Analisis Komparatif Algoritma LSTM, GRU, BiGRU, dan BiLSTM Untuk Prediksi Degradasi Bearing Turbin PLTU

Rifky Raymond, Neva Saputra, Meldrin Tupamahu, Neng Ayu Herawati, Ayu Purwarianti, Nugraha Priya Utama

Abstract


Pembangkit Listrik Tenaga Uap (PLTU) merupakan salah satu sumber utama pasokan listrik nasional, di mana keandalan komponen kritis seperti bearing turbin sangat menentukan kontinuitas operasional. Kegagalan pada bearing dapat menyebabkan downtime tidak terduga dan kerugian biaya yang signifikan. Oleh karena itu, pendekatan predictive maintenance menjadi strategi penting dalam memitigasi potensi kegagalan tersebut. Penelitian ini bertujuan untuk membandingkan performa empat algoritma deep learning yaitu LSTM, GRU, BiGRU, dan BiLSTM dalam memprediksi Remaining Useful Life (RUL) dari bearing turbin. Data yang digunakan merupakan data sensor aktual dari pembangkit, yang telah direduksi dimensinya menggunakan Principal Component Analysis (PCA) untuk membentuk Health Index sebagai representasi degradasi peralatan. Evaluasi dilakukan menggunakan metrik MAE (Mean Absolute Error) dan RMSE (Root Mean Squared Error). Hasil eksperimen menunjukkan bahwa model BiLSTM memiliki performa terbaik dengan nilai MAE sebesar 0.27 dan RMSE sebesar 0.37. Penelitian ini berkontribusi dalam menyediakan panduan pemilihan model prediksi RUL berbasis data sensor riil pada peralatan PLTU, yang mendukung penerapan pemeliharaan prediktif secara lebih akurat dan efisien

Keywords


BiGRU; BiLSTM; GRU; LSTM; Remaining Useful Life

References


M. Bělohoubek, K. Liška, Z. Kubín, P. Polcar, L. Smolík dan P. Polach, “An Investigation of Efficiency Issues in a Low-Pressure Steam Turbine Using Neural Modelling,†Sensors, vol. 24, no. 7, p. 2056, 2024.

H. Peng, H. Zhang, L. Shangguan dan Y. Fan, “Review of Tribological Failure Analysis and Lubrication Technology Research of Wind Power Bearings,†Polymers, p. 14, 2022.

S. Pashami, S. Nowaczyk, Y. Fan, J. Jakubowski, N. Paiva, N. Davari, S. Bobek, S. Jamshidi, H. Sarmadi, A. Alabdallah, B. V. Rita P. Ribeiro, M. Sayed-Mouchaweh, L. Rajaoarisoa dan G. J. Nalepa, “Explainable Predictive Maintenance,†2023.

M. Kraus dan S. Feuerriegel, “Forecasting remaining useful life: Interpretable deep learning approach via variational Bayesian inferences,†Decision Support Systems, vol. 125, p. 113100, 2019.

M. Pirani, P. Thakkar, P. Jivrani, M. H. Bohara dan D. Garg, “A Comparative Analysis of ARIMA, GRU, LSTM and BiLSTM on Financial Time Series Forecasting,†dalam 2022 IEEE International Conference on Distributed Computing and Electrical Circuits and Electronics (ICDCECE), Ballari, India, 2022.

Y. Li, X. Qin, F. Ma, H. Wu, M. Chai, F. Zhang, F. Jiang dan X. Lei, “Fusion Technology-Based CNN-LSTM-ASAN for RUL Estimation of Lithium-Ion Batteries,†Sustainability , vol. 16, no. 21, p. 9223, 2024.

P. R. d. O. d. Costa, J. Rhuggenaath, Y. Zhang dan A. Akcay, “Learning 2-opt Heuristics for the Traveling Salesman Problem via Deep Reinforcement Learning,†dalam In Proceedings of the Asian Conference on Machine Learning (ACML 2020), PMLR, 2020.

S. Sayyad, S. Kumar, A. Bongale, K. Kotecha dan A. Abraham', “Remaining Useful-Life Prediction of the Milling Cutting Tool Using Time–Frequency-Based Features and Deep Learning Models,†Sensors, vol. 23, no. 12, p. 5659, 2023.

D. Zhao, H. Li, F. Zhou, Y. Zhong, G. Zhang, Z. Liu dan J. Hou, “Research Progress on Data-Driven Methods for Battery States Estimation of Electric Buses,†World Electric Vehicle Journal, vol. 14, no. 6, p. 145, 2023.

