Data fusion-based multiple fault diagnosis of rotating machines using transfer learning
DOI:
https://doi.org/10.22399/ijcesen.5103Keywords:
Data Fusion, Transfer Learning, Fault Diagnosis, Rotating Machinery, Convolutional Neural Networks (CNN).Abstract
This Study presents a fault diagnosis system, which uses data fusion together with transfer learning and multiple monotonic sensors (vibration, acoustic and temperature) to diagnose faults in rotating machinery. The system achieved an impressive overall accuracy of 99% on the combined dataset, as it utilised pre-trained convolutional neural networks (CNN), specifically ResNet50, adapted to the fault diagnosis task. The proposed system performed exceptionally well for fault classification and had particularly strong results for a number of the fault classes. For example, the inner race fault class had an outstanding recall of 1.00, demonstrating robust detection capabilities, and the outer race fault class had strong precision and recall with 0.98 and 0.98. The healthy class had outstanding precision and recall performance with values very close to 1.00. Having access to multiple sensor data sources helped to improve not only the overall classification accuracy but also the ability of the model to generalise to different operational conditions and provide consistent performance across those conditions. The presented results show the capabilities of data fusion and transfer learning for fault diagnosis and provide a scalable and effective solution for real-time, actionable data for monitoring machinery, with relatively low requirements for data labelling. The system presented has great potential to improve fault detection for industrial fault detection systems by improving reliability and reducing downtime.
References
[1] An, Zenghui, Xingxing Jiang, Jing Cao, Rui Yang, and Xuegang Li. "Self-learning transferable neural network for intelligent fault diagnosis of rotating machinery with unlabeled and imbalanced data." Knowledge-Based Systems 230 (2021): 107374. DOI: https://doi.org/10.1016/j.knosys.2021.107374
[2] Asutkar, Supriya, Chaitravi Chalke, Kajal Shivgan, and Siddharth Tallur. "TinyML-enabled edge implementation of transfer learning framework for domain generalization in machine fault diagnosis." Expert Systems with Applications 213 (2023): 119016. DOI: https://doi.org/10.1016/j.eswa.2022.119016
[3] Brito, Lucas Costa, Gian Antonio Susto, Jorge Nei Brito, and Marcus Antonio Viana Duarte. "Fault Diagnosis using eXplainable AI: A transfer learning-based approach for rotating machinery exploiting augmented synthetic data." Expert Systems with Applications 232 (2023): 120860. DOI: https://doi.org/10.1016/j.eswa.2023.120860
[4] Cha, Young-Jin, Rahmat Ali, John Lewis, and Oral Büyükӧztürk. "Deep learning-based structural health monitoring." Automation in Construction 161 (2024): 105328. DOI: https://doi.org/10.1016/j.autcon.2024.105328
[5] Chakrapani, G., and V. Sugumaran. "Transfer learning-based fault diagnosis of automobile dry clutch system." Engineering Applications of Artificial Intelligence 117 (2023): 105522. DOI: https://doi.org/10.1016/j.engappai.2022.105522
[6] Chao, Qun, Yuechen Shao, Chengliang Liu, and Xiaoxue Yang. "Health evaluation of axial piston pumps based on density weighted support vector data description." Reliability Engineering & System Safety 237 (2023): 109354. DOI: https://doi.org/10.1016/j.ress.2023.109354
[7] Chen, Qitong, Liang Chen, Qi Li, Juanjuan Shi, Zhongkui Zhu, and Changqing Shen. "A lightweight and robust model for engineering cross-domain fault diagnosis via feature fusion-based unsupervised adversarial learning." Measurement 205 (2022): 112139. DOI: https://doi.org/10.1016/j.measurement.2022.112139
[8] Ding, Yifei, Minping Jia, Jichao Zhuang, Yudong Cao, Xiaoli Zhao, and Chi-Guhn Lee. "Deep imbalanced domain adaptation for transfer learning fault diagnosis of bearings under multiple working conditions." Reliability Engineering & System Safety 230 (2023): 108890. DOI: https://doi.org/10.1016/j.ress.2022.108890
