Detecting insulation performance through testing the Raman spectroscopy of transformer oil is noninvasive and shows great promise in on-site diagnosis. The information, stored in spectra, that may reflect aging states of insulation aims to be effectively unfolded and provides decision support as well. In this article, a transformation method based on intrinsic product arithmetic is used to transform the 1-D Raman spectral data into 2-D image data. With the help of CNN based on the dimensionality expanding method, diagnosis of oil-paper insulation with different aging states based on the Raman spectroscopy was realized. The network-based oil-paper insulation aging diagnosis model has an accuracy of 95% in ten aging categories of 60 test samples and 100% in four aging categories. The result shows the trained CNN was able to identify the differences of transformer oil samples at each aging stage through visualized Raman spectral image. This method provides a more accurate determination method for diagnosing oil-immersed transformers' aging conditions; it also develops an available method for a more detailed evaluation of insulation aging levels.

In the field of machine vision and pattern recognition, the convolutional neural network (CNN) is one of the hottest research topics. However, the application of CNN, which requires complicated operations, appears to be exceptionally difficult in resource-constrained embedded devices. In this paper, a parallel processing CNN accelerator based on optimized MobileNet is presented. By modifying the fully-connected layer of the MobileNet network topology with the convolution process, and postponing the global pooling layer, the model topology is unified, which is conducive to the design of the hardware accelerator. After using the 8-bit quantization strategy of network model parameters, the process of depthwise separable convolution is accelerated by parallel processing between channels and pipelined processing between layers. Thus, the processing speed and throughput of the accelerator can be improved. The designed accelerator classification performance on ImageNet achieved 580.6 frames per second (fps) on a ZYNQ AXZU5EV platform and a system power consumption of only 6.51 W. This result represents a 22.3x speedup compared to CPU and a 1.7x speedup compared to GPU, while the design has a lower power consumption than CPU and GPU, providing a reference for the application of CNN in embedded devices.

This study explores the method of applying surface enhanced Raman scattering (SERS) in diagnosing the aging stage of oil–paper insulation equipment in the power system, which provides access to the on-line mornitoring of electrical equipment. Oil–paper samples in different aging stages were obtained by accelerated aging experiments. Effective Raman signals of insulating oil were collected by using the self-made hexagonal sliver nano-plates SERS substrates and the self-assembled Raman detection platform. For the SERS data of oil-paper insulation samples, kernel entropy component analysis (KECA) was applied to extract the Raman spectral features and support vector machine (SVM) was used to recognize the the aging stage of oil–paper insulation. The results demonstrate that the KECA-SVM method exhibits a good diagnostic capacity and the recognition accuracy of the propsed method reached 81.43 % (57/70). In summary, a new spectral method is proposed to diagnose the aging stage of oil-paper insulation, which lays a foundation for the actual diagnosis of the aging condition in running oil–paper insulation equipment by Raman spectroscopy.

Timely identification of the aging stage of the transformer can effectively ensure the safe operation of the transformer and prevent the aging fault of the transformer. This work proposes the aging diagnosis of transformer using the Raman spectroscopic recurrence plot combined with learning vector quantization (LVQ) neural network. Oil-paper insulation samples at different aging stages are obtained by accelerated thermal aging tests. Acquisition of Raman spectra of insulating oil is from 800 to 3000 cm ⁻¹ and converts to the Raman spectroscopic recurrence plot. The gray-level cooccurrence matrix (GLCM) is used to extract the characteristic information of the Raman spectroscopic recurrence plot. The optimal number of neurons in competitive layer of LVQ neural network is determined by the experimental method. A transformer aging diagnosis model based on the Raman spectroscopic recurrence plot is established. The results show that the diagnostic accuracy of the proposed diagnostic model reached 95%. The Raman spectroscopic recurrence plot has more abundant aging “fingerprint” characteristic information and the proposed diagnostic method shows potential for monitoring oil-paper insulation.

Raman spectroscopy, with its specific ability to generate a unique fingerprint‐like spectrum of certain substances, has attracted much attention in diagnosing the ageing degree of oil–paper insulation. In this study, the feature extraction and ageing diagnosis methods of oil–paper insulation Raman spectroscopy data are further studied. Based on the non‐linear analysis of Raman spectra of different ageing samples, kernel principal component analysis was applied to extract the spectral features, and the back‐propagation neural network was used to build a diagnosis model with high diagnostic accuracy. The results show that Raman spectroscopy combined with kernel principal component analysis and the back‐propagation neural network can diagnose the ageing state of oil–paper insulation, with a diagnostic accuracy of 91.43% (64/70). The proposed method provides an effective and feasible method for the ageing assessment of oil‐immersed electrical equipment.