A novel unsupervised learning method for intelligent fault diagnosis of rolling element bearings based on deep functional auto-encoder

Aljemely, Anas H.; Xuan, Jianhua; Jawad, Farqad K. J.; Al-Azzawi, Osama; Alhumaima, Ali S.

doi:10.1007/s12206-020-1002-x

Cited by 22 publications

(9 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the process of point cloud feature extraction, machine learning algorithms, including supervised learning [1,2,28,29] and unsupervised learning [3,30,31], are widely applied. And the feature points are used to train deep learning networks [27,32].…”

Section: Related Workmentioning

confidence: 99%

“…Unsupervised learning is an algorithm that divides the classification space without prior knowledge. Typical supervised learning includes PCA [30], agglomerative clustering, density-based spatial clustering of applications with noise (DBSCAN), and so on [31]. In the three-dimensional space, the clustering method can divide and extract the target of the point cloud without knowing the classification of the point cloud.…”

Section: Unsupervised Learningmentioning

confidence: 99%

See 1 more Smart Citation

AOMC: An Adaptive Point Cloud Clustering Approach for Feature Extraction

Zhang

Jin

2022

Scientific Programming

View full text Add to dashboard Cite

Point cloud local feature extraction places an important part of point cloud deep learning neural networks. Accurate extraction of point cloud features is still a challenge for deep learning networks. Oversampling and feature loss of point cloud model are important problems in the accuracy of image point cloud deep learning network. In this paper, we propose an adaptive clustering method for point cloud feature extraction—adaptive optimal means clustering (AOMC)—and apply it to point cloud deep learning network tasks. This method solves the problem of determining the number of clustering centers in the process of point cloud feature extraction so that the feature points contain the whole point cloud model and avoid the problem of losing detail features. Specifically, according to the loss characteristics of point cloud clustering, AOMC selects a different number of clustering centers for various models. Moreover, in light of the density distribution of the point cloud, the radius of the clustering subset is determined. This method effectively improves the accuracy of the point cloud deep learning network on object classification and parts segmentation. Our method reaches demand on Modelnet10 and shapenetcore_partanno_segmentation_benchmark datasets. In terms of deep learning network optimization, it has good performance. Additionally, our method has high accuracy and low algorithm complexity.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Unsupervised Learningmentioning

confidence: 99%

AOMC: An Adaptive Point Cloud Clustering Approach for Feature Extraction

Zhang

Jin

2022

Scientific Programming

View full text Add to dashboard Cite

show abstract

“…The principal function of the autoencoder is to reconstruct the input given into the neural network through a small dimensional latent space. The network attempts to create as close a reconstruction to the original input by learning the salient features [7].…”

Section: A Neural Networkmentioning

confidence: 99%

Vibration Anomaly Detection using Deep Autoencoders for Smart Factory

Waters

Waszczuk

Ayre³

et al. 2022

2022 IEEE Sensors

View full text Add to dashboard Cite

Early fault detection in production is crucial for manufacturing facilities to prevent unplanned downtimes and maximise the operational life of equipment. The aim of this paper is to present a method of anomaly detection for an in service motor using self-supervised learning. The authors have developed a condition monitoring system for a Smart Factory using deep autoencoders. The systems was installed in a live production facility with the goal of improving site maintenance.

show abstract

“…Recently, deep learning technology has been widely used in fault identification based on vibration measurement, for example: (a) application of the spectral kurtosis technique to select the frequency bandwidth, which contains the fault characteristics, for fault detection of rolling bearings [8]; (b) a fault diagnosis method based on variational pattern decomposition and an improved convolutional neural network (CNN) [9]; (c) a fault diagnosis method based on multivariate singular spectral decomposition and improved Kolmogorov complexity [10], which has shown good performance in fault diagnosis [11,12]. However, most studies have focused on how to optimize the model [10][11][12] and little attention has been paid to two problems caused by the limited mounting position of acceleration sensors in engineering applications, namely: (a) incomplete observation of the phenomenon [13] and (b) the low signal to noise ratio (SNR) of the acquired acceleration signals [14]. The impact of these problems on machine learning-based fault diagnosis methods has not yet seen much research.…”

Section: Introductionmentioning

confidence: 99%

A fault diagnosis method based on low signal to noise ratio vibration measurement for use in casing cutters

Zhang

Liu

Tao³

et al. 2022

Meas. Sci. Technol.

View full text Add to dashboard Cite

In this paper, a fault diagnosis method for casing cutter was proposed, a vibration signal acquisition circuit used at high temperature environment was designed, and a casing cutter measurement model was established, including the model of the casing cutter in a trouble-free state and two other common fault states, the vibration characteristics of the model was analyzed. A fault feature enhancement model based on SNR enhancement and sparse representation, which effectively solves the fault diagnosis problem caused by the limited installation location and the limited performance of the vibration measurement at high-temperature was also designed. The MobieNet-V3- Small convolutional neural network (CNN) model is improved by reducing the basic blocks of the continuous homogeneous structure in the original model, the Squeeze and Excitation-SE structure is expanded to the global level to obtain a lightweight CNN fault recognition model. The effectiveness and efficiency of the proposed method are validated by various experiments.

show abstract

A novel unsupervised learning method for intelligent fault diagnosis of rolling element bearings based on deep functional auto-encoder

Cited by 22 publications

References 45 publications

AOMC: An Adaptive Point Cloud Clustering Approach for Feature Extraction

AOMC: An Adaptive Point Cloud Clustering Approach for Feature Extraction

Vibration Anomaly Detection using Deep Autoencoders for Smart Factory

A fault diagnosis method based on low signal to noise ratio vibration measurement for use in casing cutters

Contact Info

Product

Resources

About