X. Tang, H. Wan, W. Wang, M. Gu, L. Wang dan L. Gan, “Lithium-Ion Battery Remaining Useful Life Prediction Based on Hybrid Model,†Sustainability, vol. 15, no. 7, p. 6261, 2023.

K. Basulaiman dan M. Barati, “Sequence-to-Sequence Forecasting-aided State Estimation for Power Systems,†dalam 2021 IEEE Texas Power and Energy Conference (TPEC), College Station, TX, USA, 2021.

Y. Hu, Y. Bai, E. Fu dan P. Liu, “A Novel Remaining Useful Life Probability Prediction Approach for Aero-Engine with Improved Bayesian Uncertainty Estimation Based on Degradation Data,†Applied Sciences, vol. 13, no. 16, p. 9194, 2023.

Y. Liu, J. Liu, H. Wang, M. Yang, X. Gao dan S. Li, “A Remaining Useful Life Prediction Method of Mechanical Equipment Based on Particle Swarm Optimization-Convolutional Neural Network-Bidirectional Long Short-Term Memory,†Machines, vol. 12, no. 5, p. 342, 2024.

V. Plotnikova, M. Dumas dan F. Milani, “Adaptations of data mining methodologies: a systematic literature review,†PeerJ Computer Science, 2020.

C. Schröer, F. Kruse dan J. M. Gómez, “A Systematic Literature Review on Applying CRISP-DM Process Model,†Procedia Computer Science, vol. 181, pp. 526-534, 2021.

D. T. Wiranata, T. Prahasto dan A. Widodo, “Analisis Prognostik Terhadap Kerusakan Bantalan Pada Poros Kecepatan Tinggi Turbin Angin Menggunakan Machine Learning Dengan Pendekatan Support Vector Regression (SVR),†Jurnal Teknik Mesin Universitas Diponegoro, vol. 9, 2021.

A. Dokumentov dan R. J. Hyndman, “STR: Seasonal-Trend Decomposition Using Regression,†INFORMS Journal on Data Science, 2020.

R. C. Ripan, I. H. Sarker, M. M. Anwar, M. H. Furhad, F. Rahat, M. M. Hoque dan M. Sarfraz, “An Isolation Forest Learning Based Outlier Detection Approach for Effectively Classifying Cyber Anomalies,†International Conference on Health Information Science, 2020.

Y. Xia dan G. M. J. Barca, “Machine-Learning-Driven Runtime Optimization of BLAS Level 3 on Modern Multi-Core Systems,†arXiv, 2024.

A. Omogbai, “Application of multiview techniques to NHANES dataset,†arXiv.org, 2016.

J. Farshad dan C. Arthur, “Striking a New Chord: Neural Networks in Music Information Dynamics,†arXiv.org, 2024.

S. Zhang, M. Wang, W. Wang, J. Gao, W. Zhao dan Y. Yang, “GLINT-RU: Gated Lightweight Intelligent Recurrent Units for Sequential Recommender Systems,†Knowledge Discovery and Data Mining, 2024.

J.-H. Lee dan J.-K. Hong, “Comparative Performance Analysis of RNN Techniques for Predicting Concatenated Normal and Abnormal Vibrations,†Electronics, 2023.

O. Ozupek, R. Yilmaz, B. Ghasemkhani, D. Birant dan R. A. Kut, “A Novel Hybrid Model (EMD-TI-LSTM) for Enhanced Financial Forecasting with Machine Learning,†Mathematics, 2024.

M. I. Rifki, A. Ikhwan dan F. Muhammad, “Performance Evaluation of RSSI Prediction Methods in Wireless Communication Networks,†Zero: Jurnal Sains, Matematika, dan Terapan, vol. 8, pp. 14-25, 2024.

W. Li, X. Li, Q. Niu, T. Huang, D. Zhang dan Y. Dong, “Analysis and Treatment of Shutdown Due to Bearing Vibration Towards Ultra-supercritical 660MW Turbine,†dalam IOP Conference Series: Earth and Environmental Science, 2019.




DOI: http://dx.doi.org/10.30811/jim.v10i1.7127

Refbacks

  • There are currently no refbacks.


Copyright (c) 2025 Neva Saputra, Rifky Raymond, Neva Saputra, Meldrin Tupamahu, Neng Ayu Herawati, Ayu Purwarianti, Nugraha Priya Utama