Using machine learning algorithms for diagnostics of moving equipment control systems
DOI:
https://doi.org/10.31548/Abstract
The article investigates the application of machine learning algorithms for automated diagnostics of mobile equipment control systems. The relevance of the work is due to the growing complexity of control systems, where the failure of individual components can lead to significant economic losses and safety threats. In the conditions of modern industrial production and transport, the need to create automated solutions for monitoring the technical condition is especially important.
The purpose of the research is to develop and implement machine learning methods to increase the efficiency of detecting and predicting failures in control systems. The tasks of the work include creating models based on deep neural networks, training them on data about the operation of control systems, and assessing their performance.
Analysis of control system operation data obtained from mobile equipment sensors, creation and testing of machine learning models are taken as research methods. Open source data and synthetically generated sets were used for experiments. The main tools were neural networks such as LSTM and CNN, which are implemented in the TensorFlow and PyTorch frameworks. The study was conducted using computing clusters to speed up training.
The results of the study showed that the use of machine learning allows achieving high accuracy in technical condition diagnostics. For example, LSTM models provided failure prediction accuracy of up to 95%, while CNN effectively identified anomalies in real time. A comparative analysis was conducted with classical machine learning methods, which demonstrated the advantages of deep neural networks in terms of speed of adaptation to new data and noise resistance. At the same time, the main challenges remain the need for large amounts of data for training models and ensuring their energy efficiency when used in real conditions.
Key words: machine learning, control system diagnostics, neural networks, failure prediction, maintenance automation
References
1. Artelt, M., et al. (2024). Hybrid Approaches and Datasets for Remaining Useful Life Prediction: A Review. Procedia CIRP, 130, 294–300. Available at: https://doi.org/10.1016/j.procir.2024.10.090
2. Bruneo, D., & De Vita, F. (2019). On the Use of LSTM Networks for Predictive Maintenance in Smart Industries. 2019 IEEE International Conference on Smart Computing (SMARTCOMP), 241–248. Available at: https://doi.org/10.1109/SMARTCOMP.2019.00059
3. Chen, X. (2024). A novel gear RUL prediction method by diffusion model generation health index and attention guided multi-hierarchy LSTM. Scientific Reports, 14(1). Available at: https://doi.org/10.1038/s41598-024-52151-y
4. Mirlekar, S., Kanojia, K. P., & Chourasia, B. (2024). A Stacked CNN-BiLSTM Model with Majority Technique for Detecting the Intrusions in Network. International Journal of Intelligent Systems and Applications in Engineering, 12(5s), 152–162.
5. Traini, E., Bruno, G., & Lombardi, F. (2021). Design of a Physics-Based and Data-Driven Hybrid Model for Predictive Maintenance. IFIP Advances in Information and Communication Technology, 536–543. Available at: https://doi.org/10.1007/978-3-030-85914-5_57
6. Shcherbakov, M., & Sai, C. (2022). A hybrid deep learning framework for intelligent predictive maintenance of Cyber-Physical Systems. ACM Transactions on Cyber-Physical Systems, 1–22. Available at: https://doi.org/10.1145/3486252
7. Chen, C., et al. (2023). The advance of digital twin for predictive maintenance: The role and function of machine learning. Journal of Manufacturing Systems, 71, 581–594. Available at: https://doi.org/10.1016/j.jmsy.2023.10.010
8. Serradilla, O., et al. (2022). Deep learning models for predictive maintenance: a survey, comparison, challenges and prospects. Applied Intelligence. Available at: https://doi.org/10.1007/s10489-021-03004-y
9. Lu, L., Zhang, C., Cao, K., Deng, T., & Yang, Q. (2022). A Multichannel CNN-GRU Model for Human Activity Recognition. IEEE Access, 10, 66797–66810. Available at: https://doi.org/10.1109/ACCESS.2022.3185112
10. Meriem, H., Nora, H., & Samir, O. (2023). Predictive Maintenance for Smart Industrial Systems: A Roadmap. Procedia Computer Science, 220, 645–650. Available at: https://doi.org/10.1016/j.procs.2023.03.082
Published
Issue
Section
License
Relationship between right holders and users shall be governed by the terms of the license Creative Commons Attribution – non-commercial – Distribution On Same Conditions 4.0 international (CC BY-NC-SA 4.0):https://creativecommons.org/licenses/by-nc-sa/4.0/deed.uk
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
