I am developing an LSTM model to predict the force-deformation response for wind turbine blades. I have generated the training data from a high-fidelity model for wind speeds ranging from 3m/s to 25m/s. Naturally, the input feature has varying mean values, and so does the output. I can normalize the input features while training the LSTM model by including the layerNormalization functionality in Matlab but this won't allow me to normalize the output time history. Due to this, the predicted output has a constant mean. How do I get around this?



Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Browse other questions tagged or ask your own question.