scholarly journals A Fault Diagnosis Method of Rolling Mill Bearing at Low Frequency and Overload Condition Based on Integration of EEMD and GA-DBN

2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Jiang Ji ◽  
Chen Zhao ◽  
Yongqin Wang ◽  
Tuanmin Zhao ◽  
Xinyou Zhang

To solve the problems of difficult fault signal recognition and poor diagnosis effect of different damage in the same position in rolling mill bearing at low speed, a fault diagnosis method of rolling mill bearing based on integration of EEMD and DBN was proposed. The vibration signals in horizontal, axial, and vertical directions were decomposed and reconstructed by EEMD, and frequency domain analysis was carried out by using refined spectrum. Then, the signal's time-frequency domain index, rolling force, and torque component feature vector were input into genetic algorithm (GA) to optimize DBN model classification. In order to verify the effectiveness of the method, the experimental study was carried out on the two-high experimental rolling mill. The results show that EEMD combined with thinning spectrum can solve the problem of fault feature extraction well. Compared with time-frequency domain characteristic input, the prediction accuracy of DBN model is obviously improved. And the accuracy of GA-DBN model is higher, and the accuracy is 98.3%, and the time taken to diagnose is significantly reduced. Finally, the fault classification of different parts of bearings and the fault diagnosis of different damage in the same part are realized, which provides a good theoretical basis for the fault diagnosis of low-speed bearings and has important engineering significance.

Sensors ◽  
2021 ◽  
Vol 21 (24) ◽  
pp. 8168
Author(s):  
Lihao Ye ◽  
Xue Ma ◽  
Chenglin Wen

Aiming at the problem of fault diagnosis when there are only a few labeled samples in the large amount of data collected during the operation of rotating machinery, this paper proposes a fault diagnosis method based on knowledge transfer in deep learning. First, we describe the data collected during the operation as a two-dimensional image with both time and frequency-domain characteristics. Second, we transform the trained source domain model into a shallow model suitable for small samples in the target domain, and we train the shallow model with small samples with labels. Third, we input a large number of unlabeled samples into the shallow model, and the output result of the system is regarded as the label of the input sample. Fourth, we combine the original data and the data annotated by the shallow model to train the new deep CNN fault diagnosis model so as to realize the migration of knowledge from the expert system to the deep CNN. The newly built deep CNN model is used for the online fault diagnosis of rotating machinery. The FFCNN-SVM shallow model tagger method proposed in this paper compares the fault diagnosis results with other transfer learning methods at this stage, and its correct rate has been greatly improved. This method provides new ideas for future fault diagnosis under small samples.


2012 ◽  
Vol 542-543 ◽  
pp. 161-164
Author(s):  
Yong Ying Du ◽  
Yu Ning Wang ◽  
Ming Ang Yin

In the paper it can be easier to realize the acquisition of the rotating machinery vibration signal and condition monitoring through the configuration the platform of virtual instrumentation. For the data acquisition it is enough to be plus with two acceleration sensors and a counter. The system is divided into parameter setting module, data acquisition, storage and display module, amplitude domain analysis module, time-domain analysis module, frequency domain analysis module, time-frequency domain analysis module and fault diagnosis module. The signal acquisition is got by using the PCI-6024E data acquisition card. And it is can be saved as binary data stream files and waveform data file according to the requirements of the sequence data processing. Signal analysis is conducted by using LabVIEW software and draw out the vibration spectrum diagram in order to achieve fault diagnosis of rotating machinery.


2012 ◽  
Vol 226-228 ◽  
pp. 740-744 ◽  
Author(s):  
Ya Hui Wu ◽  
Meng Xiao Shan ◽  
Yu Ning Qian ◽  
Xin Liang Li ◽  
Ru Qiang Yan

With the development of aeroengine towards the direction of high speed and high performance, the clearance between rotor and stator in aerongine is reduced so that the possibility of rub-impact fault is increased. Since rub-impact signals often exhibits non-stationarity, an integrated approach, which combines the wavelet packet transform (WPT) with local discriminate bases (LDB), is presented in this study to diagnose the rub-impact faults. Specifically, the LDB algorithm is used to select an optimal set of orthogonal time-frequency subspaces resulted from WPT, which have the best discriminatory information for aeroengine rub-impact fault classification. Then the desired parameters generated by the LDB vectors were taken as input to a Bayes classifier for identifying rub-impact faults. Experimental results from the aeroengine vibration signals show that the fault diagnosis method can classify working conditions and fault patterns effectively.


