A novel transfer-learning method based on selective normalization for fault diagnosis with limited labeled data
Sign Up to like & getrecommendations! Published in 2021 at "Measurement Science and Technology"
DOI: 10.1088/1361-6501/ac03e5
Abstract: The application of deep learning to fault diagnosis has made encouraging progress in recent years. However, it is hard to obtain sufficient labeled data to ensure the performance of diagnostic models, due to complex and… read more here.
Keywords: fault; fault diagnosis; normalization; novel transfer ... See more keywords