YU XIN

Dr. YU XIN

orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
14 December 2018 in Measurement Science and Technology
Verified
Journal Article
Closed access
PDF file
JWJinrui Wang
Jinrui Wang
Shunming LiShunming Li
Shunming Li
BHBaokun Han
Baokun Han
ZAZenghui An
Zenghui An
YXYU XIN
YU XIN
QWQijun Wu
Qijun Wu
Among various fault diagnosis methods, deep learning has shown state-of-the-art performance in processing mechanical big data. This paper investigates a reliable deep learning method known as autoencoder, which is most suitable for automatic feature extraction of fault signals. However, traditional autoencoders have two deficiencies: (1) the multi-layer structure of autoencoder has an internal covariate shift problem, which will cause great difficulty for the network training. (2) The application of autoencoder in the case of rotating speed fluctuation is not mature. To overcome the aforementioned deficiencies, batch normalization strategy is employed in every layer of the autoencoder network to obtain a steady distribution of activation values during training. It can regularize the network without parameter adjustment, and deal with the speed fluctuation problem perfectly. So, a new network named batch-normalized autoencoder is first proposed for intelligent fault diagnosis. The raw vibration signals are directly fed into the network and the extracted features are employed to train a softmax classifier for health state identification. A bearing and a gearbox data set are finally used to confirm the effectiveness of the proposed method. The results manifest that the proposed method can extract salient features from the raw signals and handle the fault diagnosis problem under the speed fluctuation problem.

20 September 2019 in Measurement Science and Technology
Verified
Journal Article
Closed access
PDF file
ZAZenghui An
Zenghui An
Shunming LiShunming Li
Shunming Li
YXYU XIN
YU XIN
KXKun Xu
Kun Xu
HMHuijie Ma
Huijie Ma
As fault diagnosis for motor drive systems enters the era of big data, intelligent fault diagnosis methods exhibit excellent performance because of their learning capabilities. However, the existing methods are strict with the signal size, which reduces the performance of these methods for modern condition monitoring. Besides, most existing intelligent methods have a great limitation: the training data and testing data are under the same working conditions. To overcome these limitations, we propose a novel three-layer model inspired by a recurrent neural network (RNN) and transfer learning, which has the ability to process variable size sequences under different working conditions. In the first layer, the input unit is extended to ensure that there is adequate dimension to store the information of sequences. In the second layer, the main information of the whole sequence is stored, transmitted, transformed and output by gates. In the final layer, softmax is employed to classify the health conditions based on the output of the RNN with a long short-term memory cell. The classification loss based on the whole framework and the domain loss using kernel method are proposed to train the model. Furthermore, a bearing dataset is adopted to verify the effectiveness of the proposed method. The experimental results show that the proposed method can not only break the limitations of existing methods, but also achieve a superior performance compared with related methods.

26 February 2020 in Measurement Science and Technology
Verified
Journal Article
Open access
PDF file
ZZZongzhen Zhang
Zongzhen Zhang
SLShunming Li
Shunming Li
YXYU XIN
YU XIN
HMHuijie Ma
Huijie Ma
The compound fault diagnosis of gearboxes, which can prevent breakdown accidents and minimize production loss, has become a challenging hotspot. In practical applications, the early fault signal is weak and often concealed by environmental noise. Therefore, separating the different fault components from signals with weak faults and strong noise is the key to performing compound fault diagnosis. In this paper, a novel compound fault diagnosis method based on intrinsic component filtering is proposed for compound fault diagnosis, which can also be regarded as a multi-dimension blind deconvolution method. Firstly, a Hankel matrix is constructed from the collected vibration data. Secondly, the filter matrix is trained by intrinsic component filtering in an unsupervised way without any time-consuming preprocessing or a prior basis. Finally, Hilbert demodulation analysis is conducted on the filtered data. Different fault components can be diagnosed according to the envelope spectra of the fault components. The separation performance of the proposed method is validated by the simulation data and the experiment signals in a noisy environment. The results show that the proposed method can train the different filters using the compound fault adaptively, demonstrating superior performance to existing methods.

