Vibration and Acoustic Signal Analysis for Early Fault Detection in Clean-Room Robotics
DOI:
https://doi.org/10.63282/3050-9262.IJAIDSML-V7I1P106Keywords:
Vibration Analysis, Acoustic Signal Analysis, Early Fault Detection, Clean-Room Robotics, Condition Monitoring, Machine LearningAbstract
Clean-room robotic systems play a crucial role in semiconductor manufacturing, pharmaceutical assembly, and precision laboratory settings. These robots must operate reliably to avoid costly production delays and product contamination. Early detection of mechanical faults through vibration and acoustic signal analysis can improve reliability, reduce maintenance costs, and prevent unplanned downtime. This paper reviews key methods for extracting vibration and acoustic features, signal processing techniques, diagnostic models, experimental results, and future research directions. Results show that frequency domain analysis, machine learning classifiers, and sensor fusion improve fault detection accuracy in robotic joints, motors, and bearings.
References
[1] R. B. Randall, Vibration-Based Condition Monitoring, Chichester, UK: Wiley, 2011.
[2] K. S. Jardine, D. Lin, and D. Banjevic, “A review on machinery diagnostics and prognostics implementing condition-based maintenance,” Mechanical Systems and Signal Processing, vol. 20, no. 7, pp. 1483–1510, 2006.
[3] Y. Lei, B. Yang, X. Jiang, F. Jia, N. Li, and A. K. S. Jardine, “Machinery health prognostics: A systematic review from data acquisition to remaining useful life prediction,” Mechanical Systems and Signal Processing, vol. 104, pp. 799–834, 2018.
[4] W. Zhang, G. Peng, C. Li, Y. Chen, and Z. Zhang, “A new deep learning model for fault diagnosis with good anti-noise and domain adaptation ability on raw vibration signals,” Sensors, vol. 17, no. 2, pp. 1–22, 2017.
[5] S. Braun, “The extraction of periodic waveforms by time domain averaging,” Acustica, vol. 32, pp. 69–77, 1975.
