Journal of Applied Science and Engineering

Published by Tamkang University Press

1.30

Impact Factor

2.10

CiteScore

Baofan Chen1, Chunrong Zhou2, and Zhenghong Jiang2This email address is being protected from spambots. You need JavaScript enabled to view it.

1College of Intelligent ManufacturingChongqing Water Resources And Electric Engineering College, Yongchuan 402160 ,Chongqing China

2School of Big Data, Chongqing Vocational College of Transportation, Jiangjin 402247, Chongqing, China


 

Received: May 3, 2023
Accepted: March 4, 2024
Publication Date: May 23, 2024

 Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.


Download Citation: ||https://doi.org/10.6180/jase.202503_28(3).0015  


This research presents a new method for identifying faults in gas turbine compressors, using vibration analysis and statistical tests inside the support vector machine (SVM) algorithm. In the proposed technique, the dynamic signals are first received in the frequency domain, and the investigated frequency domain is divided into smaller ranges. Then, the RMS of each range is extracted as a frequency feature and given as input to the SVM algorithm. Because a large selection of features causes the classification accuracy to decrease, and also to select better features, the extracted feature vector is first passed through T-test filters with different significance levels and then given as input to the SVM algorithm. This method, while increasing the classification accuracy from 80.9% to 99.4%, helps the recognition of frequency ranges, which have noticeable variations under the influence of the fault. Based on the obtained results, compressor faults mostly increase the intensity of vibrations in frequency bands above 1500 Hz.


Keywords: Fault diagnosis, gas turbine compressors, vibration analysis, support vector machine.


