A Adaptable Fault Detection Method in Engineering Systems Using Machine Learning

Authors

1 Faculty of Management and Industrial Engineering Department, Malek-Ashtar University of Technology, Tehran, Iran.

2 Faculty of Management and Industrial Engineering Department, Malek-Ashtar University of Technology, Tehran, Iran

Abstract

In the realm of system engineering, efficient and rapid fault detection is crucial for maintaining operational safety and performance. Traditional fault detection methodologies often depend on extensive system-specific knowledge and are designed to identify only predefined faults, limiting their broader application. This paper introduces a novel machine learning-based fault detection approach that leverages minimal system inputs to model normal operating conditions. Unlike traditional methods, our approach does not require detailed expertise about specific fault conditions. In-stead, it detects deviations from normal behavior, flag-ging these as potential faults. This model assumes that any significant discrepancy between expected and actu-al sensor data indicates a fault, thereby simplifying the fault detection process and enhancing its applicability across various systems. To validate the effectiveness of this approach, we conducted experiments on a quad-copter, focusing on motor and external disturbances. The results demonstrate that our model can successfully identify faults without prior knowledge of specific fault types, offering a flexible and scalable solution for vari-ous industrial applications. The simplicity and adapta-bility of this method make it particularly attractive for systems where traditional fault detection techniques may be impractical due to complexity or the need for rapid deployment.

Keywords

Main Subjects

References

[1]     Bektash, O., & la Cour-Harbo, A. (2020). Vibration analysis for anomaly detection in unmanned aircraft. Paper presented at the Annual Conference of the Prognostics and Health Management Society 2020.
[2]     Cheng, D.-L., & Lai, W.-H. (2019). APPLICATION OF SELF-ORGANIZING MAP ON FLIGHT DATA ANALYSIS FOR QUADCOPTER HEALTH DIAGNOSIS SYSTEM. International Archives of the Photogrammetry, Remote Sensing & Spatial Information Sciences.
[3]     Zhang, X., Zhao, Z., Wang, Z., & Wang, X. (2021). Fault detection and identification method for quadcopter based on airframe vibration signals. Sensors, 21(2), 581.
[4]     Feierl, L., Unterberger, V., Rossi, C., Geradts, B., & Gaetani, M. (2023). Fault Detective: Automatic Fault-Detection for Solar Thermal Systems based on Artificial Intelligence. Solar Energy Advances, 100033.
[5]     Yairi, T., Kawahara, Y., Fujimaki, R., Sato, Y., & Machida, K. (2006). Telemetry-mining: a machine learning approach to anomaly detection and fault diagnosis for space systems. Paper presented at the 2nd IEEE International Conference on Space Mission Challenges for Information Technology (SMC-IT'06), pp. 8 pp.-476.
[6]     Ahmad, M. W., Reynolds, J., & Rezgui, Y. (2018). Predictive modelling for solar thermal energy systems: A comparison of support vector regression, random forest, extra trees and regression trees. J. cleaner production, 203, 810-821.
[7]     Cheliotis, M., Lazakis, I., & Theotokatos, G. (2020). Machine learning and data-driven fault detection for ship systems operations. Ocean Engineering, 216, 107968.
[8]     Bode, G., Thul, S., Baranski, M., & Müller, D. (2020). Real-world application of machine-learning-based fault detection trained with experimental data. Energy, 198, 117323.
[9]     Li, Y. (2022). Exploring real-time fault detection of high-speed train traction motor based on machine learning and wavelet analysis. Neural Computing and Applications, 34(12), 9301-9314.
[10]   Abdelgayed, T. S., Morsi, W. G., & Sidhu, T. S. (2017). Fault detection and classification based on co-training of semisupervised machine learning. IEEE Transactions on Industrial Electronics, 65(2), 1595-1605.
[11]   Amruthnath, N., & Gupta, T. (2018). A research study on unsupervised machine learning algorithms for early fault detection in predictive maintenance. Paper presented at the 2018 5th international conference on industrial engineering and applications (ICIEA).
[12]   Sievers, M., & Madni, A. M. (2016). Agent-based flexible design contracts for resilient spacecraft swarms. Paper presented at the 54th AIAA aerospace sciences meeting, p. 0476.
[13]   Abbasi, M. A., Khan, A. Q., Abid, M., Mustafa, G., Mehmood, A., Luo, H., & Yin, S. (2020). Parity-based robust data-driven fault detection for nonlinear systems using just-in-time learning approach. Transactions of the Institute of Measurement and Control, 42(9),1690-1699.
[14]   Cao, W., Cong, W., & Sun, M. (2012). Iterative learning based fault detection and estimation in nonlinear systems. J.  Sys. Eng. Elec., 23(3), 419-424.
[15]   Zeng, C., Chen, T., Xing, M., & Wang, Y. (2024). Fast fault detection for nonlinear interconnected systems via deterministic learning. Transactions of the Institute of Measurement and Control, 46(4), 624-637.
[16]   Park, K. H., Park, E., & Kim, H. K. (2021). Unsupervised fault detection on unmanned aerial vehicles: Encoding and thresholding approach. Sensors, 21(6), 2208.
[17]   Zhu, Z., & Jiao, X. (2012). Fault detection for nonlinear networked control systems based on fuzzy observer. J. Sys. Eng. Elect., 23(1), 129-136.
[18]   Puchalski, R., & Giernacki, W. (2022). UAV fault detection methods, state-of-the-art. Drones, 6(11), 330.
[19]   López-Estrada, F., Méndez-López, A., Santos-Ruiz, I., Valencia-Palomo, G., & Escobar-Gómez, E. (2021). Fault detection in unmanned aerial vehicles via orientation signals and machine learning. Revista iberoamericana de automática e informática industrial, 18(3), 254-264.
 
[20]   Yang, L., Li, S., Li, C., Zhu, C., Zhang, A., & Liang, G. (2023). Data-driven unsupervised anomaly detection and recovery of unmanned aerial vehicle flight data based on spatiotemporal correlation. Science China Technological Sciences, 66(5), 1304-1316.
[21]   Doostmohammadian, M., Zarrabi, H., & Charalambous, T. (2023). Sensor fault detection and isolation via networked estimation: rank-deficient dynamical systems. Int. J. Cont., 96(11), 2853-2870.
[22]   ایوقی م.و، دلی ع. ش. (2023). مدل های مبتنی بر یادگیری عمیق در شناسایی سیستم های غیرخطی. مجله کنترل, 17(2), 1-23.
[23]   یعقوبی ع، محمدی م. (2024). تشخیص خطا با استفاده از شبکه عصبی در روتور تمایل یابنده. نشریه مهندسی مکانیک امیرکبیر, 56(3), 321-344.
[24]   مرزبالی ح.م، حسنی س، مشایخی ه، مشایخی و. (2021). استخراج ویژگی به کمک یادگیری عمیق برای تشخیص و دسته بندی خطاهای مکانیکی یاتاقان در ماشین‌های القایی قفس سنجابی. مکانیک سازه ها و شاره ها, 11(5), 33-48.
Journal of Solid and Fluid Mechanics
Volume 15, Issue 2
May and June 2025
Pages 33-50

Files

Share

How to cite

Statistics