Intelligent Anomaly Detection Framework for Industrial Robots Using Vibration Signals and ML Algorithms
DOI:
https://doi.org/10.63282/3050-922X.IJERET-V4I2P116Keywords:
Industrial Robots, Anomaly Detection, Smart Manufacturing, Vibration Signals, Signal Processing, Machine Learning, Vibration DataAbstract
Many industrial manufacturing firms have adopted industrial robots to increase production efficiency. There is a greater chance of an industrial robot joint failing or developing a problem as its service duration increases. It is still challenging to identify industrial robot joint faults using only the current signal, even though some vibration-based detection techniques have been successfully established. This is particularly true when there is not enough labelled data to distinguish between normal conditions and faults. This study suggests a brand-new method for anomaly identification utilizing vibration data from industrial robot joints, addressing the challenge of limited anomaly samples. A Long Short-Term Memory (LSTM) model is used for precise defect identification when the method incorporates sophisticated preprocessing techniques including noise filtering, normalization, and Fast Fourier Transform (FFT)-based feature extraction. The model's effectiveness is demonstrated by its 97.70% accuracy rate and a precision of 99.9% showing its potential towards the real time deployment in prsedictive maintenance systems of industrial robots, to ensure its continuous and efficient operation. These results show the feasibility of applying this model in predictive maintenance systems that boost the industrial manufacturing processes reliability without downtime and increase operational efficiency.
References
[1] A. Angelopoulos et al., “Tackling faults in the industry 4.0 era—a survey of machine-learning solutions and key aspects,” 2020. doi: 10.3390/s20010109.
[2] S. Dang, Z. Kong, L. Peng, Y. Ji, and Y. Zhang, “Adaptive state observer for robot manipulators diagnostics and health degree assessment,” Appl. Sci., 2020, doi: 10.3390/app10020514.
[3] Z. Zhong, Y. Zhao, A. Yang, H. Zhang, D. Qiao, and Z. Zhang, “Industrial Robot Vibration Anomaly Detection Based on Sliding Window One-Dimensional Convolution Autoencoder,” Shock Vib., 2022, doi: 10.1155/2022/1179192.
[4] R. Hornung, H. Urbanek, J. Klodmann, C. Osendorfer, and P. Van Der Smagt, “Model-free robot anomaly detection,” in IEEE International Conference on Intelligent Robots and Systems, 2014. doi: 10.1109/IROS.2014.6943078.
[5] V. Pillai, “Anomaly Detection for Innovators: Transforming Data into Breakthroughs,” Lib. Media Priv. Ltd., 2022.
[6] T. Chen, X. Liu, B. Xia, W. Wang, and Y. Lai, “Unsupervised anomaly detection of industrial robots using sliding-window convolutional variational autoencoder,” IEEE Access, 2020, doi: 10.1109/ACCESS.2020.2977892.
[7] S. Chen, M. Luo, and F. He, “A universal algorithm for sensorless collision detection of robot actuator faults,” Adv. Mech. Eng., 2018, doi: 10.1177/1687814017740710.
[8] T. Wuest, D. Weimer, C. Irgens, and K. D. Thoben, “Machine learning in manufacturing: Advantages, challenges, and applications,” Prod. Manuf. Res., 2016, doi: 10.1080/21693277.2016.1192517.
[9] R. K. Ketakee Kishorkumar Nimavat, “Updating machine learning training data using graphical inputs,” 17178360, 2022
[10] V. Malviya, I. Mukherjee, and S. Tallur, “Edge-Compatible Convolutional Autoencoder Implemented on FPGA for Anomaly Detection in Vibration Condition-Based Monitoring,” IEEE Sensors Lett., 2022, doi: 10.1109/LSENS.2022.3159972.
[11] Y. Bel-Hadj and W. Weijtjens, “Anomaly Detection in Vibration Signals for Structural Health Monitoring of an Offshore Wind Turbine,” Lect. Notes Civ. Eng., vol. 270 LNCE, pp. 348–358, 2022, doi: 10.1007/978-3-031-07322-9_36.
[12] S. Ahmad, K. Styp-Rekowski, S. Nedelkoski, and O. Kao, “Autoencoder-based Condition Monitoring and Anomaly Detection Method for Rotating Machines,” in Proceedings - 2020 IEEE International Conference on Big Data, Big Data 2020, 2020. doi: 10.1109/BigData50022.2020.9378015.
[13] L. Variz, L. Piardi, P. J. Rodrigues, and P. Leitao, “Machine learning applied to an intelligent and adaptive robotic inspection station,” in IEEE International Conference on Industrial Informatics (INDIN), 2019. doi: 10.1109/INDIN41052.2019.8972298.
[14] Z. Li, J. Li, Y. Wang, and K. Wang, “A deep learning approach for anomaly detection based on SAE and LSTM in mechanical equipment,” Int. J. Adv. Manuf. Technol., 2019, doi: 10.1007/s00170-019-03557-w.
[15] Y. H. Rajarshi Tarafdar, “Finding majority for integer elements,” J. Comput. Sci. Coll., vol. 33, no. 5, pp. 187–191, 2018.
[16] S. Misra et al., “Fault Detection in Induction Motor Using Time Domain and Spectral Imaging-Based Transfer Learning Approach on Vibration Data,” Sensors, 2022, doi: 10.3390/s22218210.
[17] J. Yan and H. Cheng, “Designing and Manufacturing of Industrial Robots with Dual-Angle Sensors Taking into Account Vibration Signal Fusion,” J. Robot., vol. 2023, pp. 1–11, May 2023, doi: 10.1155/2023/1855226.