Complexity ◽  
2021 ◽  
Vol 2021 ◽  
pp. 1-13
Author(s):  
Tongle Xu ◽  
Junqing Ji ◽  
Xiaojia Kong ◽  
Fanghao Zou ◽  
Wilson Wang

The classification frameworks for fault diagnosis of rolling element bearings in rotating machinery are mostly based on analysis in a single time-frequency domain, where sensitive features are not completely extracted. To solve this problem, a new fault diagnosis technique is proposed in the mixed domain, based on the crossover-mutation chaotic particle swarm optimization support vector machine. Firstly, fault features are generated using techniques in the time domain, the frequency domain, and the time-frequency domain. Secondly, the weighted maximum relevance minimum redundancy (WMRMR) algorithm is adopted to reduce the dimension of the feature set and to establish the representative feature set. Thirdly, a new crossover-mutation strategy is suggested to reduce the local minima in optimization, and an optimization disturbance is added. Finally, the support vector machine is optimized using the improved chaotic particle swarm to improve fault classification diagnosis. The effectiveness of the proposed new bearing fault diagnostic technique is verified by experimental tests under different bearing conditions. Test results showed that the bearing fault classification accuracy of CMCPSO-SVM in the mixed domain was much higher than those in a single feature domain.


2019 ◽  
Vol 2019 ◽  
pp. 1-13
Author(s):  
Guodong Sun ◽  
Yuan Gao ◽  
Kai Lin ◽  
Ye Hu

To accurately diagnose fine-grained fault of rolling bearing, this paper proposed a new fault diagnosis method combining multisynchrosqueezing transform (MSST) and sparse feature coding based on dictionary learning (SFC-DL). Firstly, the high-resolution time-frequency images of raw vibration signals, including different kinds of fine-grained faults of rolling bearing, were constructed by MSST. Then, the basis dictionary was trained through nonnegative matrix factorization with sparseness constraints (NMFSC), and the trained basis dictionary was employed to extract features from time-frequency matrixes by using nonnegative linear equations. Finally, a linear support vector machine (LSVM) was trained with features of training samples, and the trained LSVM was employed to diagnosis the fault classification of test samples. Compared with state-of-the-art fault diagnosis methods, the proposed method, which was tested on the bearing dataset from Case Western Reserve University (CWRU), achieved the fine-grained classification of 10 mixed fault states. Meanwhile, the proposed method was applied on the dataset from the Machinery Failure Prevention Technology (MFPT) Society and realized the classification of 3 fault states under different working conditions. These results indicate that the proposed method has great robustness and could better meet the needs of practical engineering.


2013 ◽  
Vol 823 ◽  
pp. 9-12 ◽  
Author(s):  
Xiang Li Zhao ◽  
Li Xin Gao ◽  
Jian Feng Li

Aiming at the difficulties in diagnosis for low speed and heavy duty components of furnace top gearbox, an indirect diagnosis method for vibration signal is proposed in this subject, through which the vibration features of high speed rotating parts that near input end of gearbox is effectively utilized and analyzed for fault judgment of low speed components and a useful methodology is also given for fault diagnosis of both furnace top gearbox and low speed and heavy duty equipments. Since the identification for all faults and accurate fault location cannot be realized by using the existing diagnosis methods, a method of vibration analysis for fault diagnosis to furnace top gearbox is presented to realize accurate judgment and fault location. It can be found out that if near the basic frequency and double frequency of characteristic frequency of high speed components of upper gearbox, there were frequency spacing of fault characteristic frequency of low speed components of subordinate transmission chain apparently showing up, which also happened in low frequency range after demodulation, then the fault location can be determined to the low speed parts of subordinate transmission chain.


2020 ◽  
Vol 14 ◽  
Author(s):  
Xiao-bin Fan ◽  
Hao Li ◽  
Yu Jiang ◽  
Bing-xu Fan ◽  
Liang-jing Li

Background: Rolling mill vibration mechanism is very complex, and people haven't found a satisfactory vibration control method. Rolling interface is one of the vibration sources of the rolling mill system, and its friction and lubrication state has a great impact on the vibration of the rolling mill system. It is necessary to establish an accurate friction model for unsteady lubrication process of roll gap and a nonlinear vibration dynamic model for rolling process. In addition, it is necessary to obtain more direct and real rolling mill vibration characteristics from the measured vibration signals, and then study the vibration suppression method and design the vibration suppression device. Methods: This paper summarizes the friction lubrication characteristics of rolling interface and its influence on rolling mill vibration, as well as the dynamic friction model of rolling interface, the tribological model of unsteady lubrication process of roll gap, the non-linear vibration dynamic model of rolling process, the random and non-stationary dynamic behavior of rolling mill vibration, etc. At the same time, the research status of rolling mill vibration testing technology and vibration suppression methods were summarized. Time-frequency analysis of non-stationary vibration signals was reviewed, such as wavelet transform, Wigner-Ville distribution, empirical mode decomposition, blind source signal extraction, rolling vibration suppression equipment development. Results: The lubrication interface of the roller gap under vibration state presents unsteady dynamic characteristics. The signals generated by the vibration must be analyzed in time and frequency simultaneously. In the aspect of vibration suppression of rolling mill, the calculation of inherent characteristics should be carried out in the design of rolling mill to avoid dynamic defects such as resonance. When designing or upgrading the mill structure, it is necessary to optimize the structure of the work roll bending and roll shifting system, such as designing and developing the automatic adjustment mechanism of the gap between the roller bearing seat and the mill stand, adding floating support device to the drum shaped toothed joint shaft, etc. In terms of rolling technology, rolling vibration can be restrained by improving roll lubrication, reasonably distributing rolling force of each rolling mill, reducing rolling force of vibration prone rolling mill, increasing entrance temperature, reducing rolling inlet tension, reducing strip outlet temperature and reasonably arranging roll diameter. The coupling vibration can also be suppressed by optimizing the hydraulic servo system and the frequency conversion control of the motor. Conclusion: Under the vibration state, the lubrication interface of roll gap presents unsteady dynamic characteristics. The signal generated by vibration must be analyzed by time-frequency distribution. In the aspect of vibration suppression of rolling mill, the calculation of inherent characteristics should be carried out in the design of rolling mill to avoid dynamic defects such as resonance. It is necessary to optimize the structure of work roll bending and roll shifting system when designing or reforming the mill structure. In rolling process, rolling vibration can be restrained by improving roll lubrication, reasonably distributing rolling force of each rolling mill, increasing billet temperature, reasonably arranging roll diameter and reducing rolling inlet tension. Through the optimization of the hydraulic servo system and the frequency conversion control of the motor, the coupling vibration can be suppressed. The paper has important reference significance for vibration suppression of continuous rolling mill and efficient production of high quality strip products.


