Rolling mill health states diagnosing method based on multi-sensor information fusion and improved DBNs under limited datasets

Yu, Yue; Shi, Peiming; Tian, Jinghui; Xu, Xuefang; Chen, Hua

doi:10.1016/j.isatra.2022.08.002

Cited by 20 publications

(7 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… MSIDBNs. These embed the improved single-sensor DBNs into the framework to extract the rich and complementary multi-source information from multi-source signals [ 40 ]. …”

Section: Case Validationmentioning

confidence: 99%

A Novel Hierarchical Vision Transformer and Wavelet Time–Frequency Based on Multi-Source Information Fusion for Intelligent Fault Diagnosis

Gong,

Peng

2024

Sensors

View full text Add to dashboard Cite

Deep learning (DL) has been widely used to promote the development of intelligent fault diagnosis, bringing significant performance improvement. However, most of the existing methods cannot capture the temporal information and global features of mechanical equipment to collect sufficient fault information, resulting in performance collapse. Meanwhile, due to the complex and harsh operating environment, it is difficult to extract fault features stably and extensively using single-source fault diagnosis methods. Therefore, a novel hierarchical vision transformer (NHVT) and wavelet time–frequency architecture combined with a multi-source information fusion (MSIF) strategy has been suggested in this paper to boost stable performance by extracting and integrating rich features. The goal is to improve the end-to-end fault diagnosis performance of mechanical components. First, multi-source signals are transformed into two-dimensional time and frequency diagrams. Then, a novel hierarchical vision transformer is introduced to improve the nonlinear representation of feature maps to enrich fault features. Next, multi-source information diagrams are fused into the proposed NHVT to produce more comprehensive presentations. Finally, we employed two different multi-source datasets to verify the superiority of the proposed NHVT. Then, NHVT outperformed the state-of-the-art approach (SOTA) on the multi-source dataset of mechanical components, and the experimental results show that it is able to extract useful features from multi-source information.

show abstract

“… MSIDBNs. These embed the improved single-sensor DBNs into the framework to extract the rich and complementary multi-source information from multi-source signals [ 40 ]. …”

Section: Case Validationmentioning

confidence: 99%

A Novel Hierarchical Vision Transformer and Wavelet Time–Frequency Based on Multi-Source Information Fusion for Intelligent Fault Diagnosis

Gong,

Peng

2024

Sensors

View full text Add to dashboard Cite

show abstract

“…Multi-source monitoring data can supply more rich and comprehensive information for machinery equipment health status management and can effectively boost the fault tolerance capability of the diagnostic method. 26 Hence, fusing multi-source monitoring data and mining the extensive and discriminative features embedded in them are positive for upgrading the diagnostic performance of the model. According to the discrepancy of fusion strategies, multi-source monitoring data fusion technologies can be categorized as data-level, feature-level, and decision-level fusion, 27 as demonstrated in Figure 1.…”

Section: Theoretical Backgroundmentioning

confidence: 99%

Multi-source information fusion meta-learning network with convolutional block attention module for bearing fault diagnosis under limited dataset

Song

Zhang

Dong

et al. 2023

Structural Health Monitoring

View full text Add to dashboard Cite

Applications in industrial production have indicated that the challenges of sparse fault samples and singular monitoring data will diminish the performance of deep learning-based diagnostic models to varying degrees. To alleviate the above issues, a multi-source information fusion meta-learning network with convolutional block attention module (CBAM) is proposed in this study for bearing fault diagnosis under limited dataset. This method can fully extract and exploit the complementary and enriched fault-related features in the multi-source monitoring data through the designed multi-branch fusion structure and incorporate metric-based meta-learning to enhance the fault diagnosis performance of the model under limited data samples. Furthermore, the introduction of CBAM can further assist the model to trade-off and focus on more discriminative information in both spatial and channel dimensions. Extensive experiments conducted on two bearing datasets that cover multi-source monitoring data fully demonstrate the validity and superiority of the proposed method.

show abstract

“…Most existing DL-based fault diagnosis, including Deep Belief Networks (DBNs) [2][3][4] , Convolutional Neural Networks (CNNs) [5][6][7][8] , Auto-Encoders (AEs) [9][10][11] , Long Short-Term Memory (LSTMs) [12][13][14] , Graph Neural Networks (GNNs) [15][16][17] etc., have been widely used for fault diagnosis. For example, Yu et al designed a multi-source information based on enhanced DBNs to achieve health states of the rolling mill [18] . Shi et al proposed a heterogeneous information fusion framework to diagnose mechanical faulty types [19] .…”

Section: Introductionmentioning

confidence: 99%

Weighted multi-source information fusion network-based framework for mechanical fault diagnosis

Song,

Zhang,

2024

Fourth International Conference on Mechanical Engineering, Intelligent Manufacturing, and Automation Technology (MEMAT 2023)

View full text Add to dashboard Cite

To alleviate the loss of potentially valuable and discriminative features as the number of networks increases in deep learning (DL). A weighted multi-source information fusion network-based framework is proposed for mechanical fault diagnosis. Firstly, a feature improved Deep Belief Network (FIDBNs) and a feature improved Convolutional Neural Network (FICNNNs) are designed to repetitively extract valuable information from original data. Meanwhile, an attention mechanism is adopted to further extract important fault characteristics Then, a weighted feature fusion module is used to integrate better for more diagnostic performance. Finally, an experimental dataset based on bearing failures is used to prove the effectiveness and superiority of the proposed framework compared with other methods.

show abstract

Rolling mill health states diagnosing method based on multi-sensor information fusion and improved DBNs under limited datasets

Cited by 20 publications

References 33 publications

A Novel Hierarchical Vision Transformer and Wavelet Time–Frequency Based on Multi-Source Information Fusion for Intelligent Fault Diagnosis

A Novel Hierarchical Vision Transformer and Wavelet Time–Frequency Based on Multi-Source Information Fusion for Intelligent Fault Diagnosis

Multi-source information fusion meta-learning network with convolutional block attention module for bearing fault diagnosis under limited dataset

Weighted multi-source information fusion network-based framework for mechanical fault diagnosis

Contact Info

Product

Resources

About