EKSPLORASI MODEL PREDICTIVE MAINTENANCE UNTUK PREDIKSI KEAUSAN PAHAT PADA PROSES MILLING MENGGUNAKAN MACHINE LEARNING (STUDI KASUS: DATASET NASA)

*Akmal Fathurohman Pratama  -  Department of Mechanical Engineering, Universitas Diponegoro, Jl. Prof. Sudarto, SH, Tembalang, Semarang, Indonesia 50275, Indonesia

Citation Format:
Abstract

Industri 4.0 mendorong integrasi sistem digital untuk mengurangi kegagalan produksi yang tidak terduga, di mana keausan pahat (tool wear) menjadi tantangan signifikan karena sulit diprediksi secara real-time. Penelitian ini bertujuan mengeksplorasi model prediksi keausan pahat menggunakan machine learning berbasis dataset NASA Milling guna mendukung strategi predictive maintenance. Metodologi meliputi akuisisi data, preprocessing, dan feature engineering untuk mengekstraksi indikator fisik seperti wear rate, total vibration, total acoustic emission, dan cutting intensity. Hasil penelitian menunjukkan bahwa Logistic Regression adalah model terbaik dengan akurasi 76,5% dan nilai recall mencapai 93,3%. Tingginya recall membuktikan keandalan model dalam meminimalkan risiko false negative yang berpotensi merusak benda kerja. Penelitian menyimpulkan bahwa melalui feature engineering yang tepat, model linear sederhana mampu memberikan prediksi yang lebih stabil dibandingkan model kompleks pada dataset industri yang terbatas.

Fulltext View|Download Email colleagues
Keywords: dataset nasa; feature engineering; machine learning; milling; predictive maintenance
Article Info
Section: Articles
Language : ID
  1. Z. M. Çınar, A. A. Nuhu, Q. Zeeshan, and O. Korhan, “Machine Learning in Predictive Maintenance towards Sustainable Smart Manufacturing in Industry 4.0,” Sustainability, vol. 12, no. 19, pp. 1–42, 2020
  2. F. Pashmforoush, A. Ebrahimi Araghizad, and E. Budak, “Tool wear prediction in milling process using physics-informed machine learning and thermo-mechanical force model with monitoring applications,” J. Manuf. Syst., vol. 82, no. February, pp. 1192–1212, 2025, doi: 10.1016/j.jmsy.2025.08.014
  3. Z. He, T. Shi, J. Xuan, and T. Li, “Research on tool wear prediction based on temperature signals and deep learning,” Wear, vol. 478–479, no. March, p. 203902, 2021, doi: 10.1016/j.wear.2021.203902
  4. A. Fertig, M. Weigold, and Y. Chen, “Machine Learning based quality prediction for milling processes using internal machine tool data,” Adv. Ind. Manuf. Eng., vol. 4, no. March, p. 100074, 2022, doi: 10.1016/j.aime.2022.100074
  5. R. Munaro, A. Attanasio, and A. Del Prete, “Tool Wear Monitoring with Artificial Intelligence Methods: A Review,” J. Manuf. Mater. Process., vol. 7, no. 4, 2023, doi: 10.3390/jmmp7040129
  6. K. Goebel and A. Agogino, “Documentation for Mill Data Set,” NASA Progn. Data Repos. NASA Ames Res. Cent., pp. 1–10, 2007, [Online]. Available: https://www.nasa.gov/content/prognostics-center-of-excellence-data-set-repository
  7. K. Danach, H. Harb, H. Issa, and L. Saker, “An explainable data-driven optimization framework for industrial predictive maintenance scheduling,” Results Eng., vol. 29, no. October 2025, p. 109022, 2026, doi: 10.1016/j.rineng.2026.109022
  8. H. Chen, J. Yang, Q. Qi, and H. Ding, “A robotic grinding parameter optimization approach considering tool wear to guarantee material removal accuracy and surface quality,” J. Manuf. Process., vol. 159, no. December 2025, pp. 228–242, 2026, doi: 10.1016/j.jmapro.2026.01.001
  9. P. Zhang et al., “Tool wear monitoring and multi-step forecasting in deep hole boring based on physics-informed neural network and ARIMA model,” Mech. Syst. Signal Process., vol. 249, no. February, p. 114078, 2026, doi: 10.1016/j.ymssp.2026.114078
  10. G. Yin, Z. Wu, F. Jiang, J. Shen, and X. Wu, “Monitoring tool wear during turning process using surface strain sensor,” Results Eng., vol. 29, no. January, 2026, doi: 10.1016/j.rineng.2026.109297
  11. Q. Zhu et al., “Application of machine learning in the design of biomedical nanomaterials,” Chem. Eng. J., vol. 530, no. October 2025, p. 173408, 2026, doi: 10.1016/j.cej.2026.173408
  12. C. He, D. Huang, R. Jia, and X. Wang, “Machine learning and insurer failure prediction,” Int. J. Forecast., no. xxxx, 2026, doi: 10.1016/j.ijforecast.2025.12.004
  13. R. Sharma, “How is AI For Predictive Maintenance Beneficial To Improving Manufacturing Efficiency?,” Markovate. [Online]. Available: https://markovate.com/ai-for-predictive-maintenance/

Last update:

No citation recorded.

Last update:

No citation recorded.