Rolling Bearing Fault Diagnosis Using a Deep Convolutional Autoencoding Network and Improved Gustafson–Kessel Clustering

Wu, You; Zhao, Rongzhen; Jin, Wuyin; Deng, Liya; He, Tianjing; Ma, Sencai

doi:10.1155/2020/8846589

Cited by 5 publications

(2 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Taking the proposed ECFD on HP0 as an example, the clustering accuracies of the fused features are improved by 9.23% in comparison with F1, 17.06% in comparison with F2, 18.00% in comparison with F3, and 10.11% in comparison with F4. As for the single features, the time-domain features [74] • GK(Gustafson-Kessel)…”

Section: Evaluation Of the Fused Featuresmentioning

confidence: 99%

Ensemble clustering-based fault diagnosis method incorporating traditional and deep representation features

Wang

Huang

Zhang

2021

Meas. Sci. Technol.

View full text Add to dashboard Cite

The traditional and deep representation features have been successfully employed in the clustering-based fault diagnosis, however, current studies have ignored their heterogeneity and complementarity. Besides, these studies have rarely explored the superiority of ensemble clustering, leading to unstable diagnostic results. To address these issues, a novel ensemble clustering-based fault diagnosis method, namely ECFD, is proposed based on the collaboration of traditional and deep representation features. To the best of our knowledge, this is the first attempt to develop an ensemble clustering method with these types of features for fault diagnosis of rotating machinery. Initially, features are extracted by different approaches, among which the traditional features are obtained by time-domain, frequency-domain, time-frequency-domain approaches, and the deep representation features are extracted by the gated recurrent units-based autoencoders. Then, the heterogeneous and complementary information among these features is explored by the adaptive group regularization method, which is also developed to generate high-quality feature subspaces for constructing the base learners of the ensemble clustering. Finally, the clustering results of each base learner are integrated by a weighted voting method. The effectiveness of the proposed ECFD was verified by the experiments on the real-world bearing vibration dataset. The results indicate that the proposed ECFD can explore the heterogeneity and complementarity among different kinds of features and take advantage of the ensemble clustering, which is superior to other existing benchmark clustering methods in unsupervised fault diagnosis.

show abstract

Section: Evaluation Of the Fused Featuresmentioning

confidence: 99%

Ensemble clustering-based fault diagnosis method incorporating traditional and deep representation features

Wang

Huang

Zhang

2021

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…Demetgul et al [16] applied the k-medoids method to the fault diagnosis of material handling systems and achieved good results. Furthermore, fuzzy c-means [17] and its variant Gustafson-Kessel [18] are also widely used in fault diagnosis as a partitional clustering algorithm task [16,19]. In addition, to solve the sparse data problem in practical industrial scenarios, Li et al [20] proposed a deep unsupervised clustering method for fault diagnosis and achieved good performances.…”

Section: Introductionmentioning

confidence: 99%

A novel complex network community clustering method for fault diagnosis

Chen¹,

Lei²,

Tian³

et al. 2022

Meas. Sci. Technol.

View full text Add to dashboard Cite

Complex network, as a method for analyzing nonlinear and non-stationary signals, overcomes the shortcomings of traditional time-frequency analysis methods and proves its effectiveness in mechanical fault diagnosis. Community clustering, as one of them, has made great progress in recent years. However, the existing community clustering algorithms have the disadvantages of lacking significant global extreme value and huge search space. Therefore, a Fast Newman algorithm based on reliability judgment is proposed. Starting from the community structure characteristics of the complex network, with the fault sample as a network node, the relationship between the samples as a connected edge, and a complex network model of fault data is established. Clusters in troubleshooting are transformed into community structure discovery in the network. Firstly, the initial division of the community is obtained by measuring the distance between the samples. Then, the modularity index of the network is used as a standard function of the community division, and the bottom-up community merger is performed. The local edge density index is used for reliability determination before each combination to achieve global optimization, and the network block structure is the most obvious. Finally, with all data being merged into one community, the optimal division of the community structure is obtained while accurate community clustering and fault diagnosis is realized. The benchmark graphs for testing community detection (LFR standard test network) and different fault data of rolling bearings under multiple operating conditions are applied to verify the effectiveness of this method, and the experiment results prove that the modified Fast Newman algorithm has better clustering effect and higher correct rate than the original one. Compared with K-means clustering and fuzzy clustering, the modified Fast Newman algorithm achieves higher performance for fault diagnosis of rolling bearing under multiple operating conditions.

show abstract