Open AccessRecognition method of voltage sag causes based on two‐dimensional transform and deep learning hybrid model
Author(s) -
Zheng Zhicong,
Qi Linhai,
Wang Hong,
Pan Aiqiang,
Zhou Jian
Publication year - 2020
Publication title -
iet power electronics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.637
H-Index - 77
eISSN - 1755-4543
pISSN - 1755-4535
DOI - 10.1049/iet-pel.2019.0593
Subject(s) - computer science , artificial intelligence , deep learning , voltage sag , convolutional neural network , deep belief network , noise (video) , artificial neural network , pattern recognition (psychology) , noise reduction , grid , smart grid , machine learning , electric power system , power (physics) , engineering , electrical engineering , physics , geometry , mathematics , quantum mechanics , image (mathematics)
The voltage sags’ caused recognition is the basis for formulating governance plans and clarifying liabilities for accidents. The diversification of smart grid equipment, the grid‐connected power generation of new energy sources and the regional differentiation of power consumption modes pose new challenges to the traditional methods. In this study, a method based on deep learning hybrid model is proposed. The convolutional neural network is used to flexibly receive the voltage after two‐dimensional transformation, so as to automatically obtain the time series and spatial characteristics of the voltage sag signals. The deep belief network is used to replace the fully connected layers in convolutional neural network, thereby enhancing the multi‐label classification ability of the model. The parameters obtained by the unsupervised training of the stacked sparse denoising auto‐encoder are used to initialise the weight of deep belief network, thereby improving the convergence speed and the anti‐noise performance of the model. Iterative training and repeated testing of the network using pre‐processed simulation data and actual recorded data verify the high recognition accuracy and strong anti‐noise performance of the hybrid model. Compared with the traditional methods, the hybrid model also has good generalisation ability and can be effectively applied in practical engineering.