Sistem Prediktif Pemeliharaan Hidraulik dengan Pendekatan Algoritma Histogram Gradient Boosting
DOI:
https://doi.org/10.70609/jusifor.v5i1.9630Kata Kunci:
Predictive maintenance, Sistem hidrolik, Histogram gradient boosting, StreamlitAbstrak
Sistem hidrolik banyak digunakan dalam industri karena kepadatan daya tinggi dan kontrol presisi, namun kegagalan pada komponen seperti cooler, valve, pump leakage, dan hydraulic accumulator dapat menyebabkan downtime serta biaya perawatan tinggi. Pendekatan pemeliharaan korektif maupun preventif masih kurang optimal karena bergantung pada inspeksi manual atau jadwal tetap. Oleh karena itu, penelitian ini menerapkan predictive maintenance berbasis machine learning untuk memprediksi kondisi komponen hidrolik secara lebih dini. Penelitian ini bertujuan memprediksi kondisi empat komponen utama (Cooler, Valve, Internal Pump Leakage, dan Hydraulic Accumulator), mengevaluasi model Histogram Gradient Boosting (HGB) menggunakan Accuracy dan F1-score macro, serta menerapkan model ke dalam aplikasi Streamlit. Dataset yang digunakan adalah Condition Monitoring of Hydraulic Systems dengan 2205 siklus operasi. Data sensor dari file .txt diolah menjadi fitur tabular per siklus, distandarisasi menggunakan StandardScaler, dan dibagi menjadi data latih dan data uji dengan rasio 70:30. Model dibangun sebagai empat model HGB terpisah dan dievaluasi menggunakan confusion matrix, Accuracy, dan F1-score macro. Hasil menunjukkan performa sangat baik, yaitu Cooler_condition (Accuracy 0,998; F1-score 0,998), Valve_condition (0,834; 0,786), Internal_pump_leakage (0,968; 0,963), dan Hydraulic_accumulator/bar (0,989; 0,987). Model yang telah dilatih disimpan dalam format .pkl dan diintegrasikan ke aplikasi Streamlit untuk menampilkan hasil prediksi secara interaktif serta menyediakan output tabel dan unduhan CSV.
Referensi
[1] J. Garcia, L. Rios-Colque, P. Alvaro, and L. Rojas, “Condition Monitoring and Predictive Maintenance in Industrial Equipment: An NLP-Assisted Review of Signal Processing, Hybrid Models, and Implementation Challenges,” Multidiscip. Digit. Publ. Inst., vol. 15, no. 10, 2025, doi: https://doi.org/10.3390/app15105465.
[2] J. Sun, H. Ding, N. Li, X. Sun, and X. Dong, “Intelligent Fault Diagnosis of Hydraulic System Based on Multiscale One-Dimensional Convolutional Neural Networks with Multiattention Mechanism,” Sensors, vol. 24, no. 22, pp. 1–19, 2024, [Online]. Available: https://doi.org/10.3390/s24227267
[3] J. Azeta et al., “Artificial Intelligence and Robotics in Predictive Maintenance: A Comprehensive Review,” Front. Mech. Eng., vol. 11, 2026, doi: https://doi.org/10.3389/fmech.2025.1722114.
[4] M. Achouch et al., “On Predictive Maintenance in Industry 4.0: Overview, Models, and Challenges,” Appl. Sci., vol. 12, no. 16, 2022, doi: https://doi.org/10.3390/app12168081.
[5] E. Hermawan, S. D. Panjaitan, and E. F. Ripanti, “Sistem Prediksi Banjir Rob Kota Pontianak Berbasis Machine Learning Menggunakan Framework Streamlit,” J. Edukasi Penelit. Inform., vol. 10, no. 3, 2024, doi: https://doi.org/10.26418/jp.v10i3.79955.
[6] C. Tsallis, P. Papageorgas, D. Piromalis, and R. A. Munteanu, “Application-Wise Review of Machine Learning-Based Predictive Maintenance: Trends, Challenges, and Future Directions,” Appl. Sci., vol. 15, no. 9, 2025, doi: https://doi.org/10.3390/app15094898.
[7] M. Mahetaji and J. Brahma, “Enhancing Wellbore Stability Through Machine Learning for Sustainable Hydrocarbon Exploitation,” Sci. Rep., vol. 15, no. 1, 2025.
[8] S. Sethi, “Predictive Maintenance in IoT Environments Using Machine Learning: Opportunities, Challenges, and Innovations,” Int. J. Innov. Res. Eng. Multidisplinary Phys. Sci., vol. 11, no. 4, 2023, doi: https://doi.org/10.5281/zenodo.14945146.
[9] P. Mallioris, E. Aivazidou, and D. Bechtsis, “Predictive Maintenance in Industry 4.0: A Systematic Multi-Sector Mapping,” CIRP J. Manuf. Sci. Technol., vol. 50, pp. 80–103, 2024, doi: https://doi.org/10.1016/j.cirpj.2024.02.003.
[10] J. Wu et al., “Fault Diagnosis of the HVDC System Based on the CatBoost Algorithm Using Knowledge Graphs,” Front. Energy Res., vol. 11, 2023, doi: https://doi.org/10.3389/fenrg.2023.1144785.
[11] S. M. Almazrouei, F. Dweiri, R. Aydin, and A. Alnaqbi, “An Ensemble Machine Learning Model for Predictive Maintenance on Water Injection Pumps in the Oil and Gas Industry,” Int. J. Adv. Comput. Sci. Appl., vol. 15, no. 11, 2024, doi: 10.14569/IJACSA.2024.0151141.
[12] D. Kim and T. Heo, “Anomaly Detection with Feature Extraction Based on Machine Learning Using Hydraulic System IoT Sensor Data,” Sensors, vol. 22, no. 7, 2022, doi: https://doi.org/10.3390/s22072479.
[13] H. N. Noura, T. Chu, Z. Allal, O. Salman, and K. Chahine, “A Comparative Study of Ensemble Methods and Multi-Output Classifiers for Predictive Maintenance of Hydraulic Systems,” Results Eng., vol. 24, 2024, doi: https://doi.org/10.1016/j.rineng.2024.102900.
[14] N. L. Fitriyani et al., “A Novel Approach Utilizing Bagging, Histogram Gradient Boosting, and Advanced Feature Selection for Predicting the Onset of Cardiovascular Diseases,” Mathematics, vol. 13, no. 13, 2025, doi: https://doi.org/10.3390/math13132194.
[15] F. A. Ramirez-Rivera and F. Guerrero-Rodriguez, “Ensemble Learning Algorithms for Solar Radiation Prediction in Santo Domingo: Measurements and Evaluation,” Sustainability, vol. 16, no. 18, 2024, doi: https://doi.org/10.3390/su16188015.
Unduhan
Diterbitkan
Terbitan
Bagian
Lisensi
Hak Cipta (c) 2026 Faizah Via Fadhillah, Muhammad Fatchan, Wahyu Hadikristanto
Artikel ini berlisensiCreative Commons Attribution-ShareAlike 4.0 International License.
