KEYWORDS: Data modeling, Wind turbine technology, Neural networks, Performance modeling, Feature extraction, Education and training, Process modeling, Data storage, Convolutional neural networks, Data acquisition
Temperature, as an important indicator in wind turbine condition monitoring, can reflect the working state of bearing promptly and intuitively. To enhance feature extraction capability and temperature prediction accuracy, a multi-channel parallel deep residual neural network is proposed. The model consists of a parallel network composed of Deep Separable Convolutional Neural Network (DSCNN) and Bidirectional Long Short-Term Memory (BiLSTM), enabling the model to extract spatial and temporal features effectively. Additionally, the residual connections are employed to avoid the gradient vanishing problem that may occur with increased model depth, significantly improving feature extraction capability and temperature prediction performance. To validate the effectiveness of the proposed model, a comparative experiment was conducted, and compared with four comparison models, the method described in this paper achieves higher model prediction accuracy.
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.