[9] Dong, Yunjia, Yuqing Li, Huailiang Zheng, Rixin Wang, and Minqiang Xu. "A new dynamic model and transfer learning based intelligent fault diagnosis framework for rolling element bearings race faults: Solving the small sample problem." ISA transactions 121 (2022): 327-348. DOI: https://doi.org/10.1016/j.isatra.2021.03.042
[10] Feng, Ke, J. C. Ji, Yongchao Zhang, Qing Ni, Zheng Liu, and Michael Beer. "Digital twin-driven intelligent assessment of gear surface degradation." Mechanical Systems and Signal Processing 186 (2023): 109896. DOI: https://doi.org/10.1016/j.ymssp.2022.109896
[11] Gao, Jiaqing, Hua Han, Zhengxiong Ren, and Yuqiang Fan. "Fault diagnosis for building chillers based on data self-production and deep convolutional neural network." Journal of Building Engineering 34 (2021): 102043. DOI: https://doi.org/10.1016/j.jobe.2020.102043
[12] Han, Te, Chao Liu, Wenguang Yang, and Dongxiang Jiang. "Learning transferable features in deep convolutional neural networks for diagnosing unseen machine conditions." ISA transactions 93 (2019): 341-353. DOI: https://doi.org/10.1016/j.isatra.2019.03.017
[13] He, You, Hesheng Tang, Yan Ren, and Anil Kumar. "A deep multi-signal fusion adversarial model-based transfer learning and residual network for axial piston pump fault diagnosis." Measurement 192 (2022): 110889. DOI: https://doi.org/10.1016/j.measurement.2022.110889
[14] Hou, Wenbo, Chunlin Zhang, Yunqian Jiang, Keshen Cai, Yanfeng Wang, and Ni Li. "A new bearing fault diagnosis method via simulation data driving transfer learning without target fault data." Measurement 215 (2023): 112879. DOI: https://doi.org/10.1016/j.measurement.2023.112879
[15] Huang, Min, Jinghan Yin, Shumin Yan, and Pengcheng Xue. "A fault diagnosis method of bearings based on deep transfer learning." Simulation Modelling Practice and Theory 122 (2023): 102659. DOI: https://doi.org/10.1016/j.simpat.2022.102659
[16] Huo, Chunran, Quansheng Jiang, Yehu Shen, Chenhui Qian, and Qingkui Zhang. "New transfer learning fault diagnosis method of rolling bearing based on ADC-CNN and LATL under variable conditions." Measurement 188 (2022): 110587. DOI: https://doi.org/10.1016/j.measurement.2021.110587
[17] El Hindi, Khalil, Hussien AlSalman, Safwan Qasem, and Saad Al Ahmadi. "Building an ensemble of fine-tuned naive Bayesian classifiers for text classification." Entropy 20, no. 11 (2018): 857. DOI: https://doi.org/10.3390/e20110857
[18] Sriranga, Nandan, Kyatsandra G. Nagananda, Rick S. Blum, A. Saucan, and Pramod K. Varshney. "Energy-efficient decision fusion for distributed detection in wireless sensor networks." In 2018 21st International Conference on information fusion (FUSION), pp. 1541-1547. IEEE, 2018. DOI: https://doi.org/10.23919/ICIF.2018.8454976
[19] Samet, Ahmed, Eric Lefevre, and Sadok Ben Yahia. "Belief function classification with conflict management: Application on forest image." In 2014 Tenth International Conference on Signal-Image Technology and Internet-Based Systems, pp. 14-20. IEEE, 2014. DOI: https://doi.org/10.1109/SITIS.2014.34
[20] Zhang, Zhenjiang, Ziqi Hao, Sherali Zeadally, Jing Zhang, Bowen Han, and Han-Chieh Chao. "Multiple attributes decision fusion for wireless sensor networks based on intuitionistic fuzzy set." IEEE Access 5 (2017): 12798-12809. DOI: https://doi.org/10.1109/ACCESS.2017.2722483
[21] Butler, S. W., Pattipati, K. R., Volponi, A., HullJ., Rajamani, R., and Siegel, J., 2006, “An Assessment Methodology for Data-Driven and Model-Based Techniques for Engine Health Monitoring. DOI: https://doi.org/10.1115/GT2006-91096
[22] Donat, William, Kihoon Choi, Woosun An, Satnam Singh, and Krishna Pattipati. "Data visualization, data reduction and classifier fusion for intelligent fault diagnosis in gas turbine engines." (2008): 041602. DOI: https://doi.org/10.1115/1.2838993
[23] Nikiforov, I., and M. Basseville. "Detection of abrupt changes: theory and application." Englewood Cliffs, NJ: PTR Prentice Hall (1993).
[24] Bishop, Christopher M., and Nasser M. Nasrabadi. Pattern recognition and machine learning. Vol. 4, no. 4. New York: Springer, 2006.
