Proficiency of Physics Informed Machine Learning in Multi-component Fault Recognition of Rotational Machines under Different Speed Conditions
##plugins.themes.bootstrap3.article.main##
##plugins.themes.bootstrap3.article.sidebar##
Published
May 16, 2025
S Sowmya
Harikrishnan Nair
M Saimurugan
Naveen Venkatesh
Abstract
Understanding the limitations of incorporating conventional machine learning synergy led to the inclusion of physics knowledge. This study presents the potency of physics-informed feature engineering for machine learning to enhance fault detection in gears, shafts, and bearings at three constant-speed running conditions. AI models such as Decision Tree (DT), Random Forest (RF), and Support Vector Machine-Radial Basis Function (SVM-RBF) are constructed to verify traditional statistical performance metric and physics-based signal descriptors. Additionally, time-frequency domain representation as spectrogram images is fed into the CNN-oriented ResNet-152 architecture to demonstrate the skillfulness of the model’s ability. Based on the results obtained, RF is observed to be supreme with 98.42% upon applying physics-centric parameters when compared with statistical variables. To make an inference, further comparison of the best classification model’s accuracy using physics expertise when accounted with ResNet image-based categorization, physics-grounded RF models have premier achievements. Thus, it is concluded that physical laws are expedient in offering exceptional outcomes for identifying various defects in complex industrial rotary machines in different operating modes.
##plugins.themes.bootstrap3.article.details##
Keywords
Fault diagnosis, Physics-informed machine learning, CNN-based ResNet, Rotational machinery
References
R. Liu, B. Yang, E. Zio, and X. Chen, “Artificial intelligence for fault diagnosis of rotating machinery: A review,” Mech Syst Signal Process, vol. 108, pp. 33–47, 2018, doi: 10.1016/j.ymssp.2018.02.016.
Y. Liu and Q. Zhao, “Diagnosis of Multiple Faults in Rotating Machinery Using Ensemble Learning,” Handbook On Computer Learning And Intelligence, vol. 2–2, pp. 635–660, 2022, doi: 10.1142/9789811247323_0016.
T. Praveen Kumar, R. Buvaanesh, M. Saimurugan, G. Naresh, S. Jenoris Muthiya, and M. Basavanakattimath, “Performance evaluation of deep learning approaches for fault diagnosis of rotational mechanical systems using vibration, sound, and acoustic emission signals,” Journal of Low Frequency Noise Vibration and Active Control, vol. 43, no. 3, pp. 1363–1380, 2024, doi: 10.1177/14613484241240927.
W. Deng, K. T. P. Nguyen, K. Medjaher, C. Gogu, and J. Morio, “Physics-informed machine learning in prognostics and health management: State of the art and challenges,” Appl Math Model, vol. 124, no. March, pp. 325–352, 2023, doi: 10.1016/j.apm.2023.07.011.
S. Shen et al., “A physics-informed deep learning approach for bearing fault detection,” Eng Appl Artif Intell, vol. 103, no. May, p. 104295, 2021, doi: 10.1016/j.engappai.2021.104295.
Z. Yang, P. Baraldi, and E. Zio, “A method for fault detection in multi-component systems based on sparse autoencoder-based deep neural networks,” Reliab Eng Syst Saf, vol. 220, no. March 2021, p. 108278, 2022, doi: 10.1016/j.ress.2021.108278.
S. Shukla, R. N. Yadav, J. Sharma, and S. Khare, “Analysis of statistical features for fault detection in ball bearing,” 2015 IEEE International Conference on Computational Intelligence and Computing Research, ICCIC 2015, 2016, doi: 10.1109/ICCIC.2015.7435755.
J. P. Xing, T. R. Lin, and D. Mba, A multi-component bearing fault diagnosis using fast iterative filtering technique, vol. 23, no. 4. Springer International Publishing, 2020. doi: 10.1007/978-3-030-57745-2.
J. Park et al., “An image-based feature extraction method for fault diagnosis of variable-speed rotating machinery,” Mech Syst Signal Process, vol. 167, Mar. 2022, doi: 10.1016/j.ymssp.2021.108524.
J. Shi, M. Liang, and Y. Guan, “Bearing fault diagnosis under variable rotational speed via the joint application of windowed fractal dimension transform and generalized demodulation: A method free from prefiltering and resampling,” Mech Syst Signal Process, vol. 68–69, pp. 15–33, Feb. 2016, doi: 10.1016/j.ymssp.2015.08.019.
J. Park, M. Hamadache, J. M. Ha, Y. Kim, K. Na, and B. D. Youn, “A positive energy residual (PER) based planetary gear fault detection method under variable speed conditions,” Mech Syst Signal Process, vol. 117, pp. 347–360, Feb. 2019, doi: 10.1016/j.ymssp.2018.08.010.