1 June 2020 in IET Science, Measurement & Technology
Verified
Journal Article
Open access
PDF file
YXYU XIN
YU XIN
SLShunming Li
Shunming Li
JWJinrui Wang
Jinrui Wang
ZAZenghui An
Zenghui An
WZWei Zhang
Wei Zhang
Traditional labour‐intensive methods always suffer from time and frequency blurring and cross‐term interference when detecting fault features from vibration signals and their time–frequency representation. Such methods need essential expertise and prior knowledge to identify features. Intelligent fault diagnosis methods based on deep learning have attracted great attention because of their ability to automatically learn the representative features in fault diagnosis. Therefore, a novel multi‐object deep convolutional neural network (CNN) is proposed to diagnose the faults. In this method, time domain, frequency domain, and time–frequency data are organised as the hybrid multi‐object input to avoid the shortcoming of the single type of data, which cannot reveal abundant information about amplitude and frequency in vibration signals. Deep CNN with four convolutional layers is constructed to intelligently learn the distinguished features. The adjacent convolutional layer is used to sensitively capture slight changes in the input data, and the other layers are used to extract and reduce the abundant features. Random forest is used to accurately classify the fault types. The vibration signal of cylinder rolling bearing and gearbox is used to validate the proposed method. The results are compared with those of other state‐of‐the‐art methods to show the superior performance of the proposed method.

15 May 2019 in IEEE Access
Verified
Journal Article
Open access
YXYU XIN
YU XIN
SLShunming Li
Shunming Li
ZZZongzhen Zhang
Zongzhen Zhang
ZAZenghui An
Zenghui An
JWJinrui Wang
Jinrui Wang
Identifying impact fault features from fault vibration signal is significantly meaningful for the fault diagnosis and condition monitoring of rotating machinery. Given defects and the working conditions, impact features are covered by background noise. A new method named empirical wavelet transform (EWT) has been receiving attention from researchers and engineers. However, detecting boundaries by using the local maxima method from Fourier spectra and capturing the impact features through Meyer wavelet are the two crucial drawbacks of EWT. The former might be invalidated by the influence of non-stationary and noise frequency, and the latter is inappropriate for impact signal features. Therefore, reinforced empirical Morlet wavelet transform (REMWT) is proposed to overcome these shortcomings and efficiently diagnose fault features. In this method, the frequency spectrum boundaries are adaptively detected from the inner product of spectral kurtosis and Gaussian function via scale space representation, which can enhance the frequency character of impact features in vibration signals. Then, the constructed empirical Morlet wavelet serves as the adaptive filter bank for decomposing the signal into several empirical modes on the basis of spectrum boundaries. The meaningful component is selected via the maximum Pearson correlation coefficient method, and the envelope spectrum is used to accurately extract the fault features. The proposed method is then used to diagnose the fault features from collected vibration signals. Results show its effectiveness and outstanding performance.

4 September 2019 in Measurement Science and Technology
Verified
Journal Article
Closed access
PDF file
YXYU XIN
YU XIN
SLShunming Li
Shunming Li
A rotating mechanical vibration signal is time-varying and non-stationary because of the effect of defects on the rotating components and working conditions. The commonly used short-time Fourier transform (STFT) divides the time-domain signal into several segments by a sliding window. However, the STFT cannot optimize the time and frequency resolution. Considerable prior knowledge and much expertise are needed to further analyze these complex vibration signals. Therefore, a novel processing method comprising a fault vibration signal and named short-frequency mutual information entropy threshold filtering is proposed to filter and reconstruct the non-stationary vibration signal for diagnosing the impulse fault features. In this method, the improved STFT with an adaptive optimal window length is used to transform the vibration signal into the time-frequency domain. Then, a Meyer wavelet filter bank is used to divide the frequency spectrum into several sub-bands in each moment. The minimum mutual information entropy between the sub-bands and the original frequency is used to remove the partial sub-bands and filter the useful features from each frequency spectrum. Then, the frequency spectra are rearranged and an inverse STFT is used to recover the original signal. The envelope spectrum method is used to extract the fault features from the recovered signal. This method is completely determined by the characteristics of the vibration signal data. Finally, the fault vibration signal from our testing rig and wind turbine gearbox are used to verify the performance of the proposed method. The results show that this method can efficiently detect impact fault features in the vibration signal.