OPTIMASI STOCHASTIC GRADIENT DESCENT ADAPTIF UNTUK PREDIKSI OEE REAL-TIME PADA SISTEM PENGISIAN BOTOL ELEKTRONIK BERBASIS PLC
Keywords:
OEE prediction, bottle filling systems, SGD optimization, Omron CP2E, PLC integrationAbstract
This study develops an adaptive Stochastic Gradient Descent (SGD) optimization method for real-time Overall Equipment Effectiveness (OEE) prediction in industrial PLC-based electronic bottle filling systems. A neural network model was implemented using a dataset of 40,000 production samples with the format [operating_time, downtime, total_count, good_count, pressure, OEE]. Experimental results showed high accuracy (R² = 0.9906; MAE = 0.0076) with an inference time of 1.2 ms per cycle. Analysis revealed that good_count (59.41%) and system pressure (25.42%) are the dominant factors for OEE. The implementation of adaptive control increased production efficiency by 22.7% in a system with a 30L capacity and a speed of 4 bottles per minute
References
DAFTAR PUSTAKA
Trentini, R., Campos, A., Espindola, G., & Silveira, A. da S. (2015). Parameter identification of a pneumatic proportional pressure valve.Journal of The Brazilian Society of Mechanical Sciences and Engineering. https://doi.org/10.1007/S40430-014-0144-0
G, L. (2022, December 28).Cost Efficient Automatic Filling System for Differently Sized Bottles. https://doi.org/10.1109/ICMACC54824.2022.10093437
Abashar, A. I., Mohammedeltoum, M. A., & Abaker, O. D. (2017, January 1).Automated and monitored liquid filling system using PLC technology. https://doi.org/10.1109/ICCCCEE.2017.7866699
Xue, F., Hai, Q., Dong, T., Cui, Z., & Gong, Y. (2022). A deep reinforcement learning based hybrid algorithm for efficient resource scheduling in edge computing environment.Information Sciences. https://doi.org/10.1016/j.ins.2022.06.078
Xie, W., Tang, W., & Kuang, Y. (2022). A new hybrid optimizer for stochastic optimization acceleration of deep neural networks: Dynamical system perspective.Neurocomputing. https://doi.org/10.1016/j.neucom.2022.09.147
Susto, G. A., Wan, J., Pampuri, S., Zanon, M., Johnston, A., O’Hara, P. G., & McLoone, S. (2014, October 30). An adaptive machine learning decision system for flexible predictive maintenance.Conference on Automation Science and Engineering. https://doi.org/10.1109/COASE.2014.6899418
Hesabi, H., Nourelfath, M., & Hajji, A. (2022). A deep learning predictive model for selective maintenance optimization.Reliability Engineering & System Safety. https://doi.org/10.1016/J.RESS.2021.108191
Yeganeh, S., Babazadeh Sangar, A., & Azizi, S. (2023). A novel Q-learning-based hybrid algorithm for the optimal offloading and scheduling in mobile edge computing environments.Journal of Network and Computer Applications. https://doi.org/10.1016/j.jnca.2023.103617
An Adaptive Gradient Method with Energy and Momentum. (2022). https://doi.org/10.4208/aam.oa-2021-0095
Li, D., Abhadiomhen, S. E., Zhou, D., Shen, X.-J., Shi, L., Cui, Y., & Abhadiomhen, S. E. (n.d.).Asthma prediction via affinity graph enhanced classifier: a machine learning approach based on routine blood biomarkers.
de Ron, A. J., & Rooda, J. E. (2006). OEE and equipment effectiveness: an evaluation.International Journal of Production Research. https://doi.org/10.1080/00207540600573402
Santos, P. V. S. (2018). Aplicação do indicador overall equipment effectiveness (oee): um estudo de caso numa retífica e oficina mecânica.Brazilian Journal of Production Engineering - BJPE.
Razavi, M., Ziyadidegan, S., Jahromi, R., Kazeminasab, S., Janfaza, V., Mahmoudzadeh, A., Baharlouei, E., & Sasangohar, F. (n.d.).Machine Learning, Deep Learning and Data Preprocessing Techniques for Detection, Prediction, and Monitoring of Stress and Stress-related Mental Disorders: A Scoping Review.
Uvarov, I. V., Melenev, A. E., Selyukov, R. V., & Svetovoy, V. B. (2020). Improving the performance of the fast electrochemical actuator.Sensors and Actuators A-Physical. https://doi.org/10.1016/J.SNA.2020.112346
Aulia, D., Sar, R., Hidaya, C., Rivai, M., & Sarno, R. (n.d.).Optimization of the Electronic Nose Sensor Array for Asthma Detection Based on Genetic Algorithm.
Yu, L., Wu, W., He, G., & Yu, W. (2019).Dynamic Variance Analysis of One-Dimensional Signal in Gaussian Noise Based on Recursive Formula. https://doi.org/10.1007/978-3-030-34387-3_89
Chella, A., & Sorbello, F. (1992).Fast Convergence of Neural Networks by Application of a New Min-Max Algorithm. https://doi.org/10.1016/B978-0-444-89488-5.50040-3
Liu, C., & Belkin, M. (2020, April 30). Accelerating SGD with momentum for over-parameterized learning.International Conference on Learning Representations.
Zhou, K., Jin, Y., Ding, Q., & Cheng, J. (2020, August 27). Amortized Nesterov’s Momentum: A Robust Momentum and Its Application to Deep Learning.Uncertainty in Artificial Intelligence.
Su, S., Wu, Y., & Qian, W. (2018, June 24). Efficient batch statistical error estimation for iterative multi-level approximate logic synthesis.Design Automation Conference. https://doi.org/10.1145/3195970.3196038
Duchi, J., Hazan, E., & Singer, Y. (2011). Adaptive subgradient methods for online learning and stochastic optimization. Journal of Machine Learning Research, 12, 2121–2159.
Khayyati, S., Bobarshad, H., Liu, Z., & Wang, X. (2021). A lab-scale manufacturing system for data-driven production control. Journal of Manufacturing Systems, 60, 132–145. https://doi.org/10.1016/j.jmsy.2021.05.011
Omron Corporation. (2023). CP2E CPU Unit Manual. Kyoto, Japan: Omron.
Trentini, R., Campos, A., Espindola, G., & Silveira, A. da S. (2015). Parameter identification of a pneumatic proportional pressure valve. Journal of the Brazilian Society of Mechanical Sciences and Engineering, 37(3), 1047–1055. https://doi.org/10.1007/s40430-014-0144-0
de Ron, A. J., & Rooda, J. E. (2006). OEE and equipment effectiveness: An evaluation. International Journal of Production Research, 44(23), 4987–5006. https://doi.org/10.1080/00207540600573402
Herrera-Alcántara, O. (2020). Fractional-order gradient descent optimization. Fractional Calculus and Applied Analysis, 23(4), 1090–1105. https://doi.org/10.1515/fca-2020-0056
Iiduka, H. (2020). Appropriate learning rates of adaptive learning rate optimization algorithms. arXiv preprint arXiv:2002.09647. https://doi.org/10.48550/arXiv.2002.09647
Indonesian Society of Applied Science (ISAS)
