Fault Detection Method of Power Insulator Based on Deep Convolution Neural Network

Detection Methods ◽

Detection Accuracy ◽

Region Selection ◽

Function Design ◽

Deep Convolution Neural Network ◽

Anchor Design

Aiming at the problem of low detection accuracy of traditional power insulator fault detection methods, a power insulator fault detection method based on deep convolution neural network is designed. For the training of deep convolution neural network, the fault detection of power insulator based on deep convolution neural network is realized by anchor design, loss function design, candidate region selection mechanism establishment and sharing convolution features. The experimental results show that the fault detection method of power insulator based on deep convolution neural network is more accurate than the traditional method, and the detection time is less.

An Improved Object Detection Method Based On Deep Convolution Neural Network For Smoke Detection

2018 International Conference on Machine Learning and Cybernetics (ICMLC) ◽

10.1109/icmlc.2018.8527037 ◽

2018 ◽

Cited By ~ 2

Author(s):

Junying Zeng ◽

Zuoyong Lin ◽

Chuanbo Qi ◽

Xiaoxiao Zhao ◽

Fan Wang

Keyword(s):

Neural Network ◽

Object Detection ◽

Detection Method ◽

Smoke Detection ◽

An anomaly detection method using deep convolution neural network for vision image of robot

Multimedia Tools and Applications ◽

10.1007/s11042-020-08684-1 ◽

2020 ◽

Vol 79 (13-14) ◽

pp. 9629-9642

Author(s):

Yueyun Du

Keyword(s):

Neural Network ◽

Anomaly Detection ◽

Detection Method ◽

Infrared Ship Target Detection Method Based on Deep Convolution Neural Network

Acta Optica Sinica ◽

10.3788/aos201838.0712006 ◽

2018 ◽

Vol 38 (7) ◽

pp. 0712006

Author(s):

王文秀 Wang Wenxiu ◽

傅雨田 Fu Yutian ◽

董峰 Dong Feng ◽

李锋 Li Feng

Keyword(s):

Neural Network ◽

Target Detection ◽

Detection Method ◽

Deep Convolution Neural Network Based Fault Detection and Identification for Modular Multilevel Converters

2018 IEEE Power & Energy Society General Meeting (PESGM) ◽

10.1109/pesgm.2018.8586661 ◽

2018 ◽

Cited By ~ 4

Author(s):

Xiangshuai Qu ◽

Bin Duan ◽

Qiaoxuan Yin ◽

Mengjun Shen ◽

Yinxin Yan

Keyword(s):

Neural Network ◽

Fault Detection ◽

Multilevel Converters ◽

Detection And Identification ◽

Fault Detection And Identification ◽

Modular Multilevel Converters ◽

Research on Flame Combustion Stability Based on Neural Network

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.516-517.390 ◽

2012 ◽

Vol 516-517 ◽

pp. 390-394

Author(s):

Gui Zhi Bai ◽

Li Hong Zhang ◽

Shu Qian Chen

Keyword(s):

Neural Network ◽

Detection Method ◽

Combustion Stability ◽

Detection Methods ◽

Detection Accuracy ◽

Multiple Features ◽

Flame Combustion ◽

Flame Pulsation ◽

Neural Network Input ◽

The Impact

For the use of boiler flame image analysis to detect the boiler flame combustion stability, when the combustion affected by coal, peaking , improper operation or other effects, the flame appeared short pulsation. In general, the traditional detection methods based on gray scale variance can not avoid the impact of flame pulsation on account of the inaccuracy of the boiler combustion stability detection. This paper presents a flame combustion instability detection method based on neural network and selects multiple features which are directly related to the flame stability as neural network input vector. Experiments show that this method can fight off the tiny ripple influence caused by the impurities combustion or peak and simultaneously, greatly improve the detection accuracy and stability.

Proceedings of the 2019 8th International Conference on Computing and Pattern Recognition ◽

Fire Detection Method Based on Improved Deep Convolution Neural Network

10.1145/3373509.3373570 ◽

2019 ◽

Author(s):

Yiheng Cai ◽

Yajun Guo ◽

Yuanyuan Li ◽

Hui Li ◽

Jiaqi Liu

Keyword(s):

Neural Network ◽

Detection Method ◽

Fire Detection ◽

Improving Performance of Seismic Fault Detection by Fine-Tuning the Convolutional Neural Network Pre-Trained with Synthetic Samples

Energies ◽

10.3390/en14123650 ◽

2021 ◽

Vol 14 (12) ◽

pp. 3650

Author(s):

Zhe Yan ◽

Zheng Zhang ◽

Shaoyong Liu

Keyword(s):

Neural Network ◽

Deep Learning ◽

Fault Detection ◽

Seismic Data ◽

Learning Strategy ◽

Real Data ◽

Fine Tuning ◽

Detection Methods ◽

Training Dataset ◽

Detection Accuracy

Fault interpretation is an important part of seismic structural interpretation and reservoir characterization. In the conventional approach, faults are detected as reflection discontinuity or abruption and are manually tracked in post-stack seismic data, which is time-consuming. In order to improve efficiency, a variety of automatic fault detection methods have been proposed, among which widespread attention has been given to deep learning-based methods. However, deep learning techniques require a large amount of marked seismic samples as a training dataset. Although the amount of synthetic seismic data can be guaranteed and the labels are accurate, the difference between synthetic data and real data still exists. To overcome this drawback, we apply a transfer learning strategy to improve the performance of automatic fault detection by deep learning methods. We first pre-train a deep neural network with synthetic seismic data. Then we retrain the network with real seismic samples. We use a random sample consensus (RANSAC) method to obtain real seismic samples and generate corresponding labels automatically. Three real 3D examples are included to demonstrate that the fault detection accuracy of the pre-trained network models can be greatly improved by retraining the network with a few amount of real seismic samples.