Fault diagnosis of machines operating in variable conditions using artificial neural network not requiring training data from a faulty machine

• Autorzy: Pawlik Paweł , Kania Konrad , Przysucha Bartosz

Identyfikatory

DOI

10.17531/ein/168109

• Języki publikacji: EN

Abstrakty

EN

The fault diagnosis for maintenance of machines operating in variable conditions requires special dedicated methods. Variable load or temperature conditions affect the vibration signal values. The article presents a new approach to diagnosing rotating machines using an artificial neural network, the training of which does not require data from the damaged machine. This is a new approach not previously found in the literature. Until now, neural networks have been used for machine diagnosis in the form of classifiers, where data from individual faults were required. A new diagnostic parameter rDPNS (Relative Differences Product of Network Statistics) as a function of the machine's shaft order was proposed as a kind of new order spectrum independent of the machine's operating conditions. The presented work analyses the use of the proposed method to diagnose misalignment and unbalance. The results of an experiment carried out in the laboratory demonstrated the effectiveness of the proposed method.

Słowa kluczowe

EN

fault diagnosis; vibroacoustic diagnostics; deep learning; neural networks; maintenance of technical systems

• Wydawca: Polskie Naukowo-Techniczne Towarzystwo Eksploatacyjne
• Czasopismo: Eksploatacja i Niezawodność
• Rocznik: 2023
• Tom: Vol. 25, no. 3
• Strony: art. no. 168109
• Opis fizyczny: Bibliogr. 46 poz., rys. tab., wykr.

Twórcy

autor

Pawlik Paweł

• Department of Mechanics and Vibroacoustics, AGH University of Science and Technology, Poland

• https://orcid.org/0000-0002-2654-6138

autor

Kania Konrad

• Department of Quantitative Methods in Management, Lublin University of Technology, Poland

• https://orcid.org/0000-0003-1545-0891

autor

Przysucha Bartosz

• Department of Quantitative Methods in Management, Lublin University of Technology, Poland

