Attallah Omneya, Ibrahim Rania A, Zakzouk Nahla E
Electronics and Communications Engineering Department, College of Engineering and Technology, Arab Academy for Science, Technology, and Maritime Transport, Alexandria, 21937, Egypt.
Wearables, Biosensing, and Biosignal Processing Laboratory, Arab Academy for Science, Technology, and Maritime Transport, Alexandria, 21937, Egypt.
Sci Rep. 2025 Apr 25;15(1):14505. doi: 10.1038/s41598-025-96290-2.
Scheduled maintenance and condition monitoring of power transformers in smart grids is mandatory to reduce their downtimes and maintain economic benefits. However, to minimize energy losses during inspection, non-invasive fault diagnosis techniques such as thermogram imaging can enable continuous monitoring of transformer health with minimal out-of-service time. Deep learning (DL) has proven to be a fast and efficient intelligent diagnostic tool. In this paper, a DL-based thermography method is proposed called Trans-Light for transformers' interturn faults detection and short-circuit severity identification. Trans-light extracts deep features from two deep layers of a convolutional neural network (CNN) rather than depending on one layer, thus obtaining more intricate patterns. Moreover, a Dual-tree Complex Wavelet Transform method is adopted which offers two enhancements. First, it acquires time-frequency knowledge besides the already obtained spatial information and second, it reduces the huge deep features dimensionality. Trans-light combines extracted deep features, then a feature selection process is applied to further reduce features' size, thus decreasing computation burden and reducing classification and training time. To validate the proposed scheme's diagnosis performance and robustness, different combinations of two CNN models, two feature selection methods, and six classifiers were tested, applying the proposed Trans-light framework, under noise-free and noise-existing conditions. Experimental results indicated that the combination of the LDA classifier, applied with the ResNet-18 CNN model and trained with merged deep features undergoing the chi-square (χ) selection approach, attained superior performance under noise-free conditions. Compared to its counterparts in previous work, this configuration outperforms their performance since it uses the fewest features' number yet maintains 100% classification accuracy. Besides, it attained robust performance under two different noise natures again with minimal features' dimension, thus minimizing computational load and implementation complexity.
对智能电网中的电力变压器进行定期维护和状态监测，对于减少其停机时间并维持经济效益而言是必不可少的。然而，为了在检查期间将能量损失降至最低，诸如热成像等非侵入式故障诊断技术能够以最短的停用时间对变压器健康状况进行持续监测。深度学习（DL）已被证明是一种快速且高效的智能诊断工具。在本文中，提出了一种基于深度学习的热成像方法，称为Trans-Light，用于变压器匝间故障检测和短路严重程度识别。Trans-Light从卷积神经网络（CNN）的两个深层中提取深度特征，而不是依赖于一层，从而获得更复杂的模式。此外，采用了双树复数小波变换方法，该方法有两个改进之处。第一，除了已获取的空间信息外，它还能获取时频信息；第二，它降低了巨大的深度特征维度。Trans-Light将提取的深度特征进行组合，然后应用特征选择过程进一步减小特征规模，从而减轻计算负担并减少分类和训练时间。为了验证所提方案的诊断性能和鲁棒性，在无噪声和有噪声条件下，应用所提的Trans-Light框架，对两个CNN模型、两种特征选择方法和六个分类器的不同组合进行了测试。实验结果表明，在无噪声条件下，将线性判别分析（LDA）分类器与ResNet-18 CNN模型相结合，并使用经过卡方（χ）选择方法训练的合并深度特征，可获得卓越的性能。与先前工作中的同类方法相比，这种配置表现更优，因为它使用的特征数量最少，同时保持了100%的分类准确率。此外，它在两种不同噪声特性下再次以最小的特征维度实现了鲁棒性能，从而将计算负载和实现复杂度降至最低。
