Azarya Raffael Siburian, . (2025) ANALISIS PREDICTIVE MAINTENANCE DENGAN UNSUPERVISED LEARNING DAN ANOVA PADA VIBRASI SOLAR CENTAUR 50 GAS TURBINE DI PT. XYZ. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (572kB) |
|
Text
AWAL.pdf Download (2MB) |
|
Text
BAB 1.pdf Restricted to Repository UPNVJ Only Download (571kB) |
|
Text
BAB 2.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
Text
BAB 3.pdf Restricted to Repository UPNVJ Only Download (593kB) |
|
Text
BAB 4.pdf Restricted to Repository UPNVJ Only Download (3MB) |
|
Text
BAB 5.pdf Download (500kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (586kB) |
|
Text
RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (227kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (3MB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (12MB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (1MB) |
Abstract
Rotating machinery, such as gas turbines, play an important role in various industries, so predictive maintenance is crucial to prevent unexpected downtime. This study aims to analyze predictive maintenance with unsupervised learning and ANOVA approaches on engine vibration data. Vibration data is analyzed using K-Means Clustering to cluster machine operational patterns, while ANOVA is used for feature selection to filter out significant variables. The analysis results show that the Isolation Forest algorithm successfully distinguishes normal and anomaly operational conditions with an accuracy rate of 93.07%. This study proves that the unsupervised learning approach can provide insight into engine conditions based on vibration clusters as well as anomaly detection, help the isolation forest algorithm model identify gas turbine operational conditions based on vibrations, ANOVA provides an understanding of what features contribute to the anomaly findings, be a good data reduction method for the XGBoost prediction model and help for preventive and conditional-based maintenance needs.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | No. Panggil:1910311078 Pembimbing:Sigit Pradana Penguji 1:Sugeng Prayitno Penguji 2:Fitri Wahyuni |
| Uncontrolled Keywords: | Predictive Maintenance, Unsupervised Learning, Vibration Rotating Machinery |
| Subjects: | T Technology > TJ Mechanical engineering and machinery |
| Divisions: | Fakultas Teknik > Program Studi Teknik Mesin (S1) |
| Depositing User: | AZARYA RAFFAEL SIBURIAN |
| Date Deposited: | 26 Feb 2025 07:39 |
| Last Modified: | 26 Feb 2025 07:43 |
| URI: | http://repository.upnvj.ac.id/id/eprint/36278 |
Actions (login required)
 |
View Item |