Tang Zongbu, Jian Xuan
Infrastructure Department, Shanghai University of Traditional Chinese Medicine, Shanghai, 201203, China.
Power Supply Service Command Center, State Grid Beibei Power Supply Company, Chongqing, 400070, China.
Sci Rep. 2024 Mar 6;14(1):5547. doi: 10.1038/s41598-024-56142-x.
This paper realizes infrared image denoising, recognition, and semantic segmentation for complex electrical equipment and proposes a thermal fault diagnosis method that incorporates temperature differences. We introduce a deformable convolution module into the Denoising Convolutional Neural Network (DeDn-CNN) and propose an image denoising algorithm based on this improved network. By replacing Gaussian wrap-around filtering with anisotropic diffusion filtering, we suggest an image enhancement algorithm that employs Weighted Guided Filtering (WGF) with an enhanced Single-Scale Retinex (Ani-SSR) technique to prevent strong edge halos. Furthermore, we propose a refined detection algorithm for electrical equipment that builds upon an improved RetinaNet. This algorithm incorporates a rotating rectangular frame and an attention module, addressing the challenge of precise detection in scenarios where electrical equipment is densely arranged or tilted. We also introduce a thermal fault diagnosis approach that combines temperature differences with DeeplabV3 + semantic segmentation. The improved RetinaNet's recognition results are fed into the DeeplabV3 + model to further segment structures prone to thermal faults. The accuracy of component recognition in this paper achieved 87.23%, 86.54%, and 90.91%, with respective false alarm rates of 7.50%, 8.20%, and 7.89%. We propose a comprehensive method spanning from preprocessing through target recognition to thermal fault diagnosis for infrared images of complex electrical equipment, providing practical insights and robust solutions for future automation of electrical equipment inspections.
本文实现了复杂电气设备的红外图像去噪、识别和语义分割，并提出了一种结合温差的热故障诊断方法。我们将可变形卷积模块引入去噪卷积神经网络（DeDn-CNN），并基于此改进网络提出了一种图像去噪算法。通过用各向异性扩散滤波代替高斯环绕滤波，我们提出了一种图像增强算法，该算法采用加权引导滤波（WGF）和增强单尺度视网膜（Ani-SSR）技术来防止强边缘光晕。此外，我们提出了一种基于改进的RetinaNet的电气设备精细检测算法。该算法结合了旋转矩形框和注意力模块，解决了电气设备密集排列或倾斜场景下的精确检测难题。我们还介绍了一种将温差与DeeplabV3 +语义分割相结合的热故障诊断方法。将改进的RetinaNet的识别结果输入到DeeplabV3 +模型中，以进一步分割容易出现热故障的结构。本文中部件识别的准确率分别达到87.23%、86.54%和90.91%，误报率分别为7.50%、8.20%和7.89%。我们提出了一种针对复杂电气设备红外图像从预处理到目标识别再到热故障诊断的综合方法，为未来电气设备检查的自动化提供了实用的见解和可靠的解决方案。
