Implementasi K-Nearest Neighbors (KNN) untuk Prediksi Kerusakan dan Perencanaan Peremajaan Alat Berat
Keywords:
predictive maintenance, k-nearest neighbors, heavy equipment, agile methodologyAbstract
Industri pertambangan sangat bergantung pada keandalan alat berat. Permasalahan utama di XXX Group adalah tingginya unplanned downtime akibat strategi perawatan reaktif. Penelitian ini bertujuan mengintegrasikan predictive maintenance menggunakan algoritma K-Nearest Neighbors (KNN) untuk memprediksi kerusakan dan merencanakan peremajaan alat berat. Sistem dikembangkan menggunakan metode Agile dengan enam variabel prediktor: jam operasi, tahun alat, frekuensi perbaikan, jenis kerusakan, kondisi lingkungan, dan status akhir tahun. Hasil pengujian dengan parameter K=5 dan jarak Euclidean menunjukkan sistem mampu mengklasifikasikan kelayakan alat secara akurat. Pada studi kasus unit EXC-026, sistem mendeteksi anomali (3 parameter Kritis, 2 Waspada) dan merekomendasikan "Perlu Peremajaan" dengan probabilitas kerusakan 100% berdasarkan 5 tetangga terdekat. Implementasi ini mentransformasi perawatan di XXX Group menjadi proaktif, meminimalisir biaya tak terduga, dan memberikan landasan presisi untuk keputusan peremajaan aset.
References
Alsaqqa, S., Sawalha, S., & Abdel-Nabi, H. (2020). Agile software development: Methodologies and trends. International Journal of Interactive Mobile Technologies, 14(11), 246–270.
Brown, D., Smith, A., & Lee, J. (2019). Data-driven decision making in asset life cycle management. Journal of Heavy Engineering, 34(2), 112–125.
Bryman, A. (2021). Social Research Methods (6th ed.). Oxford University Press.
Chen, Q. L., & Zhou, Z. H. (2016). Unusual formations of superoxo heptaoxomolybdates from peroxo molybdates. Inorganic Chemistry Communications, 67(3), 95–98. https://doi.org/10.1016/j.inoche.2016.03.015
Chen, X., Wang, Y., & Zhao, Q. (2020). Degradation models for heavy mining machinery in extreme environments. Mining Equipment & Technology Journal, 45(4), 56–68.
Cover, T., & Hart, P. (1967). Nearest neighbor pattern classification. IEEE Transactions on Information Theory, 13(1), 21–27.
Creswell, J. W., & Creswell, J. D. (2023). Research Design: Qualitative, Quantitative, and Mixed Methods Approaches (6th ed.). SAGE Publications.
Garcia, M., Lopez, J., & Martinez, R. (2021). Adaptive algorithms in dynamic industrial environments. Industrial Computing Review, 29(1), 44–59.
Garcia, M., Perez, S., & Gomez, L. (2023). Enhancing asset lifecycle predictions using K-Nearest Neighbors in extreme operational conditions. International Journal of Predictive Analytics, 18(2), 77–92.
Kumar, R., Singh, A., & Gupta, P. (2019). The cost of reactive maintenance in the mining sector. Journal of Mining Economics, 22(3), 204–219.
Lee, S., & Park, K. (2020). Non-linear data pattern handling using supervised learning in limited datasets. Data Science in Heavy Industries, 8(4), 310–325.
Patel, V. (2023). Budget optimization through proactive maintenance scheduling. Industrial Management & Data Systems, 41(2), 150–165.
Saunders, M., Lewis, P., & Thornhill, A. (2022). Research Methods for Business Students (9th ed.). Pearson.
Smith, J., & Johnson, T. (2021). Unplanned downtime and its financial impacts on continuous production operations. Journal of Operational Excellence, 33(1), 45–58.
Stoica, M., Mircea, M., & Ghilic-Micu, B. (2022). Agile frameworks in academic and industrial application development. Software Engineering Perspectives, 27(3), 201–215.
Wang, H., & Li, C. (2022). Financial benefits of data-driven predictive maintenance in heavy industries. International Journal of Production Economics, 245, 108392.
Zhang, Y., Wu, D., & Chen, L. (2023). Multivariable analysis for degradation tracking in heavy machinery. Reliability Engineering & System Safety, 230, 108954.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Yudistira Sira Permana, Yussi Rapareni, Muhammad Syahril
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
