Henan Normal University

About: Henan Normal University is a education organization based out in Xinxiang, China. It is known for research contribution in the topics: Catalysis & Ionic liquid. The organization has 10863 authors who have published 11077 publications receiving 166773 citations.

Predicting Remaining Useful Life of Rolling Bearings Based on Deep Feature Representation and Transfer Learning

Abstract: For the data-driven remaining useful life (RUL) prediction for rolling bearings, the traditional machine learning-based methods generally provide insufficient feature representation and adaptive extraction. Although deep learning-based RUL prediction methods can solve these problems to some extent, they still do not yield satisfactory predictive results due to less degradation data and inconsistent data distribution among different bearings. To solve these problems, a new RUL prediction method based on deep feature representation and transfer learning is proposed in this paper. This method includes an off-line stage and an online stage. In the off-line stage, the Hilbert–Huang transform marginal spectra of the raw vibration signal of auxiliary bearings are first calculated as the input, and then contractive denoising autoencoder is introduced to extract deep features with good and stable fault representation. Second, by using the obtained deep features and Pearson’s correlation coefficient, a new health condition assessment method is proposed to divide the whole life of each bearing into a normal state and a fast-degradation state. Finally, using the extracted deep features and their RUL values, an RUL prediction model for the fast-degradation state is trained by means of a least-square support vector machine. In the online stage, a kind of transfer learning algorithm, i.e., transfer component analysis, is introduced to sequentially adjust the features of target bearing from auxiliary bearings, and then the corresponding RUL is predicted using the corrected features. Results using the PHM Challenging 2012 data set show a significant performance improvement when using the proposed method in terms of predictive accuracy and numerical stability.

Precise Measurement of the e+e- →π+π-J /ψ Cross Section at Center-of-Mass Energies from 3.77 to 4.60 GeV

Abstract: The cross section for the process e(+)e(-)-> pi(+) pi(-) J/psi is measured precisely at center-of-mass energies from 3.77 to 4.60 GeV using 9 fb(-1) of data collected with the BESIII detector operating at the BEPCII storage ring. Two resonant structures are observed in a fit to the cross section. The first resonance has a mass of (222.0 +/- 3.1 +/- 1.4) MeV/ c(2) and a width of (44.1 +/- 4.3 +/- 2.0)MeV, while the second one has a mass of (4320.0 +/- 10.4 +/- 7.0)MeV/c(2) and a width of (101.4(- 19.7)(+25.3) +/- 10.2) MeV, where the first errors are statistical and second ones are systematic. The first resonance agrees with the Y(4260) resonance reported by previous experiments. The precision of its resonant parameters is improved significantly. The second resonance is observed in e(+)e(-)-> pi(+) pi(-) J/psi for the first time. The statistical significance of this resonance is estimated to be larger than 7.6 sigma. The mass and width of the second resonance agree with the Y(4360) resonance reported by the BABAR and Belle experiments within errors. Finally, the Y(4008) resonance previously observed by the Belle experiment is not confirmed in the description of the BESIII data.