K. Zhang, B. Tang, L. Deng, and X. Liu, “A hybrid attention improved ResNet based fault diagnosis method of wind turbines gearbox,” Measurement (Lond), vol. 179, no. November 2020, p. 109491, 2021, doi: 10.1016/j.measurement.2021.109491.
T. Hertrampf and S. Oberst, “Recurrence Rate spectrograms for the classification of nonlinear and noisy signals,” Phys Scr, vol. 99, no. 3, pp. 1–15, 2024, doi: 10.1088/1402-4896/ad1fbe.
K. Rameshkumar, K. Nataraj, P. Krishnakumar, and M. Saimurugan, “Machine Learning Approach for Predicting the Solid Particle Lubricant Contamination in a Spherical Roller Bearing,” IEEE Access, vol. 12, no. April, pp. 78680–78700, 2024, doi: 10.1109/ACCESS.2024.3408807.
H. Parihar, S. Naveen Venkatesh, P. S. Anoop, and V. Sugumaran, “Application of feature fusion strategy for monitoring the condition of nitrogen filled tires using tree family of classifiers,” Phys Scr, vol. 99, no. 3, pp. 1–18, 2024, doi: 10.1088/1402-4896/ad2252.
A. Joshuva. and V. Sugumaran., “A data driven approach for condition monitoring of wind turbine blade using vibration signals through best-first tree algorithm and functional trees algorithm: A comparative study,” ISA Trans, vol. 67, pp. 160–172, 2017, doi: 10.1016/j.isatra.2017.02.002.
R. N. Toma, A. E. Prosvirin, and J. M. Kim, “Bearing fault diagnosis of induction motors using a genetic algorithm and machine learning classifiers,” Sensors (Switzerland), vol. 20, no. 7, 2020, doi: 10.3390/s20071884.
N. Kannan, M. Saimurugan, S. Sowmya, and I. Edinbarough, “Enhanced quadratic discriminant analysis with sensor signal fusion for speed-independent fault detection in rotating machines,” Meas Sci Technol, vol. 34, no. 12, 2023, doi: 10.1088/1361-6501/acf8e1.
V. S. Nair, K. Rameshkumar, and S. Saravanamurugan, “Chatter Identification in Milling of Titanium Alloy Using Machine Learning Approaches with Non-Linear Features of Cutting Force and Vibration Signatures,” Int J Progn Health Manag, vol. 15, no. 1, pp. 1–15, 2024, doi: 10.36001/ijphm.2024.v15i1.3590.
F. Hou, I. Selesnick, J. Chen, and G. Dong, “Fault diagnosis for rolling bearings under unknown time-varying speed conditions with sparse representation,” J Sound Vib, vol. 494, Mar. 2021, doi: 10.1016/j.jsv.2020.115854.
Z. Li, J. Zhou, H. Nassif, D. Coit, and J. Bae, “Fusing physics-inferred information from stochastic model with machine learning approaches for degradation prediction,” Reliab Eng Syst Saf, vol. 232, no. April 2022, p. 109078, 2023, doi: 10.1016/j.ress.2022.109078.
Y. Lei, B. Yang, X. Jiang, F. Jia, N. Li, and A. K. Nandi, “Applications of machine learning to machine fault diagnosis: A review and roadmap,” Mech Syst Signal Process, vol. 138, p. 106587, 2020, doi: 10.1016/j.ymssp.2019.106587.
L. Ge and L. J. Ge, “Feature extraction of time series classification based on multi-method integration,” Optik (Stuttg), vol. 127, no. 23, pp. 11070–11074, 2016, doi: 10.1016/j.ijleo.2016.08.089.
H. Sun and X. Hu, “Attribute selection for decision tree learning with class constraint,” Chemometrics and Intelligent Laboratory Systems, vol. 163, no. February, pp. 16–23, 2017, doi: 10.1016/j.chemolab.2017.02.004.
V. Vakharia, V. K. Gupta, and P. K. Kankar, “Bearing Fault Diagnosis Using Feature Ranking Methods and Fault Identification Algorithms,” Procedia Eng, vol. 144, pp. 343–350, 2016, doi: 10.1016/j.proeng.2016.05.142.
Y. Liu, X. Yan, C. A. Zhang, and W. Liu, “An ensemble convolutional neural networks for bearing fault diagnosis using multi-sensor data,” Sensors (Switzerland), vol. 19, no. 23, pp. 1–20, 2019, doi: 10.3390/s19235300.