[25] Duda, Richard O., and Peter E. Hart. Pattern classification. John Wiley & Sons, 2006.
[26] Choi, Kihoon, Satnam Singh, Anuradha Kodali, Krishna R. Pattipati, John W. Sheppard, Setu Madhavi Namburu, Shunsuke Chigusa, Danil V. Prokhorov, and Liu Qiao. "Novel classifier fusion approaches for fault diagnosis in automotive systems." IEEE Transactions on Instrumentation and Measurement 58, no. 3 (2008): 602-611. DOI: https://doi.org/10.1109/TIM.2008.2004340
[27] Yan, Ruqiang, Robert X. Gao, and Xuefeng Chen. "Wavelets for fault diagnosis of rotary machines: A review with applications." Signal processing 96 (2014): 1-15. DOI: https://doi.org/10.1016/j.sigpro.2013.04.015
[28] Lei, Yaguo, Naipeng Li, Liang Guo, Ningbo Li, Tao Yan, and Jing Lin. "Machinery health prognostics: A systematic review from data acquisition to RUL prediction." Mechanical systems and signal processing 104 (2018): 799-834. DOI: https://doi.org/10.1016/j.ymssp.2017.11.016
[29] Liu, Datong, Yuchen Song, Lyu Li, Haitao Liao, and Yu Peng. "On-line life cycle health assessment for lithium-ion battery in electric vehicles." Journal of Cleaner Production 199 (2018): 1050-1065. DOI: https://doi.org/10.1016/j.jclepro.2018.06.182
[30] Zhang, Bin, Shaohui Zhang, and Weihua Li. "Bearing performance degradation assessment using long short-term memory recurrent network." Computers in Industry 106 (2019): 14-29. DOI: https://doi.org/10.1016/j.compind.2018.12.016
[31] Li, Xin, Yu Yang, Haidong Shao, Xiang Zhong, Jian Cheng, and Junsheng Cheng. "Symplectic weighted sparse support matrix machine for gear fault diagnosis." Measurement 168 (2021): 108392. DOI: https://doi.org/10.1016/j.measurement.2020.108392
[32] Khan, Samir, and Takehisa Yairi. "A review on the application of deep learning in system health management." Mechanical Systems and Signal Processing 107 (2018): 241-265. DOI: https://doi.org/10.1016/j.ymssp.2017.11.024
[33] Zhao, Rui, Ruqiang Yan, Zhenghua Chen, Kezhi Mao, Peng Wang, and Robert X. Gao. "Deep learning and its applications to machine health monitoring." Mechanical Systems and Signal Processing 115 (2019): 213-237. DOI: https://doi.org/10.1016/j.ymssp.2018.05.050
[34] Jiao, Jinyang, Ming Zhao, Jing Lin, and Kaixuan Liang. "A comprehensive review on convolutional neural network in machine fault diagnosis." Neurocomputing 417 (2020): 36-63. DOI: https://doi.org/10.1016/j.neucom.2020.07.088
[35] Hoang, Duy-Tang, and Hee-Jun Kang. "A survey on deep learning based bearing fault diagnosis." Neurocomputing 335 (2019): 327-335. DOI: https://doi.org/10.1016/j.neucom.2018.06.078
[36] Stetco, Adrian, Fateme Dinmohammadi, Xingyu Zhao, Valentin Robu, David Flynn, Mike Barnes, John Keane, and Goran Nenadic. "Machine learning methods for wind turbine condition monitoring: A review." Renewable energy 133 (2019): 620-635. DOI: https://doi.org/10.1016/j.renene.2018.10.047
[37] Li, Chuan, Shaohui Zhang, Yi Qin, and Edgar Estupinan. "A systematic review of deep transfer learning for machinery fault diagnosis." Neurocomputing 407 (2020): 121-135. DOI: https://doi.org/10.1016/j.neucom.2020.04.045
[38] Hasan, Md Junayed, MM Manjurul Islam, and Jong-Myon Kim. "Acoustic spectral imaging and transfer learning for reliable bearing fault diagnosis under variable speed conditions." Measurement 138 (2019): 620-631. DOI: https://doi.org/10.1016/j.measurement.2019.02.075
[39] Zhao, Bo, Xianmin Zhang, Zhenhui Zhan, and Shuiquan Pang. "Deep multi-scale convolutional transfer learning network: A novel method for intelligent fault diagnosis of rolling bearings under variable working conditions and domains." Neurocomputing 407 (2020): 24-38. DOI: https://doi.org/10.1016/j.neucom.2020.04.073
