Mechanical fault diagnosis is an important method to accurately identify the health condition of mechanical equipment and ensure its safe operation. With the advent of the era of "big data", it is an inevitable trend to choose deep learning for mechanical fault diagnosis. At the same time, to improve the generalization ability of deep learning applications in different scenarios of fault diagnosis, mechanical diagnosis based on transfer learning has also been proposed and become an important branch in the field of mechanical fault diagnosis. This paper introduces the principle of transfer learning, summarizes the research and application of transfer learning in the field of fault diagnosis, discusses the shortcomings of transfer learning in the field of fault diagnosis, and discusses the future research direction of transfer learning in the field of fault diagnosis.

No abstract

No abstract

The ultra-thick wall steel pipes are very likely to have quality defects in stretch-reduction hot rolling process, and it is preferred to study these defects by simulation methods. However, traditional FEM often has the problems of convergency difficulty and time consuming for solving complex large deformation problems. Therefore, in this study, a mixed explicit-implicit FEM, was adopted for solving the thermo-mechanical coupled process of the stretch-reduction hot rolling. Multidimensional heat transfer as well as mechanical boundary conditions were acted simultaneously, and the accuracy of the model was validated by industrial experiments. Results showed that the simulation results are very consistent with the actual rolling results. Three typical rolling defects were accurately predicted, i.e., inner hexagon, thickened ends and linear mark. Besides, it is discovered that the uneven distributions of stress, strain and temperature are important causes for the rolling defects, and these influences are also presented and discussed. This paper presents an efficient and precise numerical modelling method so as to provide theoretical guidance for the production of ultra-thick wall pipes.