In view of the problem that the generalization ability of traditional data-driven fault diagnosis model declines or even fails in mechanical system diagnosis, a fault diagnosis method based on multi-scale transfer symbolic dynamic entropy and support vector machine is proposed based on the idea of ...
In the forward training stage of DBN, the greedy unsupervised learning mechanism is employed for bottom-to-top transfer, and the feature extraction of the rolling mill bearing vibration data is finally completed. After the unsupervised training, the BP algorithm is employed. The objective of back-...
Visualization results of t-SNE in four model tests (for comparison with the proposed model). As shown in Figure 15, to test the generalization performance of the model proposed in this study, this paper conducted a cross-dataset test, using the same amount of data from the real dataset of...