[40] Jia, Zhenzhong, Jing Sun, So-Ryeok Oh, Herb Dobbs, and Joel King. "Control of the dual mode operation of generator/motor in SOFC/GT-based APU for extended dynamic capabilities." Journal of Power Sources 235 (2013): 172-180. DOI: https://doi.org/10.1016/j.jpowsour.2013.01.170
[41] Yan, Dong, Chi Zhang, Linjiang Liang, Kai Li, Lichao Jia, Jian Pu, Li Jian, Xi Li, and Tao Zhang. "Degradation analysis and durability improvement for SOFC 1-cell stack." Applied Energy 175 (2016): 414-420. DOI: https://doi.org/10.1016/j.apenergy.2016.04.094
[42] Polverino, Pierpaolo, Marco Sorrentino, and Cesare Pianese. "A model-based diagnostic technique to enhance faults isolability in Solid Oxide Fuel Cell systems." Applied Energy 204 (2017): 1198-1214. DOI: https://doi.org/10.1016/j.apenergy.2017.05.069
[43] Wu, Xiaojuan, and Danhui Gao. "Fault tolerance control of SOFC systems based on nonlinear model predictive control." International Journal of Hydrogen Energy 42, no. 4 (2017): 2288-2308. DOI: https://doi.org/10.1016/j.ijhydene.2016.09.203
[44] Wu, Xiaojuan, and Danhui Gao. "Optimal fault-tolerant control strategy of a solid oxide fuel cell system." Journal of Power Sources 364 (2017): 163-181. DOI: https://doi.org/10.1016/j.jpowsour.2017.08.017
[45] Polverino, Pierpaolo, Cesare Pianese, Marco Sorrentino, and Dario Marra. "Model-based development of a fault signature matrix to improve solid oxide fuel cell systems on-site diagnosis." Journal of Power Sources 280 (2015): 320-338. DOI: https://doi.org/10.1016/j.jpowsour.2015.01.037
[46] Sorce, A., A. Greco, L. Magistri, and P. Costamagna. "FDI oriented modeling of an experimental SOFC system, model validation and simulation of faulty states." Applied Energy 136 (2014): 894-908. DOI: https://doi.org/10.1016/j.apenergy.2014.03.074
[47] Li, Shuanghong, Hongliang Cao, and Yupu Yang. "Data-driven simultaneous fault diagnosis for solid oxide fuel cell system using multi-label pattern identification." Journal of Power Sources 378 (2018): 646-659. DOI: https://doi.org/10.1016/j.jpowsour.2018.01.015
[48] Wu, XiaoJuan, and Qianwen Ye. "Fault diagnosis and prognostic of solid oxide fuel cells." Journal of Power Sources 321 (2016): 47-56. DOI: https://doi.org/10.1016/j.jpowsour.2016.04.080
[49] Huang, Qiu-An, Bingwen Wang, Wei Qu, and Rob Hui. "Impedance diagnosis of metal-supported SOFCs with SDC as electrolyte." Journal of Power Sources 191, no. 2 (2009): 297-303. DOI: https://doi.org/10.1016/j.jpowsour.2009.02.004
[50] Pahon, Elodie, N. Yousfi Steiner, Samir Jemei, Daniel Hissel, Marie-Cécile Péra, Kun Wang, and Philippe Moçoteguy. "Solid oxide fuel cell fault diagnosis and aging estimation based on wavelet transform approach." International Journal of Hydrogen Energy 41, no. 31 (2016): 13678-13687. DOI: https://doi.org/10.1016/j.ijhydene.2016.06.143
[51] Sorrentino, Marco, Dario Marra, Cesare Pianese, Maurizio Guida, Fabio Postiglione, K. Wang, and Antti Pohjoranta. "On the use of neural networks and statistical tools for nonlinear modeling and on-field diagnosis of solid oxide fuel cell stacks." Energy Procedia 45 (2014): 298-307. DOI: https://doi.org/10.1016/j.egypro.2014.01.032
[52] Barelli, Linda, Elisa Barluzzi, and Gianni Bidini. "Diagnosis methodology and technique for solid oxide fuel cells: a review." International Journal of Hydrogen Energy 38, no. 12 (2013): 5060-5074. DOI: https://doi.org/10.1016/j.ijhydene.2013.02.024
[53] He, Yu-Lin, Ran Wang, Sam Kwong, and Xi-Zhao Wang. "Bayesian classifiers based on probability density estimation and their applications to simultaneous fault diagnosis." Information Sciences 259 (2014): 252-268. DOI: https://doi.org/10.1016/j.ins.2013.09.003
