Intelligent Localization of Transformer Internal Degradations Combining Deep Convolutional Neural Networks and Image Segmentation

Duan, Jiajun; He, Yigang; Du, Bolun; Ghandour, Ruaa M. Rashad; Wu, W.; Zhang, Hui

doi:10.1109/access.2019.2916461

Cited by 24 publications

(14 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…On the basis of our results, (7) an improved gray correlation analysis technology for recognizing users' transformer attributes in intelligent platform areas is proposed. We introduce the concept of entropy into this method to compute the correlation, thus eliminating some subjective estimation.…”

Section: Introductionmentioning

confidence: 96%

“…Duan et al put forward the idea of evaluating survey data for a smart watt-hour meter that is connected to gray relational data to recognize the attributes of users' transformers and the phase of the platform area. (7) Because the weight of each variable is fixed in the correlation calculation and also subjective, the reliability of the results is low in a complex environment. Yu et al proposed the first-order differential attributes of users' transformers of the line loss rate as an index to diagnose abnormalities in users' transformer attributes, (8) and abnormalities were captured under the constraint of the proximity relationship of the common change space.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Intelligent Identification Technology of Attributes of Users’ Transformers Based on Gray Correlation Analysis

Liu¹,

Hu²,

Yang³

et al. 2021

Sensors and Materials

View full text Add to dashboard Cite

Power grid construction and power measurement automation systems are gaining popularity and becoming ever more commonplace in developing countries. However, adoption rates are affected by inaccurate intelligent identification systems that control remote meter reading and line loss management. Local electricity distribution networks also have inconsistent user cable wiring, different geographical topologies, and issues with cable crosstalk, which lead to inaccurate readings of users' data coming from the intelligent identification system, and sometimes even a failure to read electricity meters. Taking into consideration the voltage required for an intelligent identification system, we propose a new transformer for an intelligent identification system. Our new transformer improves the gray correlation analysis of watt-hour meters, which overcomes the shortcomings of existing identification methods by evaluating line voltages between unidentified and identified watt-hour meters. Experimental results show that our transformer with this method can accurately measure users' electricity meter readings and perform line loss management.

show abstract

Section: Introductionmentioning

confidence: 96%

Section: Introductionmentioning

confidence: 99%

Intelligent Identification Technology of Attributes of Users’ Transformers Based on Gray Correlation Analysis

Liu¹,

Hu²,

Yang³

et al. 2021

Sensors and Materials

View full text Add to dashboard Cite

show abstract

“…In recently years, deep learning has been widely used in the field of image processing. Since it can extract the deep semantic features of images and does not need to manually set the classifier, deep learning has many advantages in image segmentation, detection, and recognition [ 19 – 21 ]. Many researchers have applied deep learning to sonar image processing to detect sonar objective.…”

Section: Introductionmentioning

confidence: 99%

Sonar Objective Detection Based on Dilated Separable Densely Connected CNNs and Quantum‐Behaved PSO Algorithm

Zhen

Wang

Guo

et al. 2021

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Underwater sonar objective detection plays an important role in the field of ocean exploration. In order to solve the problem of sonar objective detection under the complex environment, a sonar objective detection method is proposed based on dilated separable densely connected convolutional neural networks (DS-CNNs) and quantum-behaved particle swarm optimization (QPSO) algorithm. Firstly, the dilated separable convolution kernel is proposed to extend the local receptive field and enhance the feature extraction ability of the convolution layers. Secondly, based on the linear interpolation algorithm, a multisampling pooling (MS-pooling) operation is proposed to reduce the feature information loss and restore image resolution. At last, with contraction-expansion factor and difference variance in the traditional particle swarm optimization algorithm introduced, the QPSO algorithm is employed to optimize the weight parameters of the network model. The proposed method is validated on the sonar image dataset and is compared with other existing methods. Using DS-CNNs to detect different kinds of sonar objectives, the experiments shows that the detection accuracy of DS-CNNs reaches 96.98% and DS-CNNs have better detection effect and stronger robustness.

show abstract

“…Fault locations were defined as classification labels, and different CNN's were used to classify the labels to achieve the fault localization results. Then, image segmentation was performed to extract the features of fault areas and simplify the data volumes [16].…”

Section: Introductionmentioning

confidence: 99%

Two-Terminal Fault Location Method of Distribution Network Based on Adaptive Convolution Neural Network

et al. 2020

View full text Add to dashboard Cite

When a single-phase ground fault occurs in a distribution network, it is generally allowed to operate with faults for one to two hours, which may lead to further development of the fault and even threaten the safe operation of the power system. Therefore, when a small current system has a ground fault, it must be quickly diagnosed to shorten the time of operation with fault. In this paper, an adaptive convolutional neural network (ACNN)-based fault line selection method is proposed for a distribution network. This method improves the feature extraction ability of the network by improving the pooling model. Compared with deep belief network (DBN), it can improve the accuracy of fault classification by 7.86% and reduce the training time by 42.7%. On this basis, the secondary fault location is identified using the principle of two-terminal fault location. In this research, fault data obtained by Simulink simulation is used as training set, and ACNN model is built based on TensorFlow framework. The analysis of results proves that the model has a high fault recognition rate and fast convergence speed. It can be used as an auxiliary hand for fault diagnosis in distribution networks. INDEX TERMS Convolutional neural network, adaptive pooling model, two-terminal fault location, distribution network, single-phase ground fault.

show abstract

Intelligent Localization of Transformer Internal Degradations Combining Deep Convolutional Neural Networks and Image Segmentation

Cited by 24 publications

References 38 publications

Intelligent Identification Technology of Attributes of Users’ Transformers Based on Gray Correlation Analysis

Intelligent Identification Technology of Attributes of Users’ Transformers Based on Gray Correlation Analysis

Sonar Objective Detection Based on Dilated Separable Densely Connected CNNs and Quantum‐Behaved PSO Algorithm

Two-Terminal Fault Location Method of Distribution Network Based on Adaptive Convolution Neural Network

Contact Info

Product

Resources

About