• https://orcid.org/0000-0002-1117-8088

Bibliografia

• 1. Lei Y, Lin J, Zuo M J, He Z. Condition monitoring and fault diagnosis of planetary gearboxes: A review. Measurement 2014;48:292–305. https://doi.org/10.1016/j.measurement.2013.11.012.
• 2. Tandon N, Choudhury A. A review of vibration and acoustic measurement methods for the detection of defects in rolling element bearings. Tribol Int 2000;32:469–80. https://doi.org/10.1016/S0301-679X(99)00077-8.
• 3. Randall R B, Antoni J. Rolling element bearing diagnostics-A tutorial. Mech Syst Signal Process 2011;25:485–520. https://doi.org/10.1016/j.ymssp.2010.07.017.
• 4. ISO/TC 108/SC 2. ISO - ISO 20816-1:2016 - Mechanical vibration — Measurement and evaluation of machine vibration — Part 1: General guidelines. 2016.
• 5. Randall R B. Vibration-based diagnostics of gearboxes under variable speed and load conditions. Meccanica 2016;51:3227–39. https://doi.org/10.1007/s11012-016-0583-z.
• 6. Antoniadou I, Manson G, Staszewski W J, Barszcz T, Worden K. A time–frequency analysis approach for condition monitoring of a wind turbine gearbox under varying load conditions. Mech Syst Signal Process 2015;64–65:188–216. https://doi.org/10.1016/j.ymssp.2015.03.003.
• 7. Chen Z, Chen J, Xie Z, Xu E, Feng Y, Liu S. Multi-expert Attention Network with Unsupervised Aggregation for long-tailed fault diagnosis under speed variation 2022;252:109393. https://doi.org/10.1016/j.knosys.2022.109393.
• 8. Wang X, Zheng J, Ni Q, Pan H, Zhang J. Traversal index enhanced-gram (TIEgram): A novel optimal demodulation frequency band selection method for rolling bearing fault diagnosis under non-stationary operating conditions. Mech Syst Signal Process 2022;172:109017. https://doi.org/10.1016/J.YMSSP.2022.109017.
• 9. Guan Y, Liang M, Necsulescu D S. Velocity synchronous bilinear distribution for planetary gearbox fault diagnosis under non-stationary conditions. J Sound Vib 2019;443:212–29. https://doi.org/10.1016/J.JSV.2018.11.039.
• 10. Gade S, Herlufsen H, Konstantin-Hansen H, Wismer N J. Order Tracking Analysis. vol. 2. Nærum: Brüel & Kjær; 1995.
• 11. Borghesani P, Pennacchi P, Randall R B, Ricci R. Order tracking for discrete-random separation in variable speed conditions. Mech Syst Signal Process 2012;30:1–22. https://doi.org/10.1016/j.ymssp.2012.01.015.
• 12. Fyfe K R, Munck E D S. Analysis of computed order tracking. Mech Syst Signal Process 1997;11:187–205. https://doi.org/10.1006/mssp.1996.0056.
• 13. Bartelmus W, Zimroz R. A new feature for monitoring the condition of gearboxes in non-stationary operating conditions. Mech Syst Signal Process 2009;23:1528–34. https://doi.org/10.1016/j.ymssp.2009.01.014.
• 14. Cheng W, Gao R X, Wang J, Wang T, Wen W, Li J. Envelope deformation in computed order tracking and error in order analysis. Mech Syst Signal Process 2014;48:92–102. https://doi.org/10.1016/j.ymssp.2014.03.004.
• 15. Pawlik P, Kania K, Przysucha B. The Use of Deep Learning Methods in Diagnosing Rotating Machines Operating in Variable Conditions. Energies (Basel) 2021;14:4231. https://doi.org/10.3390/EN14144231.
• 16. Kumar A, Gandhi C P, Zhou Y, Kumar R, Xiang J. Latest developments in gear defect diagnosis and prognosis: A review. Measurement 2020;158:107735. https://doi.org/10.1016/j.measurement.2020.107735.
• 17. Zuber N, Bajrić R. Gearbox faults feature selection and severity classificationusing machine learning. Eksploatacja i Niezawodnosc – Maintenance and Reliability 2020;22:748–56. https://doi.org/10.17531/ein.2020.4.19.
• 18. Ilić D, Milošević D, Jovanović Z, Cvjetković M, Vulić M. MLP ANN Condition Assessment Model of the Turbogenerator Shaft A6 HPP Đerdap 2. Technical Gazette 2021;28:291–6. https://doi.org/10.17559/TV-20190510052210.
• 19. Vinokur A I, Kulikov G B, Suslov M V, Petrov V P, Bykov A V, Litunov S N, et al. Diagnostics of rolling bearings using artificialneural networks. J Phys Conf Ser 1901:12027. https://doi.org/10.1088/1742-6596/1901/1/012027.
• 20. Haj Mohamad T, Nataraj C, Haj Mohamad T, Nataraj C. Gear Fault Diagnostics Using Extended Phase Space Topology. Annual Conference Of The Prognostics And Health Management Society, 2017, p. 1–9. https://doi.org/10.1115/1.4040041.
• 21. Soualhi M, Nguyen K T P, Soualhi A, Medjaher K, Hemsas K E. Health monitoring of bearing and gear faults by using a new health indicator extracted from current signals. Measurement (Lond) 2019;141:37–51. https://doi.org/10.1016/j.measurement.2019.03.065.
• 22. Afia A, Rahmoune C, Benazzouz D, Merainani B, Fedala S. New intelligent gear fault diagnosis method based on Autogram and radial basis function neural network. Advances in Mechanical Engineering 2020;12:1–15. https://doi.org/10.1177/1687814020916593.
• 23. Dabrowski D. Condition monitoring of planetary gearbox by hardware implementation of artificial neural networks. Measurement (Lond) 2016;91:295–308. https://doi.org/10.1016/j.measurement.2016.05.056.
