In the field of intelligent fault diagnosis, distribution divergence always exists between the training and testing sets (which could be considered as a source domain with known labels and a target domain without labels), which will lead to a significant degradation in the diagnosis performance of deep network. Generally, this problem is solved by transfer learning. Specifically, adapt the marginal distribution or jointly align the marginal and conditional distributions of two domains so that the classifier trained by labeled source data merely can correctly classify target data. However, when aligning the marginal and conditional distributions simultaneously, people usually gives them the equal weight while it is not in accordance with the general situations. In this paper, we propose a new framework called normalized recurrent dynamic adaption network (NRDAN) for intelligent fault diagnosis which not only adapts the marginal and conditional distributions of two domains simultaneously but also estimates the relative importance of two distributions dynamically and quantitatively. This framework adopts long short-term memory (LSTM) as the base network combined with layer normalization (LN) and mainly consists of a feature extractor, a dynamic adaption module, and a classifier. Finally, extensive experiments including transfer tasks between not only various operating conditions but also different machines are conducted to comprehensively evaluate the proposed method. INDEX TERMS Intelligent fault diagnosis, deep learning, transfer learning, dynamic adaption, long short-term memory.

Purpose This work aims to demonstrate the vibration suppression of the rotor system with localized defects on bearing using an integral squeeze film damper (ISFD). Design/methodology/approach Experiments were carried out to study the vibration characteristics of the rotor system with ISFD mounted on fault deep groove ball bearings. Three fault bearings including bearing with outer race defect, inner race defect and ball defect have been used in this paper. The results were compared by use of vibration acceleration level, continuous wavelet transform and envelope spectrum. Findings It was found that ISFD shows excellent damping and vibration attenuation characteristics of the rotor system with defective bearing. The fault bearing rotor system with external ISFD considerably reduces the vibration energy and amplitude compared with the system without ISFD. Originality/value There is a dearth of experimental research pertaining to vibration characteristics of rotor system support by defective bearings with ISFD. Besides, the test provides evidence for the application of ISFD in vibration control of the rotor system with incipient defects on bearing. Peer review The peer review history for this article is available at: https://publons.com/publon/10.1108/ILT-04-2020-0144/

No abstract