-3175(2024)11-0067-10

Image Registration and Fusion Method for Anomaly

Diagnosis of Power Equipment

ZHOU Xi-hong¹, XI Ya-bin¹, LI Zhong-bao²

（1 Guangdong Yuedian Daya Bay Integrated Energy Co., Ltd, Huizhou 516000, China;

2 China Nuclear Industry 23 Construction Co., Ltd, Beijing 101300, China）

Abstract: In recent years, the proportion of image fusion methods in the diagnosis of thermal anomalies of power equipment has gradually increased, but the methods involving unified consideration of image registration and fusion are rare. Therefore, this paper proposes an image fusion method based on maximum iterative correlation image registration and regional feature discrimination, which is used to assist thermal anomaly diagnosis. This method calculates the number of source image registration iterations by constructing a constraint function, and the membership function defines the regional characteristics of the source image. The sub-images with known regional characteristics preferentially select the fusion strategy according to the characteristics that the thermal anomaly of the power equipment attaches importance to, so as to retain the texture features and thermal radiation features in the source image to the greatest extent. Compared with other methods on the self-built power equipment dataset, the proposed method not only ensures the registration accuracy of the source image, but also highlights the thermal radiation characteristics of the infrared image and the texture characteristics of the visible image, which can meet the needs of thermal anomaly diagnosis of power equipment.

Key words: image fusion; image registration; power equipment; thermal anomaly diagnosis; constraint function; membership function;thermal radiation

参考文献

[1] CHEN Xiaolong, WANG Peihong, HAO Yongsheng, et al.Evidential KNN-Based Condition Monitoring and Early Warning Method with Applications in Power Plant[J].Neurocomputing，2018，315 ：18-32.

[2] HUANG Z, XIE W, LIU W, et al.TSCDNet +: A Highly Robust Substation Anomaly Detection Method[J].Optik，2021，246 ：167808.

[3] NAN L D, RUI H, QIANG L, et al.Research on Fuzzy Enhancement Algorithms for Infrared Image Recognition Quality of Power Internet of Things Equipment Based on Membership Function[J].Journal of Visual Communication & Image Representation，2019，62 ：359-367.

[4] ZOU H, HUANG F.A Novel Intelligent Fault Diagnosis Method for Electrical Equipment Using Infrared Thermography[J].Infrared Physics & Technology，2015，73 ：29-35.

[5] 鲁晓涵，李洋，邰昱博，等. 基于 GAN 轻量化改进的红外与可见光图像融合算法[J] . 电光与控制，2024，31(8) ：58-62.

[6] 冯新文，刘璟明，朱吕甫. 基于 MSR 和 BCI 的变电站巡检图像融合方法[J] . 电力信息与通信技术，2022，20(4) ：94-101.

[7] 阴锡君，刘郁，王一珺. 图像融合技术在变电站设备热故障监测中的应用研究[J] . 科技通报，2019，35(12) ：121-124.

[8] JIANG Qian, LIU Yadong, YAN Yingjie, et al.A Contour Angle Orientation for Power Equipment Infrared and Visible Image Registration[J].IEEE Transactions on Power Delivery，2020，36(4) ：2559-2569.

[9] LU Mingshu, LIU Haiting, YUAN Xipeng.Thermal Fault Diagnosis of Electrical Equipment in Substations Based on Image Fusion[J]. Traitement Du ：Signal Imageparole，2021，38(4) ：1095-1102.

[10] 李健，王滨海，李丽，等. 基于 SIFT 的电力设备红外与可见光图像的配准和融合[J] . 光学与光电技术，2012，10(1) ：75-78.

[11] XU Han, MA Jiayi, YUAN Jiteng, et al.RFNet:Unsupervised Network for Mutually Reinforcing Multi-Modal Image Registration and Fusion[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR)，2022.

[12] ZHU Qidan, JING Liqiu, BI Rongsheng.Exploration and Improvement of Ostu Threshold Segmentation Algorithm [C]//The 8th World Congress on Intelligent Control and Automation, 2010.

[13] JING Zhongliang.Image Fusion Based on an Expectation Maximization Algorithm[J].Optical Engineering，2005，44(7) ：077001.

