Fault diagnosis of rolling bearings is of great significance to ensure the production efficiency of rotating machinery as well as personal safety. In recent years, machine learning has shown great potential in signal feature extraction and pattern recognition, and it is superior to traditional fault diagnosis methods in dealing with big data. However, most of the current intelligent diagnostic methods are based on the ideal conditions that bearing data set and label information are sufficient, which are often not always available in engineering practice. In response to this problem, this paper proposes to use probabilistic mixture model (PMM) to approximate the data distribution of the bearing signal, and then use Markov Chain Monte Carlo (MCMC) algorithm to sample the probabilistic model to expand the fault data set. In addition, Semi-supervised Ladder Network (SSLN) can achieve the effect of supervised learning classifier with only a few labeled samples. Based on Case Western Reserve University (CWRU) Bearing Database, the recognition accuracy of the proposed PMM-SSLN model can reach 99.5%, and the experimental results show that this model is applicable to the case where both bearing data set and label information are insufficient.
Earthquake disaster assessment is one of the most critical aspects in reducing earthquake disaster losses. However, traditional seismic intensity assessment methods are not effective in disaster-stricken areas with insufficient observation data. Social media data contain a large amount of disaster information with the advantages of timeliness and multiple temporal-spatial scales, opening up a new channel for seismic intensity assessment. Based on the earthquake disaster information on the microblog platform obtained by the network technique, a multi-model coupled seismic intensity assessment method is proposed, which is based on the BERT-TextCNN model, constrained by the seismaesthesia intensity attenuation model, and supplemented by the method of ellipse-fitting inverse distance interpolation. Taking four earthquakes in Sichuan Province as examples, the earthquake intensity was evaluated in the affected areas from the perspective of seismaesthesia. The results show that (1) the microblog data contain a large amount of earthquake information, which can help identify the approximate scope of the disaster area; (2) the influences of the subjectivity and uneven spatial distribution of microblog data on the seismic intensity assessment can be reduced by using the seismaesthesia intensity attenuation model and the method of ellipse-fitting inverse distance interpolation; and (3) the accuracy of seismic intensity assessment based on the coupled model is 70.81%. Thus, the model has higher accuracy and universality. It can be used to assess seismic intensity in multiple regions and assist in the formulation of earthquake relief plans.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.