  1. [1] M. Tiboni, C. Remino, R. Bussola, and C. Amici, (2022) “A review on vibration-based condition monitoring of rotating machinery" Applied Sciences 12(3): 972. DOI: 10.3390/app12030972.
  2. [2] G. Shen, W. Zeng, C. Han, P. Liu, and Y. Zhang, (2017) “Determination of the average maintenance time of CNC machine tools based on type II failure correlation" Eksploatacja i Niezawodno´s´c 19(4): DOI: 10.17531/ein.2017.4.15.
  3. [3] Y. Zhang, L. Mu, G. Shen, Y. Yu, and C. Han, (2019) “Fault diagnosis strategy of CNC machine tools based on cascading failure" Journal of Intelligent Manufacturing 30: 2193–2202. DOI: 10.1007/s10845-017-1382-7.
  4. [4] A. Althubaiti, F. Elasha, and J. A. Teixeira, (2022) “Fault diagnosis and health management of bearings in rotating equipment based on vibration analysis–a review" Journal of Vibroengineering 24(1): 46–74. DOI: 10.21595/jve.2021.22100.
  5. [5] C. Mongia, D. Goyal, and S. Sehgal, (2022) “Vibration response-based condition monitoring and fault diagnosis of rotary machinery" Materials Today: Proceedings 50: 679–683. DOI: 10.1016/j.matpr.2021.04.395.
  6. [6] J. Park, Y. Kim, K. Na, B. D. Youn, Y. Chen, M. J. Zuo, and Y.-C. Bae, (2022) “An image-based feature extraction method for fault diagnosis of variable-speed rotating machinery" Mechanical Systems and Signal Processing 167: 108524. DOI: 10.1016/j.ymssp.2021.108524.
  7. [7] N. Saravanan and K. Ramachandran, (2010) “Incipient gear box fault diagnosis using discrete wavelet transform (DWT) for feature extraction and classification using artificial neural network (ANN)" Expert systems with applications 37(6): 4168–4181. DOI: 10.1016/j.eswa.2009.11.006.
  8. [8] B. Li, M.-Y. Chow, Y. Tipsuwan, and J. C. Hung, (2000) “Neural-network-based motor rolling bearing fault diagnosis" IEEE transactions on industrial electronics 47(5): 1060–1069. DOI: 10.1109/41.873214.
  9. [9] Y. Kang, C.-C. Wang, Y.-P. Chang, C.-C. Hsueh, and M.-C. Chang. “Certainty improvement in diagnosis of multiple faults by using versatile membership functions for fuzzy neural networks”. In: Advances in Neural Networks-ISNN 2006: Third International Symposium on Neural Networks, Chengdu, China, May 28-June 1, 2006, Proceedings, Part III 3. Springer. 2006, 370–375. DOI: 10.1007/11760191_55.
  10. [10] X. Lou and K. A. Loparo, (2004) “Bearing fault diagnosis based on wavelet transform and fuzzy inference" Mechanical systems and signal processing 18(5): 1077–1095. DOI: 10.1016/S0888-3270(03)00077-3.
  11. [11] N. Saravanan, S. Cholairajan, and K. Ramachandran, (2009) “Vibration-based fault diagnosis of spur bevel gear box using fuzzy technique" Expert systems with applications 36(2): 3119–3135. DOI: 10.1016/j.eswa.2008.01.010.
  12. [12] Y. Lei and M. J. Zuo, (2009) “Gear crack level identification based on weighted K nearest neighbor classification algorithm" Mechanical Systems and Signal Processing 23(5): 1535–1547. DOI: 10.1016/j.ymssp.2009.01.009.
  13. [13] G. Shen, C. Han, B. Chen, L. Dong, and P. Cao. “Fault analysis of machine tools based on grey relational analysis and main factor analysis”. In: Journal of physics: conference series. 1069. 1. IOP Publishing. 2018, 012112. DOI: 10.1088/1742-6596/1069/1/012112.
  14. [14] m. rezaee mousa, H. Javadian, and V. A. Maleki, (2016) “Investigation of Vibration Behavior and Crack Detection of a Cracked Short Cantilever Beam under the Axial Load" Amirkabir Journal of Mechanical Engineering 47(2): 1–12. DOI: 10.22060/mej.2016.599.
  15. [15] M. Rezaee, S. Lotfan, and V. A. Maleki, (2023) “Using disturbance function for vibration analysis of a beam with an open edge crack" arXiv preprint arXiv:2305.18297: DOI: 10.48550/arXiv.2305.18297.
  16. [16] M. Rezaee and V. A. Maleki, (2012) “Vibration analysis of a cracked pipe conveying fluid":
  17. [17] G. Eslami, V. A. Maleki, and M. Rezaee, (2016) “Effect of open crack on vibration behavior of a fluid-conveying pipe embedded in a visco-elastic medium" Latin American Journal of Solids and Structures 13: 136–154. DOI: 10.1590/1679-78251986.
  18. [18] Z. Zhang and Q. Yang, (2022) “Unsupervised feature learning with reconstruction sparse filtering for intelligent fault diagnosis of rotating machinery" Applied Soft Computing 115: 108207. DOI: 10.1016/j.asoc.2021.108207.
  19. [19] E. Q. Wu, J. Wang, X.-Y. Peng, P. Zhang, R. Law, X. Chen, and J.-x. Lin, (2019) “Fault diagnosis of rotating machinery using Gaussian process and EEMD-treelet" International Journal of Adaptive Control and Signal Processing 33(1): 52–73. DOI: 10.1002/acs.2952.
  20. [20] X. Jiang, Q. Song, H. Wang, G. Du, J. Guo, C. Shen, and Z. Zhu, (2022) “Central frequency mode decomposition and its applications to the fault diagnosis of rotating machines" Mechanism and Machine Theory 174: 104919. DOI: 10.1016/j.mechmachtheory.2022.104919.
  21. [21] C. Rajeswari, B. Sathiyabhama, S. Devendiran, and K. Manivannan, (2014) “A gear fault identification using wavelet transform, rough set based GA, ANN and C4. 5 algorithm" Procedia Engineering 97: 1831–1841. DOI: 10.1016/j.proeng.2014.12.337.
  22. [22] D. Bordoloi and R. Tiwari, (2014) “Support vector machine based optimization of multi-fault classification of gears with evolutionary algorithms from time–frequency vibration data" Measurement 55: 1–14. DOI: 10.1016/j.measurement.2014.04.024.
