Advanced Industrial Fault Detection: A Comparative Analysis of Ultrasonic Signal Processing and Ensemble Machine Learning Techniques
Source abstract
Abstract
Modern condition monitoring and industrial fault prediction have advanced to include intelligent techniques, aiming to improve reliability, productivity, and safety. The integration of ultrasonic signal processing with various machine learning (ML) models can significantly enhance the efficiency of industrial fault diagnosis. In this paper, ultrasonic data are analyzed and applied to ensemble ML algorithms. Four methods for reducing dimensionality are employed to illustrate differences among acoustic faults. Different features in the time domain are extracted, and predictive ensemble models including a gradient boosting classifier (GB), stacking classifier (Stacking), voting classifier (Voting), Adaboost, Logit boost (Logit), and bagging classifier (Bagging) are implemented. To assess the model’s performance on new data during experiments, k-fold cross-validation (CV) was employed. Based on the designed workflow, GB demonstrated the highest performance, with less variation over 5 cross-folds. Finally, the real-time capability of the model was evaluated by deployment on an ARM Cortex-M4F microcontroller (MCU).
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Fault Detection and Control Systems · Anomaly Detection Techniques and Applications · Machine Fault Diagnosis Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Electrical Engineering, École de Technologie Supérieure, ETS, Montreal, QC H3C 1K3, Canada
Funding
Collaborative Research and Development · Natural Sciences and Engineering Research Council of Canada (NSERC)
References (41)
Show source-provided references
1. Integrity Assessment of Corroded Oil and Gas Pipelines Using Machine Learning: A Systematic Review10.1016/j.engfailanal.2021.105810 ↗
2. Yang, J., Li, S., Wang, Z., Dong, H., Wang, J., and Tang, S. (2020). Using Deep Learning to Detect Defects in Manufacturing: A Comprehensive Survey and Current Challenges. Materials, 13.10.3390/ma13245755 ↗
3. A review on different pipeline fault detection methods10.1016/j.jlp.2016.03.010 ↗
4. Fault detection of circulation pumps on the basis of motor current evaluation10.1109/TIA.2021.3085697 ↗
5. Prediction of Oil and Gas Pipeline Failures through Machine Learning Approaches: A Systematic Review10.1016/j.egyr.2023.08.009 ↗
6. Acoustic and Ultrasonic Techniques for Defect Detection and Condition Monitoring in Water and Sewerage Pipes: A Review10.1016/j.apacoust.2021.108282 ↗
7. Unbalance Bearing Fault Identification Using Highly Accurate Hilbert-Huang Transform Approach
8. Defect Identification for Oil and Gas Pipeline Safety Based on Autonomous Deep Learning Network10.1016/j.comcom.2022.08.001 ↗
9. Fault Diagnosis of Bearings Using Recurrences and Artificial Intelligence Techniques
10. Moshrefi, A., Gratuze, M., Tawfik, H.H., Elsayed, M.Y., and Nabki, F. (2023, January 3–8). Ensemble AI fault diagnosis model using ultrasonic microphone. Proceedings of the 2023 IEEE International Ultrasonics Symposium (IUS), Montreal, QC, Canada.10.1109/IUS51837.2023.10306888 ↗
11. Application of Dimension Analysis and Soft Competitive Tool to Predict Compound Faults Present in Rotor-Bearing Systems10.1016/j.measurement.2022.110984 ↗
12. Detection of Crankshaft Faults by Means of a Modified Welch-Bartlett Periodogram10.1016/j.engfailanal.2021.105938 ↗
13. Reviews of Bearing Vibration Measurement Using Fast Fourier Transform and Enhanced Fast Fourier Transform Algorithms10.1177/1687814018816751 ↗
14. A Novel Method to Classify Rolling Element Bearing Faults Using K-Nearest Neighbor Machine Learning Algorithm10.1115/1.4053760 ↗
15. Fault Identification in a Nonlinear Rotating System Using Dimensional Analysis (DA) and Central Composite Rotatable Design (CCRD)10.1016/j.measurement.2022.111610 ↗