[54] Yang, JiaJun, Dong Yan, Wei Huang, Jun Li, Jian Pu, Bo Chi, and Li Jian. "Improvement on durability and thermal cycle performance for solid oxide fuel cell stack with external manifold structure." Energy 149 (2018): 903-913. DOI: https://doi.org/10.1016/j.energy.2018.02.072
[55] Zhang, Yi, Xiaoxiang Yan, Ping Xiao, Jialing Zou, and Ling Hu. "A fault diagnosis method for bearings and gears in rotating machinery based on data fusion and transfer learning." Measurement Science and Technology 36, no. 1 (2024): 016104. DOI: https://doi.org/10.1088/1361-6501/ad7f74
[56] Gawde, Shreyas, Shruti Patil, Satish Kumar, and Ketan Kotecha. "A scoping review on multi-fault diagnosis of industrial rotating machines using multi-sensor data fusion." Artificial Intelligence Review 56, no. 5 (2023): 4711-4764. DOI: https://doi.org/10.1007/s10462-022-10243-z
[57] Mian, Tauheed, Anurag Choudhary, and Shahab Fatima. "A sensor fusion-based approach for bearing fault diagnosis of the rotating machine." Proceedings of the Institution of Mechanical Engineers, Part O: Journal of Risk and Reliability 236, no. 5 (2022): 661-675. DOI: https://doi.org/10.1177/1748006X211044843
[58] Huo, Zhiqiang, Miguel Martínez-García, Yu Zhang, and Lei Shu. "A multisensor information fusion method for high-reliability fault diagnosis of rotating machinery." IEEE Transactions on Instrumentation and Measurement 71 (2021): 1-12. DOI: https://doi.org/10.1109/TIM.2021.3132051
[59] Huang, Min, Zhen Liu, and Yang Tao. "Mechanical fault diagnosis and prediction in IoT based on multi-source sensing data fusion." Simulation Modelling Practice and Theory 102 (2020): 101981. DOI: https://doi.org/10.1016/j.simpat.2019.101981
[60] Guo, Sheng, Bin Zhang, Tao Yang, Dongzhen Lyu, and Wei Gao. "Multitask convolutional neural network with information fusion for bearing fault diagnosis and localization." IEEE Transactions on Industrial Electronics 67, no. 9 (2019): 8005-8015. DOI: https://doi.org/10.1109/TIE.2019.2942548
[61] Luwei, Kenisuomo C., Akilu Yunusa-Kaltungo, and Yusuf A. Sha’aban. "Integrated fault detection framework for classifying rotating machine faults using frequency domain data fusion and artificial neural networks." Machines 6, no. 4 (2018): 59. DOI: https://doi.org/10.3390/machines6040059
[62] Zeng, Ruili, Lingling Zhang, Jianmin Mei, Hong Shen, and Huimin Zhao. "Fault detection in an engine by fusing information from multivibration sensors." International Journal of Distributed Sensor Networks 13, no. 7 (2017): 1550147717719057. DOI: https://doi.org/10.1177/1550147717719057
[63] Zhang, Li, and Hongli Gao. "A deep learning-based multi-sensor data fusion method for degradation monitoring of ball screws." In 2016 Prognostics and System Health Management Conference (PHM-Chengdu), pp. 1-6. IEEE, 2016. DOI: https://doi.org/10.1109/PHM.2016.7819792
[64] Yunusa-Kaltungo, Akilu, Jyoti K. Sinha, and Adrian D. Nembhard. "A novel fault diagnosis technique for enhancing maintenance and reliability of rotating machines." Structural Health Monitoring 14, no. 6 (2015): 604-621. DOI: https://doi.org/10.1177/1475921715604388
[65] Chen, Danmin, Zhiqiang Zhang, Funa Zhou, and Chaoge Wang. "A Real-Time Fault Diagnosis Method for Multi-Source Heterogeneous Information Fusion Based on Two-Level Transfer Learning." Entropy 26, no. 12 (2024): 1007. DOI: https://doi.org/10.3390/e26121007
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 International Journal of Computational and Experimental Science and Engineering
This work is licensed under a Creative Commons Attribution 4.0 International License.
