Due to the non-stationary characteristics of vibration signals acquired from rolling element bearing fault, thc time-frequency analysis is often applied to describe the local information of these unstable signals smar...Due to the non-stationary characteristics of vibration signals acquired from rolling element bearing fault, thc time-frequency analysis is often applied to describe the local information of these unstable signals smartly. However, it is difficult to classitythe high dimensional feature matrix directly because of too large dimensions for many classifiers. This paper combines the concepts of time-frequency distribution（TFD） with non-negative matrix factorization（NMF）, and proposes a novel TFD matrix factorization method to enhance representation and identification of bearing fault. Throughout this method, the TFD of a vibration signal is firstly accomplished to describe the localized faults with short-time Fourier transform（STFT）. Then, the supervised NMF mapping is adopted to extract the fault features from TFD. Meanwhile, the fault samples can be clustered and recognized automatically by using the clustering property of NMF. The proposed method takes advantages of the NMF in the parts-based representation and the adaptive clustering. The localized fault features of interest can be extracted as well. To evaluate the performance of the proposed method, the 9 kinds of the bearing fault on a test bench is performed. The proposed method can effectively identify the fault severity and different fault types. Moreover, in comparison with the artificial neural network（ANN）, NMF yields 99.3% mean accuracy which is much superior to ANN. This research presents a simple and practical resolution for the fault diagnosis problem of rolling element bearing in high dimensional feature space.展开更多
With the new system radar put into practical use, the characteristics of complex radar signals are changing and developing. The traditional analysis method of one-dimensional transformation domain is no longer applica...With the new system radar put into practical use, the characteristics of complex radar signals are changing and developing. The traditional analysis method of one-dimensional transformation domain is no longer applicable to the modern radar signal processing, and it is necessary to seek new methods in the two-dimensional transformation domain. The time-frequency analysis method is the most widely used method in the two-dimensional transformation domain. In this paper, two typical time-frequency analysis methods of short-time Fourier transform and Wigner-Ville distribution are studied by analyzing the time-frequency transform of typical radar reconnaissance linear frequency modulation signal, aiming at the problem of low accuracy and sen-sitivity to the signal noise of common methods, the improved wavelet transform algorithm was proposed.展开更多
The mold friction(MDF)is an important parameter reflecting the lubrication between the mold and slab quantitatively.The mold/slab friction was detected using an online monitoring system on a slab continuous caster equ...The mold friction(MDF)is an important parameter reflecting the lubrication between the mold and slab quantitatively.The mold/slab friction was detected using an online monitoring system on a slab continuous caster equipped with hydraulic oscillators.Wavelet entropy theory was introduced to describe the fluctuation characteristics of the MDF signal in order to quantitatively estimate the mold/slab lubrication.Furthermore,MDF signal and its wavelet entropy were analyzed under typical casting conditions,such as normal casting,different models(to control the relationship among the amplitude,the frequency and the casting speed),changing casting speeds and breakout.The results showed that the wavelet entropy could accurately reflect the overall changing trend of the mold friction as well as the local variation features.Besides,the wavelet entropy of the hydraulic cylinder force and the MDF was compared and analyzed,and the relationship between them was further discussed.展开更多
基金Supported by Shaanxi Provincial Overall Innovation Project of Science and Technology,China(Grant No.2013KTCQ01-06)
文摘Due to the non-stationary characteristics of vibration signals acquired from rolling element bearing fault, thc time-frequency analysis is often applied to describe the local information of these unstable signals smartly. However, it is difficult to classitythe high dimensional feature matrix directly because of too large dimensions for many classifiers. This paper combines the concepts of time-frequency distribution（TFD） with non-negative matrix factorization（NMF）, and proposes a novel TFD matrix factorization method to enhance representation and identification of bearing fault. Throughout this method, the TFD of a vibration signal is firstly accomplished to describe the localized faults with short-time Fourier transform（STFT）. Then, the supervised NMF mapping is adopted to extract the fault features from TFD. Meanwhile, the fault samples can be clustered and recognized automatically by using the clustering property of NMF. The proposed method takes advantages of the NMF in the parts-based representation and the adaptive clustering. The localized fault features of interest can be extracted as well. To evaluate the performance of the proposed method, the 9 kinds of the bearing fault on a test bench is performed. The proposed method can effectively identify the fault severity and different fault types. Moreover, in comparison with the artificial neural network（ANN）, NMF yields 99.3% mean accuracy which is much superior to ANN. This research presents a simple and practical resolution for the fault diagnosis problem of rolling element bearing in high dimensional feature space.
文摘With the new system radar put into practical use, the characteristics of complex radar signals are changing and developing. The traditional analysis method of one-dimensional transformation domain is no longer applicable to the modern radar signal processing, and it is necessary to seek new methods in the two-dimensional transformation domain. The time-frequency analysis method is the most widely used method in the two-dimensional transformation domain. In this paper, two typical time-frequency analysis methods of short-time Fourier transform and Wigner-Ville distribution are studied by analyzing the time-frequency transform of typical radar reconnaissance linear frequency modulation signal, aiming at the problem of low accuracy and sen-sitivity to the signal noise of common methods, the improved wavelet transform algorithm was proposed.
基金The project was supported by the National Natural Science Foundation of China(No.51204063)the Anhui Provincial Natural Science Foundation(No.1308085QE72).
文摘The mold friction(MDF)is an important parameter reflecting the lubrication between the mold and slab quantitatively.The mold/slab friction was detected using an online monitoring system on a slab continuous caster equipped with hydraulic oscillators.Wavelet entropy theory was introduced to describe the fluctuation characteristics of the MDF signal in order to quantitatively estimate the mold/slab lubrication.Furthermore,MDF signal and its wavelet entropy were analyzed under typical casting conditions,such as normal casting,different models(to control the relationship among the amplitude,the frequency and the casting speed),changing casting speeds and breakout.The results showed that the wavelet entropy could accurately reflect the overall changing trend of the mold friction as well as the local variation features.Besides,the wavelet entropy of the hydraulic cylinder force and the MDF was compared and analyzed,and the relationship between them was further discussed.
