The embodiment of the present application provides a kind of shear wave
time difference prediction method and device, belong to
petroleum exploration development technical field.The method comprises: obtaining
well logging sample data as the training
data set of prediction model;The training
data set is preprocessed, data screening is carried out based on importance analysis, data grouping is carried out based on kurtosis and skewness, and the processed training
data set is obtained;The processed training data set is input into the neural network of CNN and LSTM
hybrid building respectively for training, and the shear wave
time difference prediction model is obtained;Obtain the
well logging data of the shear wave
time difference to be predicted;The
well logging data is preprocessed, well
logging data grouping is carried out based on kurtosis and skewness, and the processed well
logging data is obtained;The processed well
logging data is respectively input into the shear wave time difference prediction model, and the shear wave time difference is obtained.The shear wave time difference prediction method and device of the present application have the advantages of high
processing efficiency, high prediction accuracy and strong regional applicability.