The parametric fault diagnosis of analog circuits is very crucial for condition-based maintenance (CBM) in prognosis and health management. In order to improve the diagnostic rate of parametric faults in engineering applications, a semi-supervised machine learning algorithm was used to classify the parametric fault. A lifting wavelet transform was used to extract fault features, a local preserving mapping algorithm was adopted to optimize the Fisher linear discriminant analysis, and a semi-supervised cooperative training algorithm was utilized for fault classification. In the proposed method, the fault values were randomly selected as training samples in a range of parametric fault intervals, for both optimizing the generalization of the model and improving the fault diagnosis rate. Furthermore, after semi-supervised dimensionality reduction and semi-supervised classification were applied, the diagnosis rate was slightly higher than the existing training model by fixing the value of the analyzed component.

Grain boundaries are thought to be the primary demagnetization sites of precipitate-hardening 2:17-type Sm-Co-Fe-Cu-Zr permanent magnets with a unique cellular nanostructure, leading to a poor squareness factor as well as a much lower than ideal energy product. In this work, we investigated the grain boundary microstructure evolution of a model magnet Sm₂₅Co_46.9Fe_19.5Cu_5.6Zr_3.0 (wt. %) during the aging process. The transmission electron microscopy (TEM) investigations showed that the grain boundary region contains undecomposed 2:17H, partially ordered 2:17R, 1:5H nano-precipitates, and a Sm_n+1Co_5n−1 (n = 2, 1:3R; n = 3, 2:7R; n = 4, 5:19R) phase mixture at the solution-treated state. After short-term aging, further decomposition of 2:17H occurs, characterized by the gradual ordering of 2:17R, the precipitation of the 1:5H phase, and the gradual growth of Sm_n+1Co_5n−1 compounds. Due to the lack of a defect-aggregated cell boundary near the grain boundary, the 1:5H precipitates are constrained between the 2:17R and the Sm_n+1Co_5n−1 nano-sheets. When further aging the magnet, the grain boundary 1:5H precipitates transform into Sm_n+1Co_5n−1 compounds. As the Sm_n+1Co_5n−1 compounds are magnetically softer than the 1:5H precipitates, the grain boundaries then act as the primary demagnetization sites. Our work adds important insights toward the understanding of the grain boundary effect of 2:17-type Sm-Co-Fe-Cu-Zr magnets.