Deteksi Kerusakan Bearing Menggunakan Metode Robust Principal Component Analysis (ROB PCA)

ABSTRACT. Bearings have an important role, because bearings are part of a machine element that if it has good health, the machine element can work properly. In this paper, bearing damage detection was carried out using the Principal Component Analysis (PCA) method and its development method, the Robust Principal Component Analysis (ROB PCA) method using the main monitoring index, namely the Squared Prediction Error (SPE). The purpose of this paper is to compare the main principal component method (PCA) and the main Robust Principal Component method (ROB PCA) on bearing vibration data for bearing damage detection. The data to be used is secondary data from bearing test experiments obtained from the Institute of Electrical and Electronic Engineers (IEEE) Prognostics and Health Management (PHM) 2012 through data storage from the FEMTO-ST Institute. Then, for data processing, Bearing1_1 vibration data in the horizontal direction is used and 11 statistical features are extracted. Based on the research that has been done, in detecting damage the PCA and ROBPCA methods are able to overcome it, and the ROBPCA method is better than the PCA method because it has a smaller SPE value. ABSTRAK. Bearing memiliki peranan cukup penting, karena bearing merupakan bagian dari elemen mesin yang apabila memiliki kesehatan cukup baik maka elemen mesin dapat bekerja dengan baik. Pada skripsi ini dilakukan deteksi kerusakan bearing menggunakan metode Principal Component Analysis (PCA) dan metode kembangannya yaitu metode Robust Principal Component Analysis (ROB PCA) dengan menggunakan indeks pemantauan utamanya yaitu Squared Prediction Error (SPE). Tujuan dari penelitian ini adalah untuk membandingkan metode principal component utama (PCA) dan metode Robust Principal Component utama (ROB PCA) pada data vibrasi bearing untuk deteksi kerusakan bearing. Data yang akan digunakan adalah data sekunder dari eksperimen uji bearing yang diperoleh dari Institute of Electrical and Electronic Engineers (IEEE) Prognostics and Health Management (PHM) 2012 melalui penyimpanan data dari FEMTO-ST Institute. Kemudian, untuk pengolahan data digunakan data vibrasi Bearing1_1 arah horizontal yang dilakukan ekstraksi fitur statistik sebanyak 11 fitur. Berdasarkan penelitian yang telah dilakukan, dalam mendeteksi kerusakan metode PCA dan ROBPCA mampu mengatasinya, dan metode ROBPCA lebih baik dibanding metode PCA karena memiliki nilai SPE lebih kecil.

Authors

Publication Details

Journal
Bandung Conference Series Statistics
Published
2025-02-03
DOI
https://doi.org/10.29313/bcss.v5i1.16636
Primary Topic
Machine Fault Diagnosis Techniques
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Deteksi Kerusakan Bearing Menggunakan Metode Robust Principal Component Analysis (ROB PCA)

Sutawanir Darwis, Syahida Usama Firdaus
Bandung Conference Series Statistics
Machine Fault Diagnosis Techniques
article

Deteksi Kerusakan Bearing Menggunakan Metode Robust Principal Component Analysis (ROB PCA)

Sutawanir Darwis, Syahida Usama Firdaus
article en

Abstract

ABSTRACT. Bearings have an important role, because bearings are part of a machine element that if it has good health, the machine element can work properly. In this paper, bearing damage detection was carried out using the Principal Component Analysis (PCA) method and its development method, the Robust Principal Component Analysis (ROB PCA) method using the main monitoring index, namely the Squared Prediction Error (SPE). The purpose of this paper is to compare the main principal component method (PCA) and the main Robust Principal Component method (ROB PCA) on bearing vibration data for bearing damage detection. The data to be used is secondary data from bearing test experiments obtained from the Institute of Electrical and Electronic Engineers (IEEE) Prognostics and Health Management (PHM) 2012 through data storage from the FEMTO-ST Institute. Then, for data processing, Bearing1_1 vibration data in the horizontal direction is used and 11 statistical features are extracted. Based on the research that has been done, in detecting damage the PCA and ROBPCA methods are able to overcome it, and the ROBPCA method is better than the PCA method because it has a smaller SPE value. ABSTRAK. Bearing memiliki peranan cukup penting, karena bearing merupakan bagian dari elemen mesin yang apabila memiliki kesehatan cukup baik maka elemen mesin dapat bekerja dengan baik. Pada skripsi ini dilakukan deteksi kerusakan bearing menggunakan metode Principal Component Analysis (PCA) dan metode kembangannya yaitu metode Robust Principal Component Analysis (ROB PCA) dengan menggunakan indeks pemantauan utamanya yaitu Squared Prediction Error (SPE). Tujuan dari penelitian ini adalah untuk membandingkan metode principal component utama (PCA) dan metode Robust Principal Component utama (ROB PCA) pada data vibrasi bearing untuk deteksi kerusakan bearing. Data yang akan digunakan adalah data sekunder dari eksperimen uji bearing yang diperoleh dari Institute of Electrical and Electronic Engineers (IEEE) Prognostics and Health Management (PHM) 2012 melalui penyimpanan data dari FEMTO-ST Institute. Kemudian, untuk pengolahan data digunakan data vibrasi Bearing1_1 arah horizontal yang dilakukan ekstraksi fitur statistik sebanyak 11 fitur. Berdasarkan penelitian yang telah dilakukan, dalam mendeteksi kerusakan metode PCA dan ROBPCA mampu mengatasinya, dan metode ROBPCA lebih baik dibanding metode PCA karena memiliki nilai SPE lebih kecil.

Bandung Conference Series StatisticsVol. 5(1)
Openalex Percentile: Top 96%
Machine Fault Diagnosis Techniques
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.