Journal of information and communication convergence engineering

The Korea Institute of Information and Commucation Engineering (한국정보통신학회)
권호 표지
DOI QR코드

DOI QR Code

Fault Diagnosis Management Model using Machine Learning

  • Yang, Xitong (Division of HSBC Software Development Limited Xi An Branch) ;
  • Lee, Jaeseung (Department of Computer Engineering, Pai Chai University) ;
  • Jung, Heokyung (Department of Computer Engineering, Pai Chai University)
  • Received : 2019.03.21
  • Accepted : 2019.05.22
  • Published : 2019.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

Based on the concept of Industry 4.0, various sensors are attached to facilities and equipment to collect data in real time and diagnose faults using analyzing techniques. Diagnostic technology continuously monitors faults or performance degradation of facilities and equipment in operation and diagnoses abnormal symptoms to ensure safety and availability through maintenance before failure occurs. In this paper, we propose a model to analyze the data and diagnose the state or failure using machine learning. The diagnosis model is based on a support vector machine (SVM)-based diagnosis model and a self-learning one-class SVM-based diagnostic model. In the future, it is expected that this model can be applied to facilities used in the entire industry by applying the actual data to the diagnostic model proposed in this paper, conducting the experiment, and verifying it through the model performance evaluation index.

Keywords

E1ICAW_2019_v17n2_128_f0001.png 이미지

Fig. 1. Diagnosis model use case diagram.

E1ICAW_2019_v17n2_128_f0002.png 이미지

Fig. 2. Data preprocessing of SVM-based diagnosis model.

E1ICAW_2019_v17n2_128_f0003.png 이미지

Fig. 3. Process flowchart of the SVM-based diagnosis model.

E1ICAW_2019_v17n2_128_f0004.png 이미지

Fig. 4. Functions of SVM-based diagnosis model.

E1ICAW_2019_v17n2_128_f0005.png 이미지

Fig. 5. Data preprocessing of one-class SVM-based diagnosis model.

E1ICAW_2019_v17n2_128_f0006.png 이미지

Fig. 6. Process flowchart of one-class SVM-based diagnosis model.

E1ICAW_2019_v17n2_128_f0007.png 이미지

Fig. 7. Functions of one-class SVM-based diagnosis model.

E1ICAW_2019_v17n2_128_f0008.png 이미지

Fig. 8. Class diagram of SVM-based diagnosis model.

E1ICAW_2019_v17n2_128_f0009.png 이미지

Fig. 9. Sequence diagram of SVM-based diagnosis model.

E1ICAW_2019_v17n2_128_f0010.png 이미지

Fig. 10. Class diagram of one-class SVM-based diagnosis model.

E1ICAW_2019_v17n2_128_f0011.png 이미지

Fig. 11. Sequence diagram of one-class SVM-based diagnosis model.

E1ICAW_2019_v17n2_128_f0012.png 이미지

Fig. 12. ROC curve of SVM-based diagnosis model.

E1ICAW_2019_v17n2_128_f0013.png 이미지

Fig. 13. Accuracy of SVM-based diagnosis model.

E1ICAW_2019_v17n2_128_f0014.png 이미지

Fig. 14. Results of one-class SVM-based diagnosis model.

E1ICAW_2019_v17n2_128_f0015.png 이미지

Fig. 15. AUC of one-class SVM-based diagnostic model.

Table 1. Development environment

E1ICAW_2019_v17n2_128_t0001.png 이미지

Table 2. Accuracy of SVM-based diagnostic model by experiment iteration

E1ICAW_2019_v17n2_128_t0002.png 이미지

Table 3. Accuracy of one class SVM-based diagnostic model by experiment iteration

