Intelligent fault diagnosis and visual interpretability of rotating machinery based on residual neural network

Yu, Shihang; Wang, Min; Pang, Shanchen; Song, Limei; Qiao, Sibo

doi:10.1016/j.measurement.2022.111228

Cited by 54 publications

(26 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The performance of the proposed method is evaluated based on accuracy, sensitivity, and specificity [ 32 ]. They are defined as follows:

…”

Section: Methodsmentioning

confidence: 99%

HSSG: Identification of Cancer Subtypes Based on Heterogeneity Score of A Single Gene

Pang

Zhang

et al. 2022

Cells

Self Cite

View full text Add to dashboard Cite

Cancer is a highly heterogeneous disease, which leads to the fact that even the same cancer can be further classified into different subtypes according to its pathology. With the multi-omics data widely used in cancer subtypes identification, effective feature selection is essential for accurately identifying cancer subtypes. However, the feature selection in the existing cancer subtypes identification methods has the problem that the most helpful features cannot be selected from a biomolecular perspective, and the relationship between the selected features cannot be reflected. To solve this problem, we propose a method for feature selection to identify cancer subtypes based on the heterogeneity score of a single gene: HSSG. In the proposed method, the sample-similarity network of a single gene is constructed, and pseudo-F statistics calculates the heterogeneity score for cancer subtypes identification of each gene. Finally, we construct gene-gene networks using genes with higher heterogeneity scores and mine essential genes from the networks. From the seven TCGA data sets for three experiments, including cancer subtypes identification in single-omics data, the performance in feature selection of multi-omics data, and the effectiveness and stability of the selected features, HSSG achieves good performance in all. This indicates that HSSG can effectively select features for subtypes identification.

show abstract

“…The performance of the proposed method is evaluated based on accuracy, sensitivity, and specificity [ 32 ]. They are defined as follows:

…”

Section: Methodsmentioning

confidence: 99%

HSSG: Identification of Cancer Subtypes Based on Heterogeneity Score of A Single Gene

Pang

Zhang

et al. 2022

Cells

Self Cite

View full text Add to dashboard Cite

show abstract

“…[24] applied the methodology in the monitoring of bearings and validated it in a gear fault dataset, showing that it is possible to use the methodology to identify the most attentive part of the model in relation to each type of fault. [26] used Grad-CAM and eigenvector-based class activation map (Eigen-CAM) to interpret the ResNet06 (a popular CNN architecture [50] in 4 databases, 3 bearing and 1 gearbox dataset. In order to interpret the effectiveness of the method, Grad-CAM is applied to localize the regions in the input that contribute the most to the network's prediction.…”

Section: Gradient-weighted Class Activation Mapping (Grad-cam)mentioning

confidence: 99%

“…As faults in IFD using vibration are generally identified through a visual analysis of the signal in the frequency domain, it is interesting to provide a heatmap overlaid on the input signal, identifying the most relevant frequencies for the classification. Despite the wide application in other areas, at present, Grad-CAM algorithm is seldom used in AI models for fault diagnosis [24,25,26,27].…”

Section: Introductionmentioning

confidence: 99%

Fault Diagnosis using eXplainable AI: a Transfer Learning-based Approach for Rotating Machinery exploiting Augmented Synthetic Data

Brito¹,

Brito²,

Duarte³

2022

Preprint

View full text Add to dashboard Cite

Due to the growing interest for increasing productivity and cost reduction in industrial environment, new techniques for monitoring rotating machinery are emerging. Artificial Intelligence (AI) is one of the approaches that has been proposed to analyze the collected data (e.g., vibration signals) providing a diagnosis of the asset's operating condition. It is known that models trained with labeled data (supervised) achieve excellent results, but two main problems make their application in production processes difficult: (i) impossibility or long time to obtain a sample of all operational conditions (since faults seldom happen) and (ii) high cost of experts to label all acquired data. Another limitating factor for the applicability of AI approaches in this context is the lack of interpretability of the models (black-boxes), which reduces the confidence of the diagnosis and trust/adoption from users. To overcome these problems, a new generic and interpretable approach for classifying faults in rotating machinery based on transfer learning from augmented synthetic data to real rotating machinery is here proposed, namelly FaultD-XAI (Fault Diagnosis using eXplainable AI). To provide scalability using transfer learning, synthetic vibration signals are created mimicking the characteristic behavior of failures in operation. The application of Gradient-weighted Class Activation Mapping (Grad-CAM) with 1D Convolutional Neural Network (1D CNN) allows the interpretation of results, supporting the user in decision making and increasing diagnostic confidence. The proposed approach not only obtained promising diagnostic performance, but was also able to learn characteristics used by experts to identify conditions in a source domain and apply them in another target domain. The experimental results obtained on three datasets containing different mechanical faults suggest the method offers a promising approach on exploiting transfer learning, synthetic data and explainable artificial intelligence for fault diagnosis. Lastly, to guarantee reproducibility and foster research in the field, the developed dataset is made publicly available.

show abstract

“…These methods can nd genes that effectively distinguish different cancer subtypes, but lead to slightly higher time complexity of the whole model. As a result, great computational efforts have been made to accurately identify cancer subtypes via integrative analysis of these multiomics datasets [25][26][27] .…”

Section: Introductionmentioning

confidence: 99%

MMKNF: Integrating multi-omics data to identify cancer subtypes based on multi-kernel network fusion

Zhang

Liu

et al. 2023

Preprint

View full text Add to dashboard Cite

Background The occurrence and development of cancer involves multi-level information of the system, which is highly heterogeneous. Therefore, how to effectively integrate multi-omics information to achieve accurate identification of cancer subtypes is the key to achieve precision medicine of cancer. Results In this paper, we propose a multi-kernel network fusion based on multi-omics data to identify cancer subtypes, named MMKNF. For each kind of omics data, multi-kernel functions are used to calculate the sample similarity, which can better integrate the multi-view similarity between samples. For multi-omics data, similarity network fusion (SNF) can be used to more effectively fuse the similarity of samples under different molecular features, so as to achieve more accurate clustering of samples, and then find more significant cancer subtypes. Comprehensive experiments demonstrate that MMKNF obtains more significant results than the eleven methods on six datasets in ten cancer datasets. In addition, we investigated the clinical significance of the obtained colon cancer subtypes and provided new insights into treating patients with different subtypes. Conclusion We provide a new method for the identification of cancer subtypes, named MMKNF, which also confirms the importance of cancer subtype identification in cancer treatment.

show abstract

Intelligent fault diagnosis and visual interpretability of rotating machinery based on residual neural network

Cited by 54 publications

References 29 publications

HSSG: Identification of Cancer Subtypes Based on Heterogeneity Score of A Single Gene

HSSG: Identification of Cancer Subtypes Based on Heterogeneity Score of A Single Gene

Fault Diagnosis using eXplainable AI: a Transfer Learning-based Approach for Rotating Machinery exploiting Augmented Synthetic Data

MMKNF: Integrating multi-omics data to identify cancer subtypes based on multi-kernel network fusion

Contact Info

Product

Resources

About