Y. Peng, W. Qiao, F. Cheng, and L. Qu, “Wind Turbine Drivetrain Gearbox Fault Diagnosis Using Information Fusion on Vibration and Current Signals,” IEEE Trans Instrum Meas, vol. 70, 2021, doi: 10.1109/TIM.2021.3083891.
J. D. Martínez-Morales, E. R. Palacios-Hernández, and D. U. Campos-Delgado, “Multiple-fault diagnosis in induction motors through support vector machine classification at variable operating conditions,” Electrical Engineering, vol. 100, no. 1, pp. 59–73, 2018, doi: 10.1007/s00202-016-0487-x.
I. Attoui, N. Fergani, N. Boutasseta, B. Oudjani, and A. Deliou, “A new time–frequency method for identification and classification of ball bearing faults,” J Sound Vib, vol. 397, pp. 241–265, 2017, doi: 10.1016/j.jsv.2017.02.041.
Y. Liu and Q. Zhao, “Diagnosis of Multiple Faults in Rotating Machinery Using Ensemble Learning,” Handbook On Computer Learning And Intelligence, vol. 2–2, pp. 635–660, 2022, doi: 10.1142/9789811247323_0016.
T. Praveen Kumar, R. Buvaanesh, M. Saimurugan, G. Naresh, S. Jenoris Muthiya, and M. Basavanakattimath, “Performance evaluation of deep learning approaches for fault diagnosis of rotational mechanical systems using vibration, sound, and acoustic emission signals,” Journal of Low Frequency Noise Vibration and Active Control, vol. 43, no. 3, pp. 1363–1380, 2024, doi: 10.1177/14613484241240927.
W. Deng, K. T. P. Nguyen, K. Medjaher, C. Gogu, and J. Morio, “Physics-informed machine learning in prognostics and health management: State of the art and challenges,” Appl Math Model, vol. 124, no. March, pp. 325–352, 2023, doi: 10.1016/j.apm.2023.07.011.
S. Shen et al., “A physics-informed deep learning approach for bearing fault detection,” Eng Appl Artif Intell, vol. 103, no. May, p. 104295, 2021, doi: 10.1016/j.engappai.2021.104295.
Z. Yang, P. Baraldi, and E. Zio, “A method for fault detection in multi-component systems based on sparse autoencoder-based deep neural networks,” Reliab Eng Syst Saf, vol. 220, no. March 2021, p. 108278, 2022, doi: 10.1016/j.ress.2021.108278.
S. Shukla, R. N. Yadav, J. Sharma, and S. Khare, “Analysis of statistical features for fault detection in ball bearing,” 2015 IEEE International Conference on Computational Intelligence and Computing Research, ICCIC 2015, 2016, doi: 10.1109/ICCIC.2015.7435755.
J. P. Xing, T. R. Lin, and D. Mba, A multi-component bearing fault diagnosis using fast iterative filtering technique, vol. 23, no. 4. Springer International Publishing, 2020. doi: 10.1007/978-3-030-57745-2.
J. Park et al., “An image-based feature extraction method for fault diagnosis of variable-speed rotating machinery,” Mech Syst Signal Process, vol. 167, Mar. 2022, doi: 10.1016/j.ymssp.2021.108524.
J. Shi, M. Liang, and Y. Guan, “Bearing fault diagnosis under variable rotational speed via the joint application of windowed fractal dimension transform and generalized demodulation: A method free from prefiltering and resampling,” Mech Syst Signal Process, vol. 68–69, pp. 15–33, Feb. 2016, doi: 10.1016/j.ymssp.2015.08.019.
J. Park, M. Hamadache, J. M. Ha, Y. Kim, K. Na, and B. D. Youn, “A positive energy residual (PER) based planetary gear fault detection method under variable speed conditions,” Mech Syst Signal Process, vol. 117, pp. 347–360, Feb. 2019, doi: 10.1016/j.ymssp.2018.08.010.
K. Zhang, B. Tang, L. Deng, and X. Liu, “A hybrid attention improved ResNet based fault diagnosis method of wind turbines gearbox,” Measurement (Lond), vol. 179, no. November 2020, p. 109491, 2021, doi: 10.1016/j.measurement.2021.109491.
T. Hertrampf and S. Oberst, “Recurrence Rate spectrograms for the classification of nonlinear and noisy signals,” Phys Scr, vol. 99, no. 3, pp. 1–15, 2024, doi: 10.1088/1402-4896/ad1fbe.
K. Rameshkumar, K. Nataraj, P. Krishnakumar, and M. Saimurugan, “Machine Learning Approach for Predicting the Solid Particle Lubricant Contamination in a Spherical Roller Bearing,” IEEE Access, vol. 12, no. April, pp. 78680–78700, 2024, doi: 10.1109/ACCESS.2024.3408807.