16. Leak Detection and Localization Techniques in Oil and Gas Pipeline: A Bibliometric and Systematic Review10.1016/j.engfailanal.2023.107060 ↗
17. Review and Analysis of Pipeline Leak Detection Methods10.1016/j.jpse.2022.100074 ↗
18. A Novel Pipeline Leak Detection Approach Independent of Prior Failure Information10.1016/j.measurement.2020.108284 ↗
19. Wang, H., Fan, Z., Chen, X., Cheng, J., Chen, W., Wang, Z., and Bu, Y. (2022). Automated Classification of Pipeline Defects from Ultrasonic Phased Array Total Focusing Method Imaging. Energy, 5.10.1115/PVP2023-106113 ↗
20. Moshrefi, A., Tawfik, H.H., Elsayed, M.Y., and Nabki, F. (2024). Industrial fault detection employing meta ensemble model based on contact sensor ultrasonic signal. Sensors, 24.10.3390/s24072297 ↗
21. Raišutis, R., Tumšys, O., Žukauskas, E., Samaitis, V., Draudvilienė, L., and Jankauskas, A. (2023). An Inspection Technique for Steel Pipes Wall Condition Using Ultrasonic Guided Helical Waves and a Limited Number of Transducers. Materials, 16.10.3390/ma16155410 ↗
22. Norli, P., Frijlink, M., Standal, Ø.K.-V., Bjåstad, T.G., Prieur, F., and Vallée, E. (2018, January 22–25). Ultrasonic Detection of Stress Corrosion Cracks in Pipe Samples Using Guided Waves. Proceedings of the 2018 IEEE International Ultrasonics Symposium (IUS), Kobe, Japan.10.1109/ULTSYM.2018.8579864 ↗
23. Feature Extraction Method for Ultrasonic Pipeline Defects Based on Fractional-Order VMD
24. Identification method of circumferential declination based on amplitude reduction of pipeline ultrasonic internal inspection signals
25. A comparative study of breast cancer tumor classification by classical machine learning methods and deep learning method10.1007/s00138-020-01094-1 ↗
26. A survey on ensemble learning10.1007/s11704-019-8208-z ↗
27. Boosting Methods for Multi-Class Imbalanced Data Classification: An Experimental Review10.1186/s40537-020-00349-y ↗
28. Robust boosting for regression problems10.1016/j.csda.2020.107065 ↗
29. A Practical Tutorial on Bagging and Boosting Based Ensembles for Machine Learning: Algorithms, Software Tools, Performance Study, Practical Perspectives, and Opportunities10.1016/j.inffus.2020.07.007 ↗
30. Heart Diseases Prediction Based on Stacking Classifiers Model10.1016/j.procs.2023.01.140 ↗
31. Performance of Machine Learning Algorithms with Different K Values in K-Fold Cross-Validation
32. What Is an Optimal Value of K in K-Fold Cross-Validation in Discrete Bayesian Network Analysis?10.1007/s00180-020-00999-9 ↗
33. Yadav, S., and Shukla, S. (2016, January 27–28). Analysis of K-Fold Cross-Validation over Hold-Out Validation on Colossal Datasets for Quality Classification. Proceedings of the 2016 IEEE 6th International Conference on Advanced Computing (IACC), Bhimavaram, India.10.1109/IACC.2016.25 ↗
34. Feature dimensionality reduction: A review10.1007/s40747-021-00637-x ↗
35. Bearing Fault Classification of Induction Motor Using Statistical Features and Machine Learning Algorithms10.1007/978-3-030-96308-8_22 ↗
36. Principal Component Analysis (PCA)
37. McConn, J.L., Lamoureux, C.R., Poudel, S., Palsson, B.O., and Sastry, A.V. (2021). Optimal dimensionality selection for independent component analysis of transcriptomic data. BMC Bioinform., 22.10.1186/s12859-021-04497-7 ↗
38. McInnes, L., Healy, J., and Melville, J. (2018). UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction. arXiv.10.21105/joss.00861 ↗
39. Linear Discriminant Analysis: A Detailed Tutorial10.3233/AIC-170729 ↗
40. Sravani, S., and Karthikeyan, P.R. (2023). Detection of cardiovascular disease using KNN in comparison with naive bayes to measure precision, recall, and f-score. AIP Conference Proceedings, AIP Publishing.10.1063/5.0177014 ↗
41. (2020, January 01). Available online: https://www.uesystems.com/resources/sound-library/.