Ball bearing test‐rig research and fault diagnosis investigation

Yau, Her‐Terng; Kuo, Ying Che; Chen, Chieh Li; Li, Yu Chung

doi:10.1049/iet-smt.2015.0146

Cited by 19 publications

(16 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Yan et al 5 and Lei et al 6 reviewed the application of wavelet analysis and empirical mode decomposition (EMD) in fault diagnosis, respectively. Her-Terng et al [7][8][9] studied ball-bearing fault diagnosis based on chaotic system and fractal theory. Although these algorithms improve the classification accuracy and efficiency of bearing fault diagnosis greatly, in the era of large data, to face complex mechanical systems and massive monitoring data, traditional intelligent diagnosis algorithms may have lost their advantages because of the limitations of applicability.…”

Section: Introductionmentioning

confidence: 99%

Deep learning for bearing fault diagnosis under different working loads and non-fault location point

Wang

Xie

Zhang

2019

Journal of Low Frequency Noise, Vibration and Active Control

View full text Add to dashboard Cite

Intelligent fault diagnosis using deep learning has achieved much success in recent years. Using deep learning method to diagnose bearing fault requires designing an appropriate neural network model and then train with a massive data. On the one hand, up to now, a variety of neural network structures have been proposed for different diagnostic tasks, but there is a lack of research of unified structure. On the other hand, the fault data of the training neural network are collected from the fault location point, which is quite different from the actual data, because the sensor cannot be located at the fault location point accurately. This paper attempts to design a unified neural network structure based on Resnet and improve the generalization performance by using transfer learning techniques. The effectiveness of the proposed method in this paper is verified using experiment under different working loads and non-fault location point. Creative Commons CC BY: This article is distributed under the terms of the Creative Commons Attribution 4.0 License (http://www. creativecommons.org/licenses/by/4.0/) which permits any use, reproduction and distribution of the work without further permission provided the original work is attributed as specified on the SAGE and Open Access pages (https://us.sagepub.com/en-us/nam/open-access-at-sage).diagnosis, exploring the use of deep learning algorithm to solve different problems has become a hot research issue.Gan et al. 12 used the deep belief network (DBN) to classify the bearing faults, and they found that the diagnostic accuracy was significantly improved compared with the traditional back propagation neural network (BPNN) and support vector machine (SVM) methods. Wei et al. 13 studied and designed the convolutional neural network named Deep Convolutional Neural Networks with Wide First-layer Kernels (WDCNN) and Convolution Neural Networks with Training Interference (TICNN) 14 to solve the problem of bearing fault diagnosis under different load conditions. Shao et al. 15 combined with compressed sensing and convolutional deep belief netowrks (CDBN) networks to design a new diagnostic method that can reduce input characteristics. They also use a Gaussian visible unit to improve traditional CDBN, and the performance of the model is significantly improved. Feng et al. 16 developed a framework named deep normalized convolutional neural network (DNCNN) in order to solve the category imbalance problem in fault diagnosis. Pan et al. 17 proposed a LiftingNet framework to solve the problem of hierarchical feature learning under the influence of different speeds and random noise and succeeded in classifying. Szegedy et al. 18 and Chen et al. 19 proposed a deep inception net with atrous convolution (ACDIN) framework based on the structure of InceptionNet, which realized the task of detecting real faults with artificial fault data. Inspired by advanced technology, Zhi et al. 20 improved the capsule network and designed an inception capsule net (ICN) framework. They implemented the task of ...

show abstract

Section: Introductionmentioning

confidence: 99%

Deep learning for bearing fault diagnosis under different working loads and non-fault location point

Wang

Xie

Zhang

2019

Journal of Low Frequency Noise, Vibration and Active Control

View full text Add to dashboard Cite

show abstract

“…Chaos theory, as an important method in the field of nonlinear analysis, plays an indispensable role in the prediction and fault diagnosis for the performance time series of rolling bearings with nonlinear dynamic characteristics. Tian et al [8], Yau et al [9], and Wu et al [10] used chaos theory to carry out fault diagnosis by analyzing vibration signals, which provided an efficient method for monitoring the running state of rolling bearings. Xia and Chen [11] fused the chaos theory and fuzzy set theory to evaluate the nonlinear performance degradation process for rolling bearings.…”

Section: Introductionmentioning

confidence: 99%

Evaluation of Dynamic Uncertainty of Rolling Bearing Vibration Performance

Liang

Xia

Chang³

2019

Mathematical Problems in Engineering

View full text Add to dashboard Cite

The variation trend, failure trajectory, probability distribution, and other information vary with time and working conditions for rolling bearing vibration performance, which makes the evaluation and prediction of the evolution process difficult for the performance reliability. In view of this, the chaos theory, grey bootstrap method, and maximum entropy method were effectively fused to propose a mathematical model for the dynamic uncertainty evaluation of rolling bearing vibration performance. After reconstructing the phase space of the vibration performance time series, four local prediction methods were applied to predict the vibration values of bearings to verify the effectiveness and validity of chaos theory. The estimated true value and estimated interval were calculated using the grey bootstrap method (GBM) and maximum entropy method. Finally, the validity of the proposed model was verified by comparing the probability that the original data fall into the estimated interval with the given confidence level. The experimental results show that the proposed method can effectively predict the variation trend and failure trajectory of the vibration performance time series so as to realize the dynamic monitoring of the evolution process for rolling bearing vibration performance online.

show abstract

“…For signal analysis, both discrete Fourier [ 17 ] transform and wavelet [ 18 , 19 , 20 , 21 , 22 , 23 , 24 ] were the most frequent analyses used. Over the last few years, chaos systems have been extensively used for diagnosis [ 25 , 26 ] with the fractional-order chaos method giving better diagnostic results, than a simpler chaotic system [ 27 , 28 ].…”

Section: Introductionmentioning

confidence: 99%

Intelligent Ball Bearing Fault Diagnosis Using Fractional Lorenz Chaos Extension Detection

Tian

et al. 2018

Sensors

View full text Add to dashboard Cite

In this study we used a non-autonomous Chua’s circuit, and the fractional Lorenz chaos system. This was combined with the Extension theory detection method to analyze the voltage signals. The bearing vibration signals, measured using an acceleration sensor, were introduced into the master and slave systems through a Chua’s circuit. In a chaotic system, minor differences can cause significant changes that generate dynamic errors. The matter-element model extension can be used to determine the bearing condition. Extension theory can be used to establish classical and sectional domains using the dynamic errors of the fault conditions. The results obtained were compared with those from discrete Fourier transform analysis, wavelet analysis and an integer order chaos system. The diagnostic rate of the fractional-order master and slave chaotic system could reach 100% if the fractional-order parameter adjustment was used. This study presents a very efficient and inexpensive method for monitoring the state of ball bearings.

show abstract

Ball bearing test‐rig research and fault diagnosis investigation

Cited by 19 publications

References 14 publications

Deep learning for bearing fault diagnosis under different working loads and non-fault location point

Deep learning for bearing fault diagnosis under different working loads and non-fault location point

Evaluation of Dynamic Uncertainty of Rolling Bearing Vibration Performance

Intelligent Ball Bearing Fault Diagnosis Using Fractional Lorenz Chaos Extension Detection

Contact Info

Product

Resources

About