Hidden Markov Models based intelligent health assessment and fault diagnosis of rolling element bearings.

Hidden Markov Models (HMMs) have become an immensely popular tool for health assessment and fault diagnosis of rolling element bearings. The advantages of an HMM include its simplicity, robustness, and interpretability, while the generalization capability of the model still needs to be enhanced. The Dempster-Shafer theory of evidence can be used to conduct a comprehensive evaluation, and Stacking provides a novel training strategy. Therefore, the HMM-based fusion method and ensemble learning method are proposed to increase the credibility of quantitative analysis and optimize classifiers respectively. Firstly, vibration signals captured from bearings are decomposed into intrinsic mode functions (IMFs) using ensemble empirical mode decomposition (EEMD), and then the Hilbert envelope spectra of main components are obtained; Secondly, multi-domain features are extracted as model input from preprocessed signals; Finally, HMM-based intelligent health assessment framework and fault diagnosis framework are established. In this work, the life cycle health assessment modeling is performed using a few training samples, the bearing degradation state is quantitatively evaluated, normal and abnormal samples are effectively distinguished, and the accuracy of fault diagnosis is significantly improved.

Construction and characterization of a full-thickness skin model with collagen matrix / 中华皮肤科杂志

Objective To construct a collagen matrix-based skin model that can last a long time in vitro for potential application of subsequent tests and studies.Methods The porcine collagen and normal human skin fibroblasts were mixed and seeded into the culture dish,which were cultured for 3-4 days to obtain a dermal structure.Then,the third-to seventh-passage normal human keratinocytes were seeded onto the dermal surface and cultured for 14 days to obtain a double-layer skin model.Hematoxylin and eosin (HE)staining and Masson staining were performed to evaluate the morphology and structure of the skin model,and electron microscopy was conducted to observe the ultrastructure of the skin model.Immunohistochemical study and immunofluorescence staining were conducted to determine the expression of major markers in each layer of the skin model.Results HE and Masson staining showed that the skin model and normal human skin tissues showed very similar dermal and epidermal structures.After harvest of the skin model,it can be cultured in vitro for another 14 days with favorable and stable dermal and epidermal structures.Electron microscopy showed lipids in the stratum corneum,keratohyalin granules in the stratum granulosum,corneodesmosomes,desmosomes and basal membrane in the skin model.Immunohistochemical and immunofluorescence staining showed the consistent expression of transglutaminase,filaggrin,keratin 10 and Ki67 in the epidermis in both the skin model and normal skin.Moreover,the expression of type Ⅳ collagen and laminin-5 in the basal membrane,as well as that of type Ⅰ collagen,type Ⅲ collagen and fibrillin in the dermis were both consistent between the skin model and normal skin.Conclusion The constructed three-dimensional (3D) skin model is highly analogous to normal human skin in the aspect of tissue structure and various protein expression,and the skin model can be stably cultured in vitro for at least 14 days after harvest.