[14] PALSSON F, SVEINSSON J R, ULFARSSON M O,et al . Model-Based Fusion of Multi-and Hyperspectral Images Using PCA and Wavelets[J].IEEE Transactions on Geoscience & Remote Sensing，2015，53(5) ：2652-2663.

[15] SHEN R, CHENG I, BASU A.Cross-Scale Coefficient Selection for Volumetric Medical Image Fusion[J].IEEE Transactions on BiomedicalEngineering，2012，60(4) ：1069-1079.

[16] JAGER F, HORNEGGER J.Nonrigid Registration of Joint Histograms for Intensity Standardization in Magnetic Resonance Imaging [J] . IEEE Transactions on Medical Imaging，2008，28(1) ：137-150.

[17] GONCALVES H, CORTE-REAL L, GONCALVES J A.Automatic Image Registration Through Image Segmentation and SIFT[J].IEEE Transactions on Geoscience and Remote Sensing，2011，49(7) ：2589-2600.

[18] BAY H, ESS A, TUYTELAARS T, et al.Speeded-Up Robust Features(SURF)[J].Computer Vision & Image Understanding，2008，110(3) ：346-359.

[19] LI Shutao, KANG Xudong, HU Jianwen.Image Fusion with Guided Filtering[J].IEEE Transactions on Image Processing，2013，22(7) ：2864-2875.

[20] MA J Y, CHEN C, LI C, et al.Infrared and Visible Image Fusion Via Gradient Transfer and Total Variation Minimization[J].Information Fusion，2016，31 ：100-109.

[21] BAVIRISETTI D P, XIAO G, LIU G.Multi-Sensor Image Fusion Based on Fourth Order Partial Differential Equations[C]//2017 20th International Conference on Information Fusion，2017.

[22] YAN Lei, CAO Jie, RIZVI Saad, et al.Improving the Performance of Image Fusion Based on Visual Saliency Weight Map Combined with CNN[J].IEEE Access，2020，8 ：59976-59986.

[23] XU Han, MA Jiayi, JIANG Junjun, et al.U2Fusion:A Unified Unsupervised Image Fusion Network[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2022，44(1) ：502-518.

[24] MA Jiayi, XU Han, JIANG Junjun, et al.DDcGAN:A Dual-Discriminator Conditional Generative Adversarial Network for Multi-Resolution Image Fusion[J].IEEE Transactions on Image Processing，2020，29 ：4980-4995.

[25] MA Jiayi, ZHANG Hao, SHAO Zhenfeng, et al.GANMcC:A Generative Adversarial Network with Multiclassification Constraints for Infrared and Visible Image Fusion[J].IEEE Transactions on Instrumentation and Measurement，2020，70 ：5005014.

[26] MA Jiayi, TANG Linfeng, XU Meilong, et al.STDFusionNet:An Infrared and Visible Image Fusion Network Based on Salient Target Detection[J].IEEE Transactions on Instrumentation and Measurement，2021，70 ：5009513.

[27] SENGUPTA D, GUPTA P, BISWAS A.A Survey on Mutual Information Based Medical Image Registration Algorithms[J].Neurocomputing，2021，486 ：174-188.

[28] ROBERTS J W, AARDT J V, AHMED F.Assessment of Image Fusion Procedures Using Entropy, Image Quality, and Multispectral Classification[J].Journal of Applied Remote Sensing，2008，2(1) ：1-28.

[29] WANG E , YANG B , PANG L . Superpixel-Based Structural Similarity Metric for Image Fusion Quality Evaluation[J].Sensing and Imaging，2021，22(1) ：1-25.

[30] XYDEAS C S , PV V . Objective Image Fusion Performance Measure[J].Military Technical Courier，2000，56(4) ：181-193.

[31] ESKICIOGLU A M, FISHER P S.Image Quality Measures and Their Performance [J] . IEEE Transactions on Communications，1995，43(12) ：2959-2965.

返回索引列表

SUBSCRIPTION MANAGEMENT

发行征订

用于电力设备异常诊断的图像配准及融合方法