Data-driven mono-component feature identification via modified nonlocal means and MEWT for mechanical drivetrain fault diagnosis

Pan, Jun; Chen, Jinglong; Ye, Zi; Yuan, Jing; Chen, Binqiang; He, Zhengjia

doi:10.1016/j.ymssp.2016.05.013

Cited by 23 publications

(11 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lu et al [12] developed data-driven vibration prediction of cold rolling mill, and proposed the XGBoost model to predict rolling mill vibration. Chen et al [13] and Pan et al [14] designed a data-driven condition monitoring system to detect mechanical faults of bearings in the main driven system of hot tandem rolling mill. Dong et al [15] used DBN and GA-BP algorithm to establish the rolling mill vibration prediction model to predict the rolling mill vibration.…”

Section: Introductionmentioning

confidence: 99%

Vibration prediction and analysis of strip rolling mill based on XGBoost and Bayesian optimization

Yang

Lin

Zhang

et al. 2022

Complex Intell. Syst.

View full text Add to dashboard Cite

The stable operation of strip rolling mill is the key factor to ensure the stability of product quality. The design capability of existing domestic imported and self-developed strip rolling mills cannot be fully developed, and the frequent occurrence of mill vibration and operation instability problems seriously restrict the equipment capacity and the production of high-end strip products. The vibration prediction analysis method for hot strip mill based on eXtreme gradient boosting (XGBoost) and Bayesian optimization (BO) is proposed. First, an XGBoost prediction model is developed based on a self-built data set to construct a complex functional relationship between process parameters and rolling mill vibration. Second, the important hyperparameters and parameters of XGBoost are optimized using Bayesian optimization algorithm to improve the prediction accuracy, computational efficiency, and stability of the model. Third, a comprehensive comparison is made between the prediction model in this paper and other well-known machine learning benchmark models. Finally, the prediction results of the model are interpreted using the SHapley Additive exPlanations (SHAP) method. The proposed model outperforms existing models in terms of prediction accuracy, computational speed and stability. At the same time, the degree of influence of each feature on rolling mill vibration is also obtained.

show abstract

Section: Introductionmentioning

confidence: 99%

Vibration prediction and analysis of strip rolling mill based on XGBoost and Bayesian optimization

Yang

Lin

Zhang

et al. 2022

Complex Intell. Syst.

View full text Add to dashboard Cite

show abstract

“…Xia et al [28] proposed a novel identification method based on key kernels-PSO for Volterra series identification. Pan et al [29] proposed a new data-driven mono-component identification method based on modified empirical wavelet transform and Hilbert transform. Zheng et al [30] proposed an adaptive parameterless empirical wavelet transform and normalized Hilbert transform for rotor rubbing fault diagnosis.…”

Section: Introductionmentioning

confidence: 99%

Fault Diagnosis Method Based on Principal Component Analysis and Broad Learning System

et al. 2019

View full text Add to dashboard Cite

Traditional feature extraction methods are used to extract the features of signal to construct the fault feature matrix, which exists the complex structure, higher correlation, and redundancy. This will increase the complex fault classification and seriously affect the accuracy and efficiency of fault identification. In order to solve these problems, a new fault diagnosis (PABSFD) method based on the principal component analysis (PCA) and the broad learning system (BLS) is proposed for rotor system in this paper. In the proposed PABSFD method, the PCA with revealing the signal essence is used to reduce the dimension of the constructed feature matrix and decrease the linear feature correlation between data and eliminate the redundant attributes in order to obtain the low-dimensional feature matrix with retaining the essential features for the classification model. Then, the BLS with low time complexity and high classification accuracy is regarded as a classification model to realize the fault identification; it can efficiently accomplish the fault classification of rotor system. Finally, the actual vibration data of rotor system are selected to test and verify the effectiveness of the PABSFD method. The experimental results show that the PCA method can effectively eliminate the feature correlation and realize the dimension reduction of the feature matrix, the BLS can take on better adaptability, faster computation speed, and higher classification accuracy, and the PABSFD method can efficiently and accurately obtain the fault diagnosis results. INDEX TERMS Rotor system, fault diagnosis, principal component analysis (PCA), broad learning system (BLS), dimension reduction.

show abstract

“…22,23 To better segment the spectrum, some scholars have proposed modifications. 21,24–27 However, these methods ignore the sideband of the gearbox fault signal spectrum. When the maximum value of the spectrum is concentrated in a frequency band, the boundary of detection will also be concentrated in the frequency band.…”

Section: Introductionmentioning

confidence: 99%

“…However, in practical applications, it is unknown or difficult to confirm. 25,26 To solve this problem, this paper takes the trend of the signal spectrum into account and proposes the improved EWT based on spectrum trend, named ST-EWT. The fault signal is decomposed by ST-EWT, and then the demodulation of BLIMFs is carried out to locate the fault position.…”

Section: Introductionmentioning

confidence: 99%

Improved empirical wavelet transform method based on spectrum trend for gearbox fault signal processing

Zhang

Wang

Li³

et al. 2019

Proceedings of the Institution of Mechanical Engineers, Part D:

View full text Add to dashboard Cite

The empirical wavelet transform decomposes the signal by segmenting the Fourier spectrum and constructing an adaptive filter bank and then segments the spectrum by detecting the maximum value in the spectrum. However, the number of mono-components is unknown or difficult to confirm when processing actual gearbox fault signals, the result of decomposition will be neither reasonable nor conducive to demodulation analysis if the maximum value is concentrated in one component. To solve this problem, a concept of an amplitude modulation–frequency modulation signal in the form of a wave crest is proposed. The spectrum trend of the Fourier spectrum of signal is extracted by the empirical mode decomposition method, and then the number of mode components is presupposed and the spectrum is segmented according to the extracted spectrum trend. The extraction method of the spectrum trend based on improved empirical wavelet transform based on spectrum trend method is proposed for gearbox fault diagnosis. The experiment, including the vibration test platform of horizontal driving machine and the processing of experimental signals based on the improved empirical wavelet transform based on spectrum trend method are also given. According to the simulation and experiment results, it can be clearly found that the spectrum trend can describe the distribution of signal spectrum well, and the components obtained by the improved empirical wavelet transform based on spectrum trend method are more suitable than original empirical wavelet transform method for demodulation analysis.

show abstract

Data-driven mono-component feature identification via modified nonlocal means and MEWT for mechanical drivetrain fault diagnosis

Cited by 23 publications

References 26 publications

Vibration prediction and analysis of strip rolling mill based on XGBoost and Bayesian optimization

Vibration prediction and analysis of strip rolling mill based on XGBoost and Bayesian optimization

Fault Diagnosis Method Based on Principal Component Analysis and Broad Learning System

Improved empirical wavelet transform method based on spectrum trend for gearbox fault signal processing

Contact Info

Product

Resources

About