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.
In recent years, the power quality problem has become more complicated in power grids because of the extensive usage of power electronics and multisource multitransformation features. The method, based on physical characteristics such as time domain, frequency domain and transform domain, is facing challenges in terms of adaptability, algorithm efficiency and accuracy for the recognition of complex disturbance recognition. The bidirectional long short-term memory network is an algorithm in deep learning. It is based on data for characterization learning, which can effectively overcome the problem of information loss and generalization ability of physical methods. Moreover, it has the characteristics of memory, which can simultaneously consider historical information and future information and can better learn data features with time series characteristics. Aiming at the transient voltage sag time series data, this paper proposes a recognition method of the voltage sag causes based on the bidirectional long short-term memory network's extraction eigenvalue, the full-connection layer's high-dimensional feature extraction and the Softmax network layer's classification. The experiment uses simulation data and measured data to prove that the model has good recognition ability and good antinoise performance in the recognition of voltage sag causes and can be reliably applied in practical engineering.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.