KEYWORDS: Data modeling, Education and training, Statistical modeling, Mathematical optimization, Engineering, Process modeling, Machine learning, Statistical analysis, Power grids, Lithium
Because the deep learning model is highly dependent on data, and the extraction effect of data sample features will directly affect the prediction accuracy. Based on this, in order to improve the accuracy of short-term power load forecasting, a load forecasting method based on time series generation antagonism network TimeGAN and short-term memory network LSTM is proposed for data enhancement. First, in order to optimize the effect of model feature extraction, the sample six-dimensional feature data is reconstructed into nine-dimensional feature data according to the date and weather characteristics. Then, analyze the correlation between historical data and sample distance, use TimeGAN model to enhance the data, and then reconstruct the data set. Finally, the prediction model of long and short-term memory network is created to import the reconstructed data to predict the electric load in the next 24 hours. The experimental results show that this method is superior to the prediction methods of CNN-LSTM, CNN-BiLSTM and LSTM models, and TimeGan-LSTM has higher prediction accuracy.
As the scale of the transmission system continues to expand, the structure and fault characteristics of the grid become more and more complex, and the existing fault diagnosis methods have difficulty in extracting the fault characteristics accurately in the face of the complex grid. A convolutional neural network (CNN) based fault diagnosis method is proposed. Firstly, the network structure is tested step by step through layer-by-layer filtering and layer-by-layer incremental stacking, with the aim of building a network structure fully adapted to grid fault diagnosis; then the training parameters are adjusted by optimization strategies; finally, an AC transmission system model is built on the MATLAB/SIMULINK platform, and the diagnostic effect is demonstrated by combining the network with the fault diagnosis. It is proved that this method has a high diagnostic accuracy and also reduces the number of fault samples, which is more in line with the practical needs.
KEYWORDS: Data modeling, Convolution, Statistical modeling, Teeth, Signal processing, 3D modeling, Data conversion, Convolutional neural networks, Neural networks, Gallium nitride
The existing gearbox fault diagnosis models often need a lot of fault data and corresponding tags to complete the model training, but the actual fault data is often less and unevenly distributed. Aiming at the situation that the gearbox fault data is scarce and unevenly distributed, this paper proposes a fault diagnosis method based on the Deep Convolution Generative Adversarial Network (DCGAN). First, the original vibration signals collected in the early stage are processed through data processing to form a sample data set and input into the DCGAN model for confrontation training, and virtual samples with real sample characteristics are generated to expand the sample data set. Then, the convolution neural network model is constructed to complete the fault diagnosis and get the results. The results show that the model trained by this method is more accurate when generating a large amount of data, and the diagnostic effect is significantly better.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.