No abstract

Remaining useful life (RUL) prediction, as an essential task for prediction and health management (PHM), can improve the reliability of degradation systems. In this paper, multi-dimensional mechanical monitoring readings are treated as natural language sequences and inputted to a natural language processing (NLP) model, Transformer, to extract semantic compression vectors. The health indicators (HI) are constructed from the changes of compressed semantic vectors during the mechanical system operation, reflecting the mechanical health status at each monitoring point. Subsequently, combined with the similarity matching method, the RUL prediction is achieved by weighted summation. Transformer mainly consists of attention layers and residual connection layers, which contain no recurrence and convolution. The attention layer can highlight the critical time step information during the HI construction. Moreover, the output of different time steps can be obtained simultaneously in a parallel computation manner. The proposed scheme is experimentally compared on two publicly available datasets and achieves competitive prediction performance

No abstract

Objective. To explore the mechanism of Shaoyao Gancao decoction (SGD) in treatment of alopecia areata (AA) by network pharmacology and animal experiments. Methods Based on the traditional Chinese medicine systems pharmacology database and analysis platform (TCMSP), the components and targets of SGD were determined. Then, the related targets of AA were retrieved from DrugBank, GeneCards, OMIM, and DisGeNET databases. The intersection of drug targets and disease targets was determined, and the key targets of the protein-protein interaction network were obtained with the String database. Gene Ontology (GO) biological process enrichment analysis and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analysis of potential key targets were carried out using the DAVID database using AutoDock for molecular docking verification. Finally, the key pathway was validated by animal experiments. Results. A total of 102 active components, 212 predicted targets, and 812 AA disease-related targets were obtained. Topological analysis yielded 45 key targets of SGD in the treatment of AA, including IL-6, PTGS2, TNF, VEGFA, CCL2, IL-1B, CXCL8, CASP3, MPO, and IL-10. There were 324 GO entries obtained through GO biological process enrichment analysis, and 20 pathways were obtained through KEGG pathway enrichment analysis, involving the PI3K-Akt signaling pathway, osteoclast differentiation, and Jak-STAT signaling pathway. The molecular docking results showed effective ingredients (quercetin, kaempferol, and 7-methoxy-2-methyl isoflavone) have good docking results with targets (IL-6, PTGS2, and TNF). The results of animal experiments showed that SGD can effectively upregulate the expression of PI3K and AKT proteins. Conclusion. This is the first in-depth study on the mechanism of SGD’s treatment effect in AA using network pharmacology, and preliminary animal experiments verified that it is closely related to the PI3K/AKT signaling pathway. This finding may provide a new basis for SGD’s clinical application in AA.