Deteksi Kegagalan Turbine GB-201 Menggunakan Metode Long Short Term Memory (LSTM) Pada Plant Ethylene Di PT Chandra Asri Pacific Tbk

Irsyad, Fairuz (2025) Deteksi Kegagalan Turbine GB-201 Menggunakan Metode Long Short Term Memory (LSTM) Pada Plant Ethylene Di PT Chandra Asri Pacific Tbk. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5009211110-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (3MB) | Request a copy

Abstract

Rotating equipment memiliki peranan penting dalam berbagai sektor industri. Pada faktanya, banyak penggunaan berkelanjutan dari mesin industri seperti pompa dan turbin uap bergantung pada kinerja rotating equipment-nya. Getaran sering kali ditemui pada berbagai kasus yang melibatkan mesin yang berputar atau rotating machinery. Salah satu rotating equipment esensial pada sebuah turbin adalah bearing. Pada penelitian ini penulis mencoba melakukan analisis deteksi vibrasi pada bearing turbin menggunakan neural networks metode Long Short Term Memory (LSTM). Data yang digunakan untuk pengolahan pada model neural networks berupa data historis maintenance pada PT. Chandra Asri Pacific Tbk berupa data sensor displacement vibrasi selama satu bulan terakhir. Pengolahan data dilakukan dengan dua tahap yaitu analisis statistik data vibrasi dan perancangan model prediksi vibrasi dengan metode LSTM. Model LSTM berhasil memprediksi nilai vibrasi beberapa masa yang akan datang. Untuk mengevaluasi performansi model, dilakukan perhitungan Root Mean Square Error (RMSE) dan Mean Absolute Error (MAE). Didapatkan nilai Root Mean Square Error (RMSE) dan Mean Absolute Error (MAE) pada vibrasi pada bearing 3.54 (4,86%) dan 2.89 (3.96%) pada data validasi. Didapatkan nilai Root Mean Square Error (RMSE) dan Mean Absolute Error (MAE) pada vibrasi pada bearing 2.673 (4.71%) dan 2.175 (3.88%) pada data testing. Hasil model prediksi yang dibangun dengan menggunakan metode LSTM memiliki nilai pengujian rata-rata RMSE < 6% dan MAE < 5% sehingga dapat dikatakan cukup baik.
========================================================================================================================
Rotating equipment plays a vital role across various industrial sectors. In fact, the continuous operation of industrial machines such as pumps and steam turbines largely depends on the performance of their rotating equipment. Vibrations are commonly encountered in many cases involving rotating machinery. One of the essential components in a turbine's rotating equipment is the bearing. In this study, the author conducted a vibration detection analysis on turbine bearings using a neural network method known as Long Short-Term Memory (LSTM).
The data used for training the neural network model consists of historical maintenance data from PT Chandra Asri Pacific Tbk, specifically vibration displacement sensor data collected over the past month. Data processing was carried out in two stages: statistical analysis of the vibration data and the design of a vibration prediction model using the LSTM method. The LSTM model successfully predicted future vibration values over several time steps. To evaluate the model's performance, Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) were calculated. The results showed that the RMSE and MAE for vibration at the bearing during the validation phase were 3.54 (4.86%) and 2.89 (3.96%), respectively. During the testing phase, the RMSE and MAE were 2.673 (4.71%) and 2.175 (3.88%), respectively. Based on these results, the predictive model built using the LSTM method achieved an average RMSE of less than 6% and an MAE of less than 5%, indicating a reasonably good performance.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Deteksi Kegagalan, Bearing, LSTM, Displacement, Failure Detection, Bearing, LSTM, Displacement.
Subjects:	Q Science > Q Science (General) > Q325.5 Machine learning. Support vector machines. Q Science > QA Mathematics > QA276 Mathematical statistics. Time-series analysis. Failure time data analysis. Survival analysis (Biometry) T Technology > TA Engineering (General). Civil engineering (General) > TA169.5 Failure analysis T Technology > TA Engineering (General). Civil engineering (General) > TA355 Vibration. T Technology > TJ Mechanical engineering and machinery > TJ174 Maintenance and repair of machinery
Divisions:	Faculty of Industrial Technology and Systems Engineering (INDSYS) > Physics Engineering > 30201-(S1) Undergraduate Thesis
Depositing User:	Fairuz Irsyad
Date Deposited:	04 Aug 2025 03:34
Last Modified:	04 Aug 2025 03:34
URI:	http://repository.its.ac.id/id/eprint/126216

Actions (login required)

View Item