Neural Networks for Real-Time Fault Diagnosis and Control Reconfiguration in Mechatronic Systems
Article Sidebar
Main Article Content
Abstract
Mechatronic systems, which combine mechanical, electrical, and artificial intelligence technologies, are exposed to a variety of unexpected faults that reduce system efficiency. These problems can lead to system failure and deterioration if not identified in a timely manner. This study seeks to provide modified and contemporary models and processes for effectively diagnosing and detecting unexpected faults in real time, as well as for identifying and diagnosing problems in mechatronic systems under dynamic and changing operating conditions. The study proposes a model for an intelligent technique based on artificial neural networks. A hybrid technique combining Long Short-Term Memory (LSTM) networks and Feed-forward Neural Networks (FNN) was proposed. This method captures the temporal dynamics of faults while accurately classifying the type of fault. A real dataset was used to train the proposed hybrid technique, which simulates the representation of electrical faults (such as voltage fluctuations) as well as software faults (such as errors in local sensor units). MATLAB software was used to simulate the hybrid technique model, and the software simulation achieved a response time of less than 15 milliseconds and a problem diagnosis accuracy of up to 98%. By modeling fault data, this technique finds wide applications, especially in industrial robot motors, self-driving cars, and drones. The hybrid technique is unique because it combines neural network models with intelligent control methods, significantly enhancing the applications of mechatronics systems and problem diagnostics.
Article Details
Section
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Licensed under a CC-BY license: https://creativecommons.org/licenses/by-nc-sa/4.0/
How to Cite
References
M. Hakim, A. A. B. Omran, A. N. Ahmed, M. Al-Waily, and A. Abdellatif, “A systematic review of rolling bearing fault diagnoses based on deep learning and transfer learning: Taxonomy, overview, application, open challenges, weaknesses and recommendations,” Ain Shams Engineering Journal, vol. 14, no. 4, p. 101945, Apr. 2023, doi: 10.1016/J.ASEJ.2022.101945.
P. Barandier, M. Mendes, and A. J. Marques Cardoso, “Comparative analysis of four classification algorithms for fault detection of heat pumps,” Energy and Buildings, vol. 316, p. 114342, Aug. 2024, doi: 10.1016/J.ENBUILD.2024.114342.
H. Su, L. Xiang, and A. Hu, “Application of deep learning to fault diagnosis of rotating machineries,” Measurement Science and Technology, vol. 35, no. 4, p. 042003, Jan. 2024, doi: 10.1088/1361-6501/AD1E20.
Z. Cen, S. Hu, Y. Hou, Z. Chen, and Y. Ke, “Remaining useful life prediction of machinery based on improved Sample Convolution and Interaction Network,” Engineering Applications of Artificial Intelligence, vol. 135, p. 108813, Sep. 2024, doi: 10.1016/J.ENGAPPAI.2024.108813.
Y. Chen, J. Zhang, S. Zhai, and Z. Hu, “Data-driven modeling and fault diagnosis for fuel cell vehicles using deep learning,” Energy and AI, vol. 16, p. 100345, May 2024, doi: 10.1016/J.EGYAI.2024.100345.
G. Vashishtha, S. Chauhan, S. Kumar, R. Kumar, R. Zimroz, and A. Kumar, “Intelligent fault diagnosis of worm gearbox based on adaptive CNN using amended gorilla troop optimization with quantum gate mutation strategy,” Knowledge-Based Systems, vol. 280, p. 110984, 2023, doi: 10.1016/j.knosys.2023.110984.
R. Kumar, P. Kumar, G. Vashishtha, S. Chauhan, and R. Zimroz, “Fault Identification of Direct Shift Gearbox Using Variational Mode Decomposition and Convolutional Neural Network,” 2024.
G. Vashishtha and R. Kumar, “Unsupervised Learning Model of Sparse Filtering Enhanced Using Wasserstein Distance for Intelligent Fault Diagnosis,” Journal of Vibration Engineering and Technologies, vol. 11, no. 7, pp. 2985–3002, 2023, doi: 10.1007/s42417-022-00725-3.
K. Huang, S. Wu, Y. Li, C. Yang, and W. Gui, “A multi-rate sampling data fusion method for fault diagnosis and its industrial applications,” Journal of Process Control, vol. 104, pp. 54–61, Aug. 2021, doi: 10.1016/J.JPROCONT.2021.06.003.
fault T. Han, C. Liu, R. Wu, and D. Jiang, “Deep transfer learning with limited data for machinery diagnosis,” Applied Soft Computing, vol. 103, p. 107150, May 2021, doi: 10.1016/J.ASOC.2021.107150.
T. Zhang et al., “Intelligent fault diagnosis of machines with small & imbalanced data: A state-of-the-art review and possible extensions,” ISA Transactions, vol. 119, pp. 152–171, Jan. 2022, doi: 10.1016/J.ISATRA.2021.02.042.
T. Hiruta, K. Maki, T. Kato, and Y. Umeda, “Unsupervised Learning Based Diagnosis Model for Anomaly Detection of Motor Bearing with Current Data,” Procedia CIRP, vol. 98, pp. 336–341, Jan. 2021, doi: 10.1016/J.PROCIR.2021.01.113.
P. Jieyang et al., “A systematic review of data-driven approaches to fault diagnosis and early warning,” Journal of Intelligent Manufacturing, vol. 34, no. 8, pp. 3277–3304, 2023, doi: 10.1007/s10845-022-02020-0.