H. Parihar, S. Naveen Venkatesh, P. S. Anoop, and V. Sugumaran, “Application of feature fusion strategy for monitoring the condition of nitrogen filled tires using tree family of classifiers,” Phys Scr, vol. 99, no. 3, pp. 1–18, 2024, doi: 10.1088/1402-4896/ad2252.
A. Joshuva. and V. Sugumaran., “A data driven approach for condition monitoring of wind turbine blade using vibration signals through best-first tree algorithm and functional trees algorithm: A comparative study,” ISA Trans, vol. 67, pp. 160–172, 2017, doi: 10.1016/j.isatra.2017.02.002.
R. N. Toma, A. E. Prosvirin, and J. M. Kim, “Bearing fault diagnosis of induction motors using a genetic algorithm and machine learning classifiers,” Sensors (Switzerland), vol. 20, no. 7, 2020, doi: 10.3390/s20071884.
N. Kannan, M. Saimurugan, S. Sowmya, and I. Edinbarough, “Enhanced quadratic discriminant analysis with sensor signal fusion for speed-independent fault detection in rotating machines,” Meas Sci Technol, vol. 34, no. 12, 2023, doi: 10.1088/1361-6501/acf8e1.
V. S. Nair, K. Rameshkumar, and S. Saravanamurugan, “Chatter Identification in Milling of Titanium Alloy Using Machine Learning Approaches with Non-Linear Features of Cutting Force and Vibration Signatures,” Int J Progn Health Manag, vol. 15, no. 1, pp. 1–15, 2024, doi: 10.36001/ijphm.2024.v15i1.3590.
F. Hou, I. Selesnick, J. Chen, and G. Dong, “Fault diagnosis for rolling bearings under unknown time-varying speed conditions with sparse representation,” J Sound Vib, vol. 494, Mar. 2021, doi: 10.1016/j.jsv.2020.115854.
Z. Li, J. Zhou, H. Nassif, D. Coit, and J. Bae, “Fusing physics-inferred information from stochastic model with machine learning approaches for degradation prediction,” Reliab Eng Syst Saf, vol. 232, no. April 2022, p. 109078, 2023, doi: 10.1016/j.ress.2022.109078.
Y. Lei, B. Yang, X. Jiang, F. Jia, N. Li, and A. K. Nandi, “Applications of machine learning to machine fault diagnosis: A review and roadmap,” Mech Syst Signal Process, vol. 138, p. 106587, 2020, doi: 10.1016/j.ymssp.2019.106587.
L. Ge and L. J. Ge, “Feature extraction of time series classification based on multi-method integration,” Optik (Stuttg), vol. 127, no. 23, pp. 11070–11074, 2016, doi: 10.1016/j.ijleo.2016.08.089.
H. Sun and X. Hu, “Attribute selection for decision tree learning with class constraint,” Chemometrics and Intelligent Laboratory Systems, vol. 163, no. February, pp. 16–23, 2017, doi: 10.1016/j.chemolab.2017.02.004.
V. Vakharia, V. K. Gupta, and P. K. Kankar, “Bearing Fault Diagnosis Using Feature Ranking Methods and Fault Identification Algorithms,” Procedia Eng, vol. 144, pp. 343–350, 2016, doi: 10.1016/j.proeng.2016.05.142.
Y. Liu, X. Yan, C. A. Zhang, and W. Liu, “An ensemble convolutional neural networks for bearing fault diagnosis using multi-sensor data,” Sensors (Switzerland), vol. 19, no. 23, pp. 1–20, 2019, doi: 10.3390/s19235300.
Y. Peng, W. Qiao, F. Cheng, and L. Qu, “Wind Turbine Drivetrain Gearbox Fault Diagnosis Using Information Fusion on Vibration and Current Signals,” IEEE Trans Instrum Meas, vol. 70, 2021, doi: 10.1109/TIM.2021.3083891.
J. D. Martínez-Morales, E. R. Palacios-Hernández, and D. U. Campos-Delgado, “Multiple-fault diagnosis in induction motors through support vector machine classification at variable operating conditions,” Electrical Engineering, vol. 100, no. 1, pp. 59–73, 2018, doi: 10.1007/s00202-016-0487-x.
I. Attoui, N. Fergani, N. Boutasseta, B. Oudjani, and A. Deliou, “A new time–frequency method for identification and classification of ball bearing faults,” J Sound Vib, vol. 397, pp. 241–265, 2017, doi: 10.1016/j.jsv.2017.02.041.
Section
Technical Papers