Deep Clustering Bearing Fault Diagnosis Method Based on Local Manifold Learning of an Autoencoded Embedding

J, An; Ai, Ping; Liu, Cong; Xu, Sen; Liu, Dakun

doi:10.1109/access.2021.3059459

Cited by 13 publications

(8 citation statements)

References 26 publications

(34 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We opted for a manifold learning technique to re-embed the data and aimed to learn the entire embedded manifold to optimize the clustering. While the autoencoder we used was a good choice for learning a meaningful data representation, it did not consider the local structure [ 56 ]. By combining the autoencoder with a manifold learning technique that considered the local structure, we could enhance the quality of the representation in terms of the clusterability.…”

Section: Methodsmentioning

confidence: 99%

“…UMAP combines Riemannian geometry, algebraic topology, and ML techniques to find a low-dimensional data representation that retains its structure. Unlike dimensionality reduction algorithms such as t-distributed stochastic neighbor embedding (t-SNE) [ 58 ] and principal component analysis (PCA) [ 59 ], UMAP can preserve the data’s local and global structure, and the algorithm can be adjusted through various hyperparameters, giving users greater control over the process [ 56 , 57 ]. Additionally, UMAP is less sensitive to changes in hyperparameters.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Towards Data-Driven Decision-Making in the Korean Film Industry: An XAI Model for Box Office Analysis Using Dimension Reduction, Clustering, and Classification

Leem

et al. 2023

Entropy

View full text Add to dashboard Cite

The Korean film market has been rapidly growing, and the importance of explainable artificial intelligence (XAI) in the film industry is also increasing. In this highly competitive market, where producing a movie incurs substantial costs, it is crucial for film industry professionals to make informed decisions. To assist these professionals, we propose DRECE (short for Dimension REduction, Clustering, and classification for Explainable artificial intelligence), an XAI-powered box office classification and trend analysis model that provides valuable insights and data-driven decision-making opportunities for the Korean film industry. The DRECE framework starts with transforming multi-dimensional data into two dimensions through dimensionality reduction techniques, grouping similar data points through K-means clustering, and classifying movie clusters through machine-learning models. The XAI techniques used in the model make the decision-making process transparent, providing valuable insights for film industry professionals to improve the box office performance and maximize profits. With DRECE, the Korean film market can be understood in new and exciting ways, and decision-makers can make informed decisions to achieve success.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Towards Data-Driven Decision-Making in the Korean Film Industry: An XAI Model for Box Office Analysis Using Dimension Reduction, Clustering, and Classification

Leem

et al. 2023

Entropy

View full text Add to dashboard Cite

show abstract

“…The fused feature vectors are used to machine health indicators. [107] proposed a simple deep learning clustering method, inspired by [43], which applied manifold learning to off-the-shelf embeddings to find an alternative model for clustering networks and simply combined the manifold learning 2332-7782 (c) 2021 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission.…”

Section: E Autoencodermentioning

confidence: 99%

Artificial Intelligence-Based Technique for Fault Detection and Diagnosis of EV Motors: A Review

Lang¹,

Gong

et al. 2022

IEEE Trans. Transp. Electrific.

View full text Add to dashboard Cite

The motor drive system plays a significant role in the safety of electric vehicles as a bridge for power transmission. Meanwhile, to enhance the efficiency and stability of the drive system, more and more studies based on AI technology are devoted to the fault detection and diagnosis of the motor drive system. This paper reviews the application of AI techniques in motor fault detection and diagnosis in recent years. AI-based FDD is divided into two main steps: feature extraction and fault classification. The application of different signal processing methods in feature extraction is discussed. In particular, the application of traditional machine learning and deep learning algorithms for fault classification is presented in detail. In addition, the characteristics of all techniques reviewed are summarized. Finally, the latest developments, research gaps and future challenges in fault monitoring and diagnosis of motor faults are discussed.

show abstract

“…In the study, clustering accuracy (ACC) [36] and normalized mutual information (NMI) [47] are used to evaluate the effectiveness of the proposed method without supervision. ACC and NMI are quite popular evaluation indicators in the field of machine learning, which can effectively measure the degree of matching between the clustering results and the actual class labels.…”

Section: Evaluation Metricsmentioning

confidence: 99%

“…Although a lot of achievements have been made in the research of deep clustering [43,44,45,46], there are few applications in the field of bearing fault diagnosis. An et al [47] proposed a deep clustering method based on autoencoded embedding and local manifold learning. Experiments on CWRU bearing dataset showed that this method could find the optimal clustering manifold and got better clustering results than current advanced baseline methods.…”

Section: Introductionmentioning

confidence: 99%

A multi-stage semi-supervised improved deep embedded clustering method for bearing fault diagnosis under the situation of insufficient labeled samples

Sun¹,

Yu²

2021

Preprint

View full text Add to dashboard Cite

Intelligent data-driven fault diagnosis methods have been widely applied, but most of these methods need a large number of high-quality labeled samples. It costs a lot of labor and time to label data in actual industrial processes, which challenges the application of intelligent fault diagnosis methods. To solve this problem, a multi-stage semisupervised improved deep embedded clustering (MS-SSIDEC) method is proposed for the bearing fault diagnosis under the insufficient labeled samples situation. This method includes three stages: pre-training, deep clustering and enhanced supervised learning. In the first stage, a skip-connection based convolutional auto-encoder (SCCAE) is proposed and pre-trained to automatically learn low-dimensional representations. In the second stage, a semisupervised improved deep embedded clustering (SSIDEC) model that integrates the pre-trained auto-encoder with a clustering layer is proposed for deep clustering. Additionally, virtual adversarial training (VAT) is introduced as a regularization term to overcome the overfitting in the model's training. In the third stage, high-quality clustering results obtained in the second stage are assigned to unlabeled samples as pseudo labels. The labeled dataset is augmented by those pseudo-labeled samples and used to train a bearing fault discriminative model. The effectiveness of the method is evaluated on the Case Western Reserve University (CWRU) bearing dataset. The results show that the method can not only satisfy the semi-supervised learning under a small number of labeled samples, but also solve the problem of unsupervised learning, and has achieved better results than traditional diagnosis methods. This method provides a new research idea for fault diagnosis with limited labeled samples by effectively using unsupervised data.

show abstract

Deep Clustering Bearing Fault Diagnosis Method Based on Local Manifold Learning of an Autoencoded Embedding

Cited by 13 publications

References 26 publications

Towards Data-Driven Decision-Making in the Korean Film Industry: An XAI Model for Box Office Analysis Using Dimension Reduction, Clustering, and Classification

Towards Data-Driven Decision-Making in the Korean Film Industry: An XAI Model for Box Office Analysis Using Dimension Reduction, Clustering, and Classification

Artificial Intelligence-Based Technique for Fault Detection and Diagnosis of EV Motors: A Review

A multi-stage semi-supervised improved deep embedded clustering method for bearing fault diagnosis under the situation of insufficient labeled samples

Contact Info

Product

Resources

About