Deteksi Anomali Sinyal Vibrasi pada Mesin Industri Menggunakan Autoencoder di PT. Pusri Palembang
DOI:
https://doi.org/10.52436/1.jpti.553Kata Kunci:
autoencoder, deteksi anomali, pembelajaran mesin, sinyal vibrasiAbstrak
Analisa sinyal vibrasi merupakan metode penting untuk mendeteksi kondisi kesehatan mesin untuk mencegah kerusakan lebih lanjut dan mengurangi downtime. Pendekatan konvensional sering kali tidak efektif dalam menangkap pola kompleks pada sinyal vibrasi, sehingga dibutuhkan metode yang lebih canggih, seperti pembelajaran mesin. Penelitian ini bertujuan untuk mengembangkan model deteksi anomali pada sinyal vibrasi menggunakan autoencoder. Data vibrasi yang digunakan diperoleh dari tiga unit blower di PT. Pusri Palembang. Evaluasi dilakukan dengan membandingkan kemampuan model dalam mendeteksi anomali dan kondisi normal. Hasil penelitian menunjukkan bahwa model autoencoder efektif mendeteksi anomali dengan akurasi tinggi serta keseimbangan optimal dalam mengidentifikasi kondisi mesin. Penelitian ini menawarkan solusi praktis bagi industri untuk meningkatkan efisiensi pemeliharaan dan keandalan peralatan.
Unduhan
Referensi
M. H. Mohd Ghazali and W. Rahiman, “Vibration Analysis for Machine Monitoring and Diagnosis: A Systematic Review,” Shock and Vibration, vol. 2021, no. 1, Jan. 2021, doi: 10.1155/2021/9469318.
T. Zonta, C. A. da Costa, R. da Rosa Righi, M. J. de Lima, E. S. da Trindade, and G. P. Li, “Predictive maintenance in the Industry 4.0: A systematic literature review,” Comput Ind Eng, vol. 150, p. 106889, Dec. 2020, doi: 10.1016/j.cie.2020.106889.
Y. Liao, H. Li, L. Zhang, Q. Yan, Y. Yang, and B. Li, “Anomaly Transformer for Vibration Data Analysis: Case Study on CWRU Dataset,” in 2023 International Conference on Image Processing, Computer Vision and Machine Learning (ICICML), IEEE, Nov. 2023, pp. 785–788. doi: 10.1109/ICICML60161.2023.10424762.
N. Raj, “An Improved Accuracy and Efficiency Based Defect Detection Method for Industrial Signal Processing,” in 2023 3rd Asian Conference on Innovation in Technology (ASIANCON), IEEE, Aug. 2023, pp. 1–7. doi: 10.1109/ASIANCON58793.2023.10270706.
X. Zhou, Y. Wu, J. Li, and C. Song, “Anomaly Detection in Rotating Machinery Vibration Signals Based on Domain Transformation and Transformer,” in 2024 IEEE 7th Information Technology, Networking, Electronic and Automation Control Conference (ITNEC), IEEE, Sep. 2024, pp. 163–167. doi: 10.1109/ITNEC60942.2024.10732926.
S. V, T. K, V. C, V. S. D, T. R, and N. A. Patil, “Anomaly Detection in Rotary Equipment using hybrid model with HGSO Optimization,” in 2024 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT), IEEE, Jul. 2024, pp. 1–6. doi: 10.1109/CONECCT62155.2024.10677203.
K. Almutairi, J. K. Sinha, and H. Wen, “Fault Detection of Rotating Machines Using poly-Coherent Composite Spectrum of Measured Vibration Responses with Machine Learning,” Machines, vol. 12, no. 8, p. 573, Aug. 2024, doi: 10.3390/machines12080573.
A. Styanidis, M. Loufakis, P. Symeonidis, D. Ioannidis, D. Tzovaras, and I. Kourmpetis, “Vibration-based Anomaly Detection on Weather Radar Rotating Machinery using One Dimensional Convolutional Autoencoder,” in 2024 2nd International Conference on Intelligent Perception and Computer Vision (CIPCV), IEEE, May 2024, pp. 38–45. doi: 10.1109/CIPCV61763.2024.00017.
K. Pawar and V. Z. Attar, “Assessment of Autoencoder Architectures for Data Representation,” 2020, pp. 101–132. doi: 10.1007/978-3-030-31756-0_4.
T. Gao, J. Yang, and S. Jiang, “A Novel Fault Detection Model Based on Vector Quantization Sparse Autoencoder for Nonlinear Complex Systems,” IEEE Trans Industr Inform, vol. 19, no. 3, pp. 2693–2704, Mar. 2023, doi: 10.1109/TII.2022.3174715.
D. Dasari and P. S. Varma, “Employing Various Data Cleaning Techniques to Achieve Better Data Quality using Python,” in 2022 6th International Conference on Electronics, Communication and Aerospace Technology, IEEE, Dec. 2022, pp. 1379–1383. doi: 10.1109/ICECA55336.2022.10009079.
P. Li, Y. Pei, and J. Li, “A comprehensive survey on design and application of autoencoder in deep learning,” Appl Soft Comput, vol. 138, p. 110176, May 2023, doi: 10.1016/j.asoc.2023.110176.
A. A. Neloy and M. Turgeon, “A comprehensive study of auto-encoders for anomaly detection: Efficiency and trade-offs,” Machine Learning with Applications, vol. 17, p. 100572, Sep. 2024, doi: 10.1016/j.mlwa.2024.100572.
D. P. Kingma and J. Ba, “Adam: A Method for Stochastic Optimization,” Dec. 2014, doi: 10.48550/arXiv.1412.6980.
I. Goodfellow, Y. Bengio, and A. Courville, “Optimization for Training Deep Models,” in Deep Learning, MIT Press, 2016.
S. Visa, B. Ramsay, A. L. Ralescu, and E. Van Der Knaap, “Confusion Matrix-based Feature Selection,” in Proceedings of the Twenty¬second Midwest Artificial Intelligence and Cognitive Science Conference, Madison: Omnipress, 2011, pp. 120–127.
H. M and S. M.N, “A Review on Evaluation Metrics for Data Classification Evaluations,” International Journal of Data Mining & Knowledge Management Process, vol. 5, no. 2, pp. 01–11, Mar. 2015, doi: 10.5121/ijdkp.2015.5201.
