Deep Learning Techniques in Intelligent Fault Diagnosis and Prognosis for Industrial Systems: A Review

Qiu, Shaohua; Cui, Xiaopeng; Ping, Zuowei; Shan, Nanliang; Li, Zhong; Bao, Xianqiang; Xu, Xinghua

doi:10.3390/s23031305

Cited by 42 publications

(22 citation statements)

References 170 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep learning is a branch of machine learning that uses multiple layers of artificial neural networks to learn complex and nonlinear patterns from large amounts of data. Deep learning has shown remarkable performance in many tasks, such as image recognition [2], natural language processing [3], speech recognition [4], and computer vision [5]. Compared with traditional methods, deep learning has some advantages for FDP in electrical systems, such as being able to automatically extract key features from raw data without prior knowledge or assumptions [6], being able to handle high-dimensional and heterogeneous data with different modalities and scales [7] being able to adapt to dynamic and changing environments with online learning and transfer learning [3].…”

Section: Introductionmentioning

confidence: 99%

Research on deep-learning-based fault diagnosis and prediction methods for electrical systems

2024

International Conference on Mechatronic Engineering and Artificial Intelligence (MEAI 2023)

View full text Add to dashboard Cite

With the breakthrough progress of deep learning technology in various fields, its application in fault diagnosis and prediction of electrical systems has received more and more attention. In this paper, a deep learning-based fault diagnosis and prediction model is proposed for the complex nonlinear characteristics in electrical systems. First, key features are automatically extracted from a large amount of electrical system operation data using a multilayer autoencoder (MLAE). These features are fed into a deep neural network (DNN) for fault classification and prediction. In order to improve the robustness and accuracy of the model, an attention mechanism is introduced so that the model pays more attention to the key features related to faults during the learning process. The method demonstrates high accuracy and reliability on multiple electrical system fault datasets compared to traditional electrical system fault diagnosis methods. In addition, this study explores the interpretability.

show abstract

Section: Introductionmentioning

confidence: 99%

Research on deep-learning-based fault diagnosis and prediction methods for electrical systems

2024

International Conference on Mechatronic Engineering and Artificial Intelligence (MEAI 2023)

View full text Add to dashboard Cite

show abstract

“…Machine learning-based fault diagnosis methods often require manual involvement in the feature extraction process, leading to potential information loss. Therefore, with the advancements in neural network technology, deep learning has emerged as a prominent research area [19,20]. Deep learning methods have the ability to automatically extract features without human intervention.…”

Section: Introductionmentioning

confidence: 99%

A novel algorithm for complex transfer conditions in bearing fault diagnosis

Dong,

Su,

Jiang

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Transfer learning in bearing fault diagnosis can effectively improve model generalization and accelerate the practical application of fault diagnosis algorithms. However, previous algorithms primarily focused on simple transfer conditions like known target domain data or the same device. In industrial practice, the conditions for algorithm transfer are more complex. Therefore, cross-domain fault diagnosis under complex transfer conditions is a challenging task with significant practical value. This paper proposes a new bearing fault diagnosis algorithm based on attention mechanism and feature enhancement, which provides better feature extraction capabilities. The main approach involves performing deep aliasing on deep features and training the model to identify domain-invariant classification features under extreme conditions for effective fault diagnosis. Additionally, our network performs well in handling low signal-to-noise ratio problems. Extensive experiments were conducted on three different bearing case studies to validate the effectiveness of the proposed method, showing superior performance compared to other deep transfer learning methods.

show abstract

“…In recent years, fault diagnosis models based on machine learning (especially deep learning) have become the research mainstream in the field of intelligent fault diagnosis of machinery. Their general idea is to use a machine learning model to establish the mapping relationship between raw monitoring data (or data features) and health categories [4,5]. In terms of the encoding form of health categories, these models can be further categorized into two main groups: single-label models and multi-label models.…”

Section: Introductionmentioning

confidence: 99%

A compound fault diagnosis model for gearboxes using correlation information between single faults

Zeng,

Wang,

Cheng

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

Gearboxes are key components of rotating machinery. Performing intelligent fault diagnosis of gearboxes with condition-based monitoring information helps to make reliable decisions on equipment operation and maintenance. Besides single faults, compound faults also are common failure forms of gearboxes. Conventional intelligent diagnosis models (known as single-label models) generally treat a compound fault as a new fault type, ignoring the correlations between the compound fault and the corresponding single faults. To overcome this problem, multi-label learning has been introduced and developed into multi-label models. It is also possible that different single faults are not independent but correlated with each other. Existing multi-label models, however, usually ignore this aspect. Therefore, exploiting the correlation information between single faults can further improve multi-label models. To this end, every single fault is treated as a label node , resulting in a label graph. The feature vector of each label node is initialized by the word embedding of the corresponding single-fault label. All the word embeddings are mapped using graph convolutional networks (GCN) into the parameter vectors of a set of interdependent binary linear classifiers that can directly perform multi-label classification on health categories. Meanwhile, the adjacency matrix of the label graph is adaptively learned by self-attention (SA) from node feature vectors. In this way, a novel multi-label model based on SA and GCN (referred to as SA-GCN) is proposed for compound fault diagnosis of gearboxes. SA-GCN mainly consists of a ResNet-based fault feature learning module, an SA-based adjacency matrix learning module, and a GCN-based multi-label classifier learning module. The application results on two gearbox cases show that SA-GCN outperforms conventional single-label models as well as state-of-the-art multi-label models in terms of both the diagnostic accuracy of compound faults and the overall diagnostic accuracy. Moreover, the effects of internal modules and hyperparameters on SA-GCN are also investigated.

show abstract

Deep Learning Techniques in Intelligent Fault Diagnosis and Prognosis for Industrial Systems: A Review

Cited by 42 publications

References 170 publications

Research on deep-learning-based fault diagnosis and prediction methods for electrical systems

Research on deep-learning-based fault diagnosis and prediction methods for electrical systems

A novel algorithm for complex transfer conditions in bearing fault diagnosis

A compound fault diagnosis model for gearboxes using correlation information between single faults

Contact Info

Product

Resources

About