CoChat

An Ensemble Deep Convolutional Neural Network Model with Improved D-S Evidence Fusion for Bearing Fault Diagnosis

Open access

The DOI matches its Crossref record; 46 of the 46 references it cites were found in a registry or an index.

Abstract

Intelligent machine health monitoring and fault diagnosis are becoming increasingly important for modern manufacturing industries. Current fault diagnosis approaches mostly depend on expert-designed features for building prediction models. In this paper, we proposed IDSCNN, a novel bearing fault diagnosis algorithm based on ensemble deep convolutional neural networks and an improved Dempster–Shafer theory based evidence fusion. The convolutional neural networks take the root mean square (RMS) maps from the FFT (Fast Fourier Transformation) features of the vibration signals from two sensors as inputs. The improved D-S evidence theory is implemented via distance matrix from evidences and modified Gini Index. Extensive evaluations of the IDSCNN on the Case Western Reserve Dataset showed that our IDSCNN algorithm can achieve better fault diagnosis performance than existing machine learning methods by fusing complementary or conflicting evidences from different models and sensors and adapting to different load conditions.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.3390/s17081729

Cites

46 of 46 references verified0 citation errors · 0 not checkable

Statistics

Figures

Figure 1 The modified Gini Index curve.
Figure 1 The modified Gini Index curve.CC BY · PubMed Central
Figure 2 Flowchart of the IDSCNN based fault diagnosis.
Figure 2 Flowchart of the IDSCNN based fault diagnosis.CC BY · PubMed Central
Figure 3 The convolution neural network model used in IDSCNN.
Figure 3 The convolution neural network model used in IDSCNN.CC BY · PubMed Central
Figure 4 Bearing Structures and Fault Location Sketch Map.
Figure 4 Bearing Structures and Fault Location Sketch Map.CC BY · PubMed Central
Figure 5 Data visualization of the input data 16 × 16 RMS maps.
Figure 5 Data visualization of the input data 16 × 16 RMS maps.CC BY · PubMed Central
Figure 6 Results of the CNN Models and Proposed IDSCNN: (a–d) the results of individual CNNs trained with drive/fan end sensor signals and the IDS fusion results; and (e) IDSCNN results from fusion models with different component CNN models including fusing all 16 drive-end CNN models (ids-de-16, ids-de-32, and ids-de-all), fusing all 16 fan-end CNN models (ids-fe-16, ids-fe-32, and ids-fe-all), and fusing all models (ids-all).
Figure 6 Results of the CNN Models and Proposed IDSCNN: (a–d) the results of individual CNNs trained with drive/fan end sensor signals and the IDS fusion results; and (e) IDSCNN results from fusion models with different component CNN models including fusing all 16 drive-end CNN models (ids-de-16, ids-de-32, and ids-de-all), fusing all 16 fan-end CNN models (ids-fe-16, ids-fe-32, and ids-fe-all), and fusing all models (ids-all).CC BY · PubMed Central
Figure 7 Accuracy of the best IDSCNN models on 20 repeated experiments.
Figure 7 Accuracy of the best IDSCNN models on 20 repeated experiments.CC BY · PubMed Central
Figure 8 Comparison with other fault diagnosis models.
Figure 8 Comparison with other fault diagnosis models.CC BY · PubMed Central
Figure 9 Information fusion between drive-end and fan-end predictions: (a) confusion matrix of #7 CNN model trained with drive-end signal (See Table 5) for C→A test; (b) confusion matrix of #25 CNN model trained with fan-end signal (See Table 5) for C→A test; and (c) confusion matrix of fused model for #7 and #25 for C→A test.
Figure 9 Information fusion between drive-end and fan-end predictions: (a) confusion matrix of #7 CNN model trained with drive-end signal (See Table 5) for C→A test; (b) confusion matrix of #25 CNN model trained with fan-end signal (See Table 5) for C→A test; and (c) confusion matrix of fused model for #7 and #25 for C→A test.CC BY · PubMed Central
Figure 10 Performance comparison of DSCNN vs IDSCNN on C→A test.
Figure 10 Performance comparison of DSCNN vs IDSCNN on C→A test.CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 3

  1. Muralidharan, 2016, Bearing Fault Diagnosis Using Vibration Signals by Variational Mode Decomposition and Naïve Bayes Classifier, Int. J. Robot. Autom., 1, 1
  2. Xing, 2016, Quantitative MMM evaluation of weld levels based on information entropy and DS evidence theory, Chin. J. Sci. Instrum., 37, 610
  3. Kang, 2012, Multi-sensor information fusion algorithm based on DS evidence theory, J. Chin. Inert. Technol., 20, 670

Cited by

See all 211

Metadata

Authors
Li, S., Liu, G., Tang, X., Lu, J., & Hu, J.
Affiliations
  • Guizhou University (CN)
  • University of South Carolina (US)
Corresponding author
Hu, Jianjun
Venue
Sensors
Publisher
MDPI AG
Published
2017-07-28
Volume
17
Issue
8
Pages
1729
ISSN
1424-8220 (ISSN-L)
OpenAlex
W2741289421
Cited by
211
References
45
Citations by year
2026: 9 · 2025: 15 · 2024: 23 · 2023: 26 · 2022: 24 · 2021: 30 · 2020: 34 · 2019: 34 · 2018: 15 · 2017: 1
FWCI
14.39
Type
journal article
Language
en
Open access
Locations
  • Sensors (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • Scholar Commons (University of South Carolina) (submittedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
National Natural Science Foundation Project of China (51475097)
Topics
  • Physical Sciences › Engineering › Control and Systems Engineering › Machine Fault Diagnosis Techniques
  • Physical Sciences › Engineering › Control and Systems Engineering › Fault Detection and Control Systems
  • Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
Keywords
bearing fault diagnosis, Dempster-Shafer theory, evidence combination, vibration signals, multi-sensor fusion, distance matrix, machine condition monitoring

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.