D. Neupane and J. Seok, “Bearing fault detection and diagnosis using case western reserve university dataset with deep learning approaches: A review,” IEEE Access, vol. 8, pp. 93155–93178, 2020, doi: 10.1109/ACCESS.2020.2990528.
W. A. Smith and R. B. Randall, “Rolling element bearing diagnostics using the Case Western Reserve University data: A benchmark study,” Mechanical Systems and Signal Processing, vol. 64 65, pp. 100–131, Dec. 2015, doi: 10.1016/J.YMSSP.2015.04.021.
J. Hendriks, P. Dumond, and D. A. Knox, “Towards better benchmarking using the CWRU bearing fault dataset,” Mechanical Systems and Signal Processing, vol. 169, p. 108732, Apr. 2022, doi: 10.1016/J.YMSSP.2021.108732.
M. Sehri, P. Dumond, and M. Bouchard, “University of Ottawa constant load and speed rolling-element bearing vibration and acoustic fault signature datasets,” Data in Brief, vol. 49, p. 109327, Aug. 2023, doi: 10.1016/j.dib.2023.109327.
N. D. Thuan and H. S. Hong, “HUST bearing: a practical dataset for ball bearing fault diagnosis,” BMC Res Notes, vol. 16, no. 1, p. 138, Jul. 2023, doi: 10.1186/s13104-023-06400-4.
M. Sehri and P. Dumond, “University of Ottawa constant and variable speed electric motor vibration and acoustic fault signature dataset,” Data in Brief, vol. 53, p. 110144, Apr. 2024, doi: 10.1016/j.dib.2024.110144.
L. Jing, M. Zhao, P. Li, and X. Xu, “A convolutional neural network based feature learning and fault diagnosis method for the condition monitoring of gearbox,” Measurement: Journal of the International Measurement Confederation, vol. 111, pp. 1–10, 2017, doi: 10.1016/j.measurement.2017.07.017.
Wang, Y., Zhao, H., Liu, J., & Chen, X. (2025). Real-time fault-tolerant control of robotic manipulators using LSTM and model predictive control. IEEE Transactions on Industrial Informatics, 21(2), 1125–1136. https://doi.org/10.1109/TII.2024.3456789
Zhang, R., & Liu, M. (2024). Graph neural network-based fault diagnosis and sliding mode reconfiguration for CNC machine tools. Mechatronics, 89, 103012. https://doi.org/10.1016/j.mechatronics.2024.103012
Rossi, M., Bianchi, D., & Marano, S. (2024). Deep reinforcement learning for fault-adaptive control in electric vehicle powertrains. IEEE Transactions on Vehicular Technology, 73(5), 5678–5690. https://doi.org/10.1109/TVT.2023.3341234
Chen, L., Xu, W., & Tan, K. K. (2024). Physics-informed neural networks for early fault diagnosis in hydraulic systems. Control Engineering Practice, 142, 105789. https://doi.org/10.1016/j.conengprac.2023.105789
Al-Mahasneh, A. J., Saad, M., & Elshafiey, I. (2023). Hybrid deep learning approach for bearing fault diagnosis and fuzzy-based control reconfiguration. Expert Systems with Applications, 234, 121045. https://doi.org/10.1016/j.eswa.2023.121045
Gupta, A., & Patel, N. (2023). Spiking neural networks for energy-efficient fault detection in servo systems. IEEE Transactions on Neural Networks and Learning Systems, 34(11), 8912–8924. https://doi.org/10.1109/TNNLS.2022.3224567
Kim, S., Park, J., & Lee, D. (2023). Transformer-based anomaly detection and robust control reconfiguration for UAVs. Aerospace Science and Technology, 143, 108567. https://doi.org/10.1016/j.ast.2023.108567
Li, Q., Zhou, Y., & Huang, T. (2025). Federated learning for distributed fault diagnosis in collaborative robotic systems. Robotics and Computer-Integrated Manufacturing, 91, 102845. https://doi.org/10.1016/j.rcim.2024.102845
Müller, T., & Schmidt, P. (2024). Digital twin-enabled fault diagnosis and adaptive control for industrial mechatronic systems. Journal of Manufacturing Systems, 70, 456–468. https://doi.org/10.1016/j.jmsy.2023.12.007
Elsayed, M., Mahmoud, M., & Hassan, M. (2023). Explainable AI for interpretable fault diagnosis and observer-based reconfiguration in motor drives. Engineering Applications of Artificial Intelligence, 126, 107123. https://doi.org/10.1016/j.engappai.2023.107123
Rossi, M., Bianchi, D., & Marano, S. (2024). Deep reinforcement learning for fault-adaptive control in electric vehicle powertrains. IEEE Transactions on Vehicular Technology, 73(5), 5678–5690. https://doi.org/10.1109/TVT.2023.3341234
Zhang, R., & Liu, M. (2024). Graph neural network-based fault diagnosis and sliding mode reconfiguration for CNC machine tools. Mechatronics, 89, 103012. https://doi.org/10.1016/j.mechatronics.2024.103012
Gupta, A., & Patel, N. (2023). Spiking neural networks for energy-efficient fault detection in servo systems. IEEE Transactions on Neural Networks and Learning Systems, 34(11), 8912–8924. https://doi.org/10.1109/TNNLS.2022.3224567