Cadrasva Ardhevan Novitza, . (2025) PENGEMBANGAN SISTEM DETEKSI DINI PANAS REAKTOR NUKLIR MENGGUNAKAN MACHINE LEARNