Resource Type

Journal Article 3

Year

2021 1

2017 1

2011 1

Keywords

feature extraction 1

heavy tailed distribution 1

kurtosis 1

normal cloud model 1

normal distribution 1

planet gear fault 1

spectral kurtosis 1

time wavelet energy spectrum 1

wind turbine 1

open ︾

Search scope:

排序： Display mode:

Fault feature extraction of planet gear in wind turbine gearbox based on spectral kurtosis and time wavelet

Yun KONG, Tianyang WANG, Zheng LI, Fulei CHU

Frontiers of Mechanical Engineering 2017, Volume 12, Issue 3,   Pages 406-419 doi: 10.1007/s11465-017-0419-0

Abstract: feature of planet gear effectively, we propose a novel feature extraction method based on spectral kurtosisFirstly, the spectral kurtosis (SK) and kurtogram of raw vibration signals are computed and exploited

Keywords： wind turbine     planet gear fault     feature extraction     spectral kurtosis     time wavelet energy spectrum    

HTML PDF Collect

Proof of the heavy tailed property of normal cloud model

Li Deyi,Liu Changyu,Gan Wenyan

Strategic Study of CAE 2011, Volume 13, Issue 4,   Pages 20-23

Abstract:

Normal distribution and heavy tailed distribution are very important in probability theories. They have totally different mathematical forms and physical meanings. The probability density function of normal distribution decay exponentially to 0. The majority of normal random variable values are around the mathematical expectation. The tailed distribution function of the random variables that obey heavy tailed distribution shows heavy tailed characteristic. The probability density function decays power exponentially to 0.In this paper, we proved that the normal cloud model is heavy tailed distribution and its mathematical expectation exists.It is intermediate between notmal distribution and heavy tailed distribution. The parameter He(hyper entropy) of the normal cloud model is the bridge from normal distribution to heavy tailed distribution.

Keywords： normal distribution     heavy tailed distribution     normal cloud model     kurtosis    

HTML PDF Collect

No-reference noisy image quality assessment incorporating features of entropy, gradient, and kurtosis Research Article

Heng Yao, Ben Ma, Mian Zou, Dong Xu, Jincao Yao,hyao@usst.edu.cn,xudong@zjcc.org.cn,yaojc@zjcc.org.cn

Frontiers of Information Technology & Electronic Engineering 2021, Volume 22, Issue 12,   Pages 1551-1684 doi: 10.1631/FITEE.2000716

Abstract: Noise is the most common type of image distortion affecting human visual perception. In this paper, we propose a no-reference image quality assessment (IQA) method for noisy images incorporating the features of entropy, gradient, and . Specifically, image is conducted in the discrete cosine transform domain based on skewness invariance. In the principal component analysis domain, feature is obtained by statistically counting the significant differences between images with and without noise. In addition, both the consistency between the entropy and features and the subjective scores are improved by combining them with the gradient coefficient. is applied to map all extracted features into an integrated scoring system. The proposed method is evaluated in three mainstream databases (i.e., LIVE, TID2013, and CSIQ), and the results demonstrate the superiority of the proposed method according to the Pearson linear correlation coefficient which is the most significant indicator in IQA.

Keywords： 噪声图像质量评价；噪声估计；峰度；人类视觉系统；支持向量回归    

HTML PDF Collect

Title Author Date Type Operation

Fault feature extraction of planet gear in wind turbine gearbox based on spectral kurtosis and time wavelet

Yun KONG, Tianyang WANG, Zheng LI, Fulei CHU

Journal Article

Proof of the heavy tailed property of normal cloud model

Li Deyi,Liu Changyu,Gan Wenyan

Journal Article

No-reference noisy image quality assessment incorporating features of entropy, gradient, and kurtosis

Heng Yao, Ben Ma, Mian Zou, Dong Xu, Jincao Yao,hyao@usst.edu.cn,xudong@zjcc.org.cn,yaojc@zjcc.org.cn

Journal Article