E1ICAW_2019_v17n2_128_t0003.png 이미지

References

  1. S.M. Rezvanizaniani, J. Dempsey, and J. Lee, "An effective predictive maintenance approach based on historical maintenance data using a probabilistic risk assessment: PHM14 data challenge," Unpublished, 2014, [Online] Available: http://rgdoi.net/10.13140/RG.2.1.2076.2640.
  2. C. Berenguer, M. Fouladirad, and E. Deloux, "Health-and-usage-based maintenance policies for a partially observable deteriorating system," Proceedings of the Institution of Mechanical Engineers, vol. 230, no. 1, pp. 120-129, 2015.
  3. A. Chaudhuri, "Predictive Maintenance for Industrial IoT of Vehicle Fleets using Hierarchical Modified Fuzzy Support Vector Machine," Unpublished, 2018, [Online] Available: https://arxiv.org/abs/1806.09612.
  4. Z. Wenjin, F. Mitra, and B. Berenguer, "A multi-level maintenance policy for a multi-component and multifailure mode system with two independent failure modes," Reliability Engineering & System Safety, vol. 153, pp. 50-63, 2016. https://doi.org/10.1016/j.ress.2016.03.020
  5. C. Prosper and D. West. "Case Study Applied Machine Learning to Optimise PCP Completion Design in a CBM Field," SPE Asia Pacific Oil and Gas Conference and Exhibition, vol. 10, no. 2018, 2018. DOI: 10.2118/192002-MS.
  6. A. Coraddu, L. Oneto, A. Ghio, S. Savio, D. Anguita, and M. Figari, "Machine learning approaches for improving condition-based maintenance of naval propulsion plants." Proceedings of the Institution of Mechanical Engineers, Part M: Journal of Engineering for the Maritime Environment, vol. 230, no. 1, pp. 136-153, 2014. DOI: 10.1177/1475090214540874.
  7. I. A. Lawal and S. A. Abdulkarim, "Adaptive SVM for data stream classification," South African Computer Journal, vol. 29, no. 1, pp. 27-42, 2017. DOI: 10.18489/sacj.v29i.414.
  8. G. J. J. Burg and P. J. F. Groenen, "GenSVM: A generalized multiclass support vector machine," The Journal of Machine Learning Research, vol. 17, no. 1, pp. 1-42, 2016.
  9. K. A. Korba and F. Arbaoui, "SVM Multi-Classification of Induction Machine's bearings defects using Vibratory Analysis based on Empirical Mode Decomposition," International Journal of Applied Engineering Research, vol. 13, no. 9, pp. 6579-6586, 2018.
  10. D. Chen, "Fault Classification Research of Analog Electronic Circuits Based on Support Vector Machine," Chemical Engineering Transactions, vol. 51, pp. 1333-1338, 2016.
  11. Y. Prasad, K. K. Biswas, and P. Singla, "Feature selection using one class svm: A new perspective," MLCB, 2013, [online] Available: https://arxiv.org/abs/1508.07535.
  12. A. Thomas, V. Feuillard, and A. Gramfort, "Calibration of One-Class SVM for MV set estimation," arXiv preprint arXiv:1508.07535, 2015, [Online] Available: https://arxiv.org/abs/1508.07535.
  13. D. Droghini, D. Ferretti, E. Principi, S. Squartini, and F. Piazza., "A combined one-class SVM and template-matching approach for user-aided human fall detection by means of floor acoustic features," Computational Intelligence and Neuroscience 2017, 2017, [Online] Available:https://www.hindawi.com/journals/cin/2017/1512676/.
  14. E. Burnaev and D. Smolyakov, "One-class SVM with privileged information and its application to malware detection," arXiv preprint arXiv:1609.08039, 2016, [Online] Available: https://arxiv.org/abs/1609.08039.
  15. A. Saxenan, K. Goebel, D. Simon, and N. Eklund, "Damage propagation modeling for aircraft engine run-to-failure simulation," inProceeding of 2008 International Conference on Prognostics and Health Management, 2018. DOI: 10.1109/PHM.2008.4711414.

Cited by

  1. 딥러닝 기반의 구조물 화재 재난 시 최적 대피로 안내 시스템 vol.23, pp.11, 2019, https://doi.org/10.6109/jkiice.2019.23.11.1371
  2. Intelligent Fault Detection and Identification Approach for Analog Electronic Circuits Based on Fuzzy Logic Classifier vol.10, pp.23, 2019, https://doi.org/10.3390/electronics10232888