Recognition of partial discharge of cable accessories based on convolutional neural network with small data set

Abstract

Purpose Considering the problem that the high recognition rate of deep learning requires the support of mass data, this study aims to propose an insulating fault identification method based on small data set convolutional neural network (CNN). Design/methodology/approach Because of the chaotic characteristics of partial discharge (PD) signals, the equivalent transformation of the PD signal of unit power frequency period is carried out by phase space reconstruction to derive the chaotic features. At the same time, geometric, fractal, entropy and time domain features are extracted to increase the volume of feature data. Finally, the combined features are constructed and imported into CNN to complete PD recognition. Findings The results of the case study show that the proposed method can realize the PD recognition of small data set and make up for the shortcomings of the methods based on CNN. Also, the 1-CNN built in this paper has better recognition performance for four typical insulation faults of cable accessories. The recognition performance is improved by 4.37% and 1.25%, respectively, compared with similar methods based on support vector machine and BPNN. Originality/value In this paper, a method of insulation fault recognition based on CNN with small data set is proposed, which can solve the difficulty to realize insulation fault recognition of cable accessories and deep data mining because of insufficient measure data.

Defect Prediction Technology in Software Engineering Based on Convolutional Neural Network

“…Describing variables in terms of its purpose as inputs is still a valid concept. To examine software flaws, authors have developed neural network prediction models, and several neural network optimization models have been suggested [28]. Various authors have introduced deep learning into the study field of software imperfection prediction technology [29][30][31].…”

Optimizing the Training Mode of Swimmers Based on Deep Learning and Data Mining Technology

“…Due to the chaotic characteristics of partial discharge (PD) signals, the chaotic characteristics are obtained by equivalently transforming the partial discharge signals per unit power frequency cycle through phase space reconstruction. This method can realize the partial discharge identification of small data sets, which makes up for the deficiency of the partial discharge identification method based on CNN [2]. Person reidentification aims to match specific persons with nonoverlapping cameras.…”

“…The innovation of this paper lies in (1) using data mining technology and deep learning to study the optimization of the training mode of swimmers; (2) it is innovative and practical.…”

An improved deep neural network method for athlete’s human motion posture recognition

“…Environment modelling is the basis of athlete body's motion analysis based on video sequence. The camera used is edited to establish background model, which lays a good foundation for motion segmentation (Zhang et al, 2020). Suppose that the extracted video sequence consists of n frames, and the pixel value of each frame at position (x, y) is marked as P j (x, y), where j represents the number of frames.…”