Predicting Computer Numerical Control (CNC) Machine Downtime using Ensemble Learning Approaches

Amir Aminuddin; Adam  Shariff; Kamarulzaman Mahmad Khairai

doi:10.62048/qjms.v3i1.137

Penulis

Amir Aminuddin Centre of Mathematical Science, Universiti Malaysia Pahang Al-Sultan Abdullah, Gambang, Malaysia
Adam Shariff Centre of Mathematical Science, Universiti Malaysia Pahang Al-Sultan Abdullah, Gambang, Malaysia
Kamarulzaman Mahmad Khairai Faculty of Industrial Management, Universiti Malaysia Pahang Al-Sultan Abdullah, Gambang, Malaysia

DOI:

https://doi.org/10.62048/qjms.v3i1.137

Kata Kunci:

CNC, pembelajaran mesin, downtime, pemeliharaan prediktif

Abstrak

Pemesinan Computer Numerical Control (CNC) merupakan teknik manufaktur subtraktif yang menghilangkan lapisan material dari bahan awal atau benda kerja untuk menghasilkan produk tertentu. Seiring dengan meningkatnya persaingan global, meminimalkan waktu henti (downtime) selama proses produksi menjadi sangat penting untuk memaksimalkan ketersediaan mesin dan produktivitas. Penelitian ini mengkaji penerapan model machine learning, khususnya Extreme Gradient Boosting (XGBoost) dan Random Forest (RF), untuk memprediksi waktu henti mesin CNC yang berasal dari berbagai sumber kegagalan. Penelitian ini menggunakan data yang dikumpulkan dari 16 mesin CNC di Perusahaan A di Malaysia selama periode waktu yang cukup panjang. Data tersebut mencakup variabel-variabel utama untuk setiap kejadian downtime, seperti identitas mesin, jenis kegagalan, waktu mulai, waktu selesai, dan durasi downtime dalam satuan menit. Jenis kegagalan diklasifikasikan ke dalam beberapa kategori, termasuk kegagalan mekanik, listrik, dan perkakas. Setelah dilakukan penyetelan hiperparameter, model XGBoost menunjukkan kinerja yang lebih unggul dibandingkan model RF, dengan nilai Mean Squared Error (MSE) sebesar 0,4017, Root Mean Squared Error (RMSE) sebesar 0,634, dan Mean Absolute Error (MAE) sebesar 0,470 pada data uji. Sebaliknya, model RF menghasilkan tingkat kesalahan yang lebih tinggi, dengan MSE sebesar 1,2654, RMSE sebesar 1,125, dan MAE sebesar 0,943. Hasil ini menunjukkan keunggulan model XGBoost dibandingkan RF dalam memprediksi downtime mesin CNC di masa mendatang, sebagaimana tercermin dari nilai kesalahan prediksi yang lebih rendah. Penelitian selanjutnya disarankan untuk menyempurnakan model dengan menggunakan dataset yang lebih besar dan lebih beragam, serta mengeksplorasi integrasinya ke dalam sistem pendukung keputusan berbasis kecerdasan buatan untuk meningkatkan ketersediaan mesin dan efisiensi operasional.

Referensi

Abdallah, A. B., Maaroufi, M., & Ouali, M. S. (2016). Dealing with machine deterioration and failures in manufacturing systems. International Journal of Production Research, 54(23), 7245–7272.

Abellán-Nebot, J. V., Liu, J., & Romero Subirón, F. (2012). Quality prediction and compensation in multi-station machining processes using sensor-based fixtures. Robotics and Computer-Integrated Manufacturing, 28(2), 208–219. https://doi.org/10.1016/j.rcim.2011.09.001

Alaswad, S., & Xiang, Y. (2017). A review on condition-based maintenance optimization models for stochastically deteriorating systems. Reliability Engineering & System Safety, 157, 54–63. https://doi.org/10.1016/j.ress.2016.08.009

Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32. https://doi.org/10.1023/A:1010933404324

Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. Dalam Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 785–794). ACM. https://doi.org/10.1145/2939672.2939785

Cochran, D. S., Arinez, J. F., Duda, J. W., & Linck, J. (2001). A decomposition approach for manufacturing system design. Journal of Manufacturing Systems, 20(6), 371–389. https://doi.org/10.1016/S0278-6125(01)80058-3

Djurdjanovic, D., Lee, J., & Ni, J. (2003). Watchdog agent—An infotronics-based prognostics approach for product performance degradation assessment and prediction. Advanced Engineering Informatics, 17(3–4), 109–125. https://doi.org/10.1016/j.aei.2004.07.005

Genuer, R., Poggi, J.-M., & Tuleau-Malot, C. (2010). Variable selection using random forests. Pattern Recognition Letters, 31(14), 2225–2236. https://doi.org/10.1016/j.patrec.2010.03.014

Hussain, Z., & Jan, H. (2019). Establishing simulation model for optimizing efficiency of CNC machine using reliability-centered maintenance approach. International Journal of Modeling, Simulation, and Scientific Computing, 10(6), 1950034. https://doi.org/10.1142/S179396231950034X

Jantunen, E. (2002). A summary of methods applied to tool condition monitoring in drilling. International Journal of Machine Tools and Manufacture, 42(9), 997–1010. https://doi.org/10.1016/S0890-6955(02)00040-8

Jauregui Becker, J. M., Borst, J., & van der Veen, A. (2015). Improving the overall equipment effectiveness in high-mix–low-volume manufacturing environments. CIRP Annals, 64(1), 419–422. https://doi.org/10.1016/j.cirp.2015.04.126

Keller, A. Z., Kamath, A. R. R., & Perera, U. D. (1982). Reliability analysis of CNC machine tools. Reliability Engineering, 3(6), 449–473. https://doi.org/10.1016/0143-8174(82)90036-1