Author(s):  
Baoling Guo ◽  
Seddik Bacha ◽  
Mazen Alamir ◽  
Julien Pouget

AbstractAn extended state observer (ESO)-based loop filter is designed for the phase-locked loop (PLL) involved in a disturbed grid-connected converter (GcC). This ESO-based design enhances the performances and robustness of the PLL, and, therefore, improves control performances of the disturbed GcCs. Besides, the ESO-based LF can be applied to PLLs with extra filters for abnormal grid conditions. The unbalanced grid is particularly taken into account for the performance analysis. A tuning approach based on the well-designed PI controller is discussed, which results in a fair comparison with conventional PI-type PLLs. The frequency domain properties are quantitatively analysed with respect to the control stability and the noises rejection. The frequency domain analysis and simulation results suggest that the performances of the generated ESO-based controllers are comparable to those of the PI control at low frequency, while have better ability to attenuate high-frequency measurement noises. The phase margin decreases slightly, but remains acceptable. Finally, experimental tests are conducted with a hybrid power hardware-in-the-loop benchmark, in which balanced/unbalanced cases are both explored. The obtained results prove the effectiveness of ESO-based PLLs when applied to the disturbed GcC.


Electronics ◽  
2021 ◽  
Vol 10 (12) ◽  
pp. 1496
Author(s):  
Hao Liang ◽  
Yiman Zhu ◽  
Dongyang Zhang ◽  
Le Chang ◽  
Yuming Lu ◽  
...  

In analog circuit, the component parameters have tolerances and the fault component parameters present a wide distribution, which brings obstacle to classification diagnosis. To tackle this problem, this article proposes a soft fault diagnosis method combining the improved barnacles mating optimizer(BMO) algorithm with the support vector machine (SVM) classifier, which can achieve the minimum redundancy and maximum relevance for feature dimension reduction with fuzzy mutual information. To be concrete, first, the improved barnacles mating optimizer algorithm is used to optimize the parameters for learning and classification. We adopt six test functions that are on three data sets from the University of California, Irvine (UCI) machine learning repository to test the performance of SVM classifier with five different optimization algorithms. The results show that the SVM classifier combined with the improved barnacles mating optimizer algorithm is characterized with high accuracy in classification. Second, fuzzy mutual information, enhanced minimum redundancy, and maximum relevance principle are applied to reduce the dimension of the feature vector. Finally, a circuit experiment is carried out to verify that the proposed method can achieve fault classification effectively when the fault parameters are both fixed and distributed. The accuracy of the proposed fault diagnosis method is 92.9% when the fault parameters are distributed, which is 1.8% higher than other classifiers on average. When the fault parameters are fixed, the accuracy rate is 99.07%, which is 0.7% higher than other classifiers on average.


2019 ◽  
Vol 16 (6) ◽  
pp. 1017-1031 ◽  
Author(s):  
Yong Hu ◽  
Liguo Han ◽  
Rushan Wu ◽  
Yongzhong Xu

Abstract Full Waveform Inversion (FWI) is based on the least squares algorithm to minimize the difference between the synthetic and observed data, which is a promising technique for high-resolution velocity inversion. However, the FWI method is characterized by strong model dependence, because the ultra-low-frequency components in the field seismic data are usually not available. In this work, to reduce the model dependence of the FWI method, we introduce a Weighted Local Correlation-phase based FWI method (WLCFWI), which emphasizes the correlation phase between the synthetic and observed data in the time-frequency domain. The local correlation-phase misfit function combines the advantages of phase and normalized correlation function, and has an enormous potential for reducing the model dependence and improving FWI results. Besides, in the correlation-phase misfit function, the amplitude information is treated as a weighting factor, which emphasizes the phase similarity between synthetic and observed data. Numerical examples and the analysis of the misfit function show that the WLCFWI method has a strong ability to reduce model dependence, even if the seismic data are devoid of low-frequency components and contain strong Gaussian noise.


Sign in / Sign up

Export Citation Format

Share Document