• 24. Kozłowski E, Borucka A, Świderski A, Skoczyński P. Classification Trees in the Assessment of the Road–Railway Accidents Mortality. Energies 2021, Vol 14, Page 3462 2021;14:3462. https://doi.org/10.3390/EN14123462.
• 25. Su H, Yang X, Xiang L, Hu A, Xu Y. A novel method based on deep transfer unsupervised learning network for bearing fault diagnosis under variable working condition of unequal quantity. Knowl Based Syst 2022;242:108381. https://doi.org/10.1016/J.KNOSYS.2022.108381.
• 26. Wang L, Han M, Li X, Zhang N, Cheng H. Review of Classification Methods on Unbalanced Data Sets. IEEE Access 2021;9:64606–28. https://doi.org/10.1109/ACCESS.2021.3074243.
• 27. Konno T, Iwazume M. Cavity Filling: Pseudo-Feature Generation for Multi-Class Imbalanced Data Problems in Deep Learning 2018. https://doi.org/10.48550/arxiv.1807.06538.
• 28. Lin L, Guo S. Text Classification Feature Extraction Method Based on Deep Learning for Unbalanced Data Sets. Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST 2021;347:320–31. https://doi.org/10.1007/978-3-030-67871-5_29/COVER.
• 29. Gecgel O, Ekwaro-Osire S, Dias J P, Serwadda A, Alemayehu F M, Nispel A. Gearbox Fault Diagnostics Using Deep Learning with Simulated Data. IEEE International Conference on Prognostics and Health Management (ICPHM)978-1-5386-8357-6/19/$31.00 ©2019 IEEE, 2019. https://doi.org/10.1109/ICPHM.2019.8819423.
• 30. Rymarczyk T, Przysucha B, Pawlik P. Analysis of multi-source data for monitoring and control of intelligent technological systems. Przegląd Elektrotechniczny 2020;1:97–100. https://doi.org/10.15199/48.2020.09.20.
• 31. Peruń G, Łazarz B. Modelling of Power Transmission Systems for Design Optimization and Diagnostics of Gear in Operational Conditions. Solid State Phenomena 2014;210:108–14. https://doi.org/10.4028/www.scientific.net/SSP.210.108.
• 32. Kozłowski E, Borucka A, Liu Y, Mazurkiewicz D. Conveyor Belts Joints Remaining Life Time Forecasting with the Use of Monitoring Data and Mathematical Modelling. In: Machado J, Soares F, Trojanowska J, Yildirim S, editors. Innovations in Mechatronics Engineering, Springer Science and Business Media Deutschland GmbH; 2022, p. 44–54. https://doi.org/10.1007/978-3-030-79168-1_5/COVER.
• 33. National Instruments Corporation. LabVIEW, Order Analysis Toolkit User Manual. Austin, Texas: 2005.
• 34. Cempel C. Application of TRIZ approach to machine vibration condition monitoring problems. Mech Syst Signal Process 2013;41:328–34. https://doi.org/10.1016/j.ymssp.2013.07.011.
• 35. Nakamura T, Okuno M, Yoshikawa M, Itoh Y. Quantitative characterization of nonlinear impedance and load characteristic of 50-kW-class fully superconducting induction/synchronous motor. Physica C: Superconductivity and Its Applications 2020;578:1353662. https://doi.org/10.1016/J.PHYSC.2020.1353662.
• 36. McCann M T, Jin K H, Unser M. Convolutional neural networks for inverse problems in imaging: A review. IEEE Signal Process Mag 2017;34:85–95. https://doi.org/10.1109/MSP.2017.2739299.
• 37. Lin S B. Limitations of shallow nets approximation. Neural Networks 2017;94:96–102. https://doi.org/10.1016/J.NEUNET.2017.06.016.
• 38. Guo Z C, Shi L, Lin S B. Realizing Data Features by Deep Nets. IEEE Trans Neural Netw Learn Syst 2020;31:4036–48. https://doi.org/10.1109/TNNLS.2019.2951788.
• 39. Kłosowski G, Rymarczyk T, Kania K, Świć A, Cieplak T. Maintenance of industrial reactors supported by deep learning driven ultrasound tomography. Eksploatacja i Niezawodnosc – Maintenance and Reliability 2020;22:138–47. https://doi.org/10.17531/ein.2020.1.16.
• 40. Rymarczyk T, Kłosowski G. Innovative methods of neural reconstruction for tomographic images in maintenance of tank industrial reactors. Eksploatacja i Niezawodnosc 2019;21:261–7. https://doi.org/10.17531/EIN.2019.2.10.
• 41. Rymarczyk T, Kłosowski G. Applying Machine Learning Algorithms to Solve Inverse Problems in Electrical Tomography. MATEC Web of Conferences 2018;210:02016. https://doi.org/10.1051/matecconf/201821002016.
• 42. Utne I B. Maintenance strategies for deep-sea offshore wind turbines. Journal of Quality in Maintenance Engineerin 2010;16:367–81. https://doi.org/10.1108/13552511011084526.
• 43. Schuh P, Schneider D, Funke L, Tracht K. Cost-optimal spare parts inventory planning for wind energy systems. Logistics Research 2015;8:1–8. https://doi.org/10.1007/S12159-015-0122-7/FIGURES/4.
• 44. Cohen J. Statistical Power Analysis for the Behavioral Sciences Second Edition. New York: Lawrence Erlbaum Associates; 1988.
• 45. Lees A W. Misalignment in rigidly coupled rotors. J Sound Vib 2007;305:261–71. https://doi.org/10.1016/j.jsv.2007.04.008.
• 46. Kumar P, Hirani H. Misalignment effect on gearbox failure: An experimental study. Measurement 2021;169:108492. https://doi.org/10.1016/J.MEASUREMENT.2020.108492.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2024).