  23. [23] L. Lu, J. Yan, and C. W. de Silva, (2015) “Dominant feature selection for the fault diagnosis of rotary machines using modified genetic algorithm and empirical mode decomposition" Journal of Sound and Vibration 344: 464–483. DOI: 10.1016/j.jsv.2015.01.037.
  24. [24] O. D. Mohammed, M. Rantatalo, J.-O. Aidanpää, and U. Kumar, (2013) “Vibration signal analysis for gear fault diagnosis with various crack progression scenarios" Mechanical systems and signal processing 41(1-2): 176–195. DOI: 10.1016/j.ymssp.2013.06.040.
  25. [25] G. Jahangiri, S. R. Nabavian, M. R. Davoodi, B. N. Neya, and S. Mostafavian, (2020) “Effect of noise on output-only modal identification of beams" arXiv preprint arXiv:2008.10416: DOI: 10.48550/arXiv.2008.10416.
  26. [26] M. Hernandez-Vargas, E. Cabal-Yepez, and A. GarciaPerez, (2014) “Real-time SVD-based detection of multiple combined faults in induction motors" Computers & Electrical Engineering 40(7): 2193–2203. DOI: 10.1016/j.compeleceng.2013.12.020.
  27. [27] Y. Tang, X. Xiao, X. Yang, and B. Lei, (2023) “Research on a small sample feature transfer method for fault diagnosis of reciprocating compressors" Journal of Loss Prevention in the Process Industries 85: 105163. DOI: 10.1016/j.jlp.2023.105163.
  28. [28] Y. He, J. Huang, and B. Zhang, (2012) “Approximate entropy as a nonlinear feature parameter for fault diagnosis in rotating machinery" Measurement Science and Technology 23(4): 045603. DOI: 10.1088/0957-0233/23/4/045603.
  29. [29] J. Xie, M. Sage, and Y. F. Zhao, (2023) “Feature selection and feature learning in machine learning applications for gas turbines: A review" Engineering Applications of Artificial Intelligence 117: 105591. DOI: 10.1016/j.engappai.2022.105591.
  30. [30] F. Hidalgo-Mompeán, J. F. G. Fernandez, G. CerruelaGarcia, and A. C. Marquez, (2021) “Dimensionality analysis in machine learning failure detection models. A case study with LNG compressors" Computers in Industry 128: 103434. DOI: 10.1016/j.compind.2021.103434.
  31. [31] M. Mousavi, A. Chaibakhsh, A. Jamali, M. Kordestani, and M. Saif, (2022) “A new fault diagnosis approach for heavy-duty gas turbines" IEEE/ASME Transactions On Mechatronics 27(5): 3339–3349. DOI: 10.1109/TMECH.2021.3138834.
  32. [32] E. Eslami and H.-B. Yun, (2023) “Comparison of deep convolutional neural network classifiers and the effect of scale encoding for automated pavement assessment" Journal of Traffic and Transportation Engineering (English Edition) 10(2): 258–275. DOI: 10.1016/j.jtte.2022.08.002.
  33. [33] B. H. K. Masjidi, S. Bahmani, F. Sharifi, M. Peivandi, M. Khosravani, and A. H. Mohammed, (2022) “Research Article CT-ML: Diagnosis of Breast Cancer Based on Ultrasound Images and Time-Dependent Feature Extraction Methods Using Contourlet Transformation and Machine Learning": DOI: 10.1155/2022/1493847.
  34. [34] R. Iranmanesh, A. Pourahmad, D. S. Shabestani, S. S. Jazayeri, H. Sadeqi, J. Akhavan, and A. Tounsi, (2023) “Wavelet-artificial neural network to predict the acetone sensing by indium oxide/iron oxide nanocomposites" Scientific Reports 13(1): 4266. DOI: 10.1038/s41598-023-29898-x.
  35. [35] M. Rezaei, E. Rahmani, S. J. Khouzani, M. Rahmannia, E. Ghadirzadeh, P. Bashghareh, F. Chichagi, S. S. Fard, S. Esmaeili, R. Tavakoli, et al., (2023) “Role of artificial intelligence in the diagnosis and treatment of diseases" Kindle 3(1): 1–160.
  36. [36] H. E. Chimeh, S. Nabavi, M. Al Janaideh, and L. Zhang, (2021) “Deep-learning-based optimization for a low-frequency piezoelectric MEMS energy harvester" IEEE Sensors Journal 21(19): 21330–21341. DOI: 10.1109/JSEN.2021.3102537.
  37. [37] E. Eslami and H.-B. Yun, (2021) “Attention-based multiscale convolutional neural network (A+ MCNN) for multi-class classification in road images" Sensors 21(15): 5137. DOI: 10.3390/s21155137.
  38. [38] E. Eslami, H.-B. Yun, et al., (2022) “Improvement of multiclass classification of pavement objects using intensity and range images" Journal of Advanced Transportation 2022: DOI: 10.1155/2022/4684669.
  39. [39] C. Han and X. Fu, (2023) “Challenge and opportunity: deep learning-based stock price prediction by using bidirectional LSTM model" Frontiers in Business, Economics and Management 8(2): 51–54. DOI: 10.54097/fbem.v8i2.6616.
  40. [40] Y. Essam, Y. F. Huang, J. L. Ng, A. H. Birima, A. N. Ahmed, and A. El-Shafie, (2022) “Predicting streamflow in Peninsular Malaysia using support vector machine and deep learning algorithms" Scientific reports 12(1): 3883. DOI: 10.1038/s41598-022-07693-4.
  41. [41] T. K. Kim, (2015) “T test as a parametric statistic" Korean journal of anesthesiology 68(6): 540. DOI: 10.4097/kjae.2015.68.6.540.
  42. [42] P. Ebrahimi, A. Salamzadeh, M. Soleimani, S. M. Khansari, H. Zarea, and M. Fekete-Farkas, (2022) “Startups and consumer purchase behavior: Application of support vector machine algorithm" Big Data and Cognitive Computing 6(2): 34. DOI: 10.3390/bdcc6020034.
  43. [43] J. Cardoso-Fernandes, A. C. Teodoro, A. Lima, and E. Roda-Robles, (2020) “Semi-automatization of support vector machines to map lithium (Li) bearing pegmatites" Remote Sensing 12(14): 2319. DOI: 10.3390/rs12142319.
  44. [44] M. Tanveer, T. Rajani, R. Rastogi, Y.-H. Shao, and M. Ganaie, (2022) “Comprehensive review on twin support vector machines" Annals of Operations Research: 1– 46. DOI: 10.1007/s10479-022-04575-w.