Khan, M. Y., Qayoom, A., Nizami, M. S., Siddiqui, M. S., Wasi, S., & Raazi, S. M. K.-R. (2021). Automated prediction of good dictionary examples (GDEX): A comprehensive experiment with distant supervision, machine learning, and word embedding-based deep learning techniques. Complexity, 2021, Article 2553199. https://doi.org/10.1155/2021/2553199

Lee, J., Wu, F., Zhao, W., Ghaffari, M., Liao, L., & Siegel, D. (2014). Prognostics and health management design for rotary machinery systems: Reviews, methodology, and applications. Mechanical Systems and Signal Processing, 42(1–2), 314–334. https://doi.org/10.1016/j.ymssp.2013.06.004

Malhotra, P., TV, V., Ramakrishnan, A., Anand, G., Vig, L., Agarwal, P., & Shroff, G. (2016). Multi-sensor prognostics using an unsupervised health index based on LSTM encoder–decoder. arXiv. https://doi.org/10.48550/arXiv.1608.06154

Mitchell, R., & Frank, E. (2017). Accelerating the XGBoost algorithm using GPU computing. PeerJ Computer Science, 3, e127. https://doi.org/10.7717/peerj-cs.127

Muchiri, P. N., Pintelon, L., Martin, H., & Chemweno, P. (2014). Modelling maintenance effects on manufacturing equipment performance: Results from simulation analysis. International Journal of Production Research, 52(11), 3287–3302. https://doi.org/10.1080/00207543.2013.870673

Newman, S. T., Nassehi, A., Imani-Asrai, R., & Dhokia, V. (2012). Energy efficient process planning for CNC machining. CIRP Journal of Manufacturing Science and Technology, 5(2), 127–136. https://doi.org/10.1016/j.cirpj.2012.03.007

Özel, T., & Karpat, Y. (2005). Predictive modeling of surface roughness and tool wear in hard turning using regression and neural networks. International Journal of Machine Tools and Manufacture, 45(4–5), 467–479. https://doi.org/10.1016/j.ijmachtools.2004.09.007

Output Industries. (2024). Understanding the real costs of machine downtime in manufacturing. https://www.output.industries/insights/costs-of-machine-downtime-in-manufacturing

Pavlyshenko, B. (2019). Machine-learning models for sales time series forecasting. Data, 4(1), 15. https://doi.org/10.3390/data4010015

Pimenov, D. Y., Bustillo, A., Wojciechowski, S., Sharma, V. S., Gupta, M. K., & Kunto?lu, M. (2023). Artificial intelligence systems for tool condition monitoring in machining: Analysis and critical review. Journal of Intelligent Manufacturing, 34(5), 2079–2121. https://doi.org/10.1007/s10845-022-01923-2

Roosefert Mohan, T., Preetha Roselyn, J., Annie Uthra, R., Devaraj, D., & Umachandran, K. (2021). Intelligent machine learning-based total productive maintenance approach for achieving zero downtime in industrial machinery. Computers & Industrial Engineering, 157, 107267. https://doi.org/10.1016/j.cie.2021.107267

Soori, M., Arezoo, B., & Dastres, R. (2023). Machine learning and artificial intelligence in CNC machine tools: A review. Sustainable Manufacturing and Service Economics, 2, 100009. https://doi.org/10.1016/j.smse.2023.100009

Soori, M., Ghaleh Jough, F. K., Dastres, R., & Arezoo, B. (2024). Sustainable CNC machining operations: A review. Sustainable Operations and Computers, 5, 73–87. https://doi.org/10.1016/j.susoc.2024.01.001

Sun, Y., Ma, L., Mathew, J., Wang, W., & Zhang, S. (2006). Mechanical systems hazard estimation using condition monitoring. Mechanical Systems and Signal Processing, 20(5), 1189–1201. https://doi.org/10.1016/j.ymssp.2004.10.009

Traini, E., Bruno, G., D’Antonio, G., & Lombardi, F. (2019). Machine learning framework for predictive maintenance in milling. IFAC-PapersOnLine, 52(13), 177–182. https://doi.org/10.1016/j.ifacol.2019.11.172

Wan, S., Li, D., Gao, J., & Li, J. (2019). A knowledge-based machine tool maintenance planning system using case-based reasoning techniques. Robotics and Computer-Integrated Manufacturing, 58, 80–96. https://doi.org/10.1016/j.rcim.2019.01.012

Widodo, A., & Yang, B.-S. (2011). Machine health prognostics using survival probability and support vector machine. Expert Systems with Applications, 38(7), 8430–8437. https://doi.org/10.1016/j.eswa.2011.01.038

Xiao, Y., Jiang, Z., Gu, Q., Yan, W., & Wang, R. (2021). A novel approach to CNC machining center processing parameters optimization considering energy-saving and low-cost. Journal of Manufacturing Systems, 59, 535–548. https://doi.org/10.1016/j.jmsy.2021.03.023

Yao, X., Fu, X., & Zong, C. (2022). Short-term load forecasting method based on feature preference strategy and LightGBM–XGBoost. IEEE Access, 10, 75257–75268. https://doi.org/10.1109/ACCESS.2022.3192011

Ye, Y., Hu, T., Zhang, C., & Luo, W. (2018). Design and development of a CNC machining process knowledge base using cloud technology. The International Journal of Advanced Manufacturing Technology, 94(9–12), 3413–3425. https://doi.org/10.1007/s00170-016-9338-1

Zhou, P., Li, Z., Snowling, S., Baetz, B. W., Na, D., & Boyd, G. (2019). A random forest model for inflow prediction at wastewater treatment plants. Stochastic Environmental Research and Risk Assessment, 33(10), 1781–1792. https://doi.org/10.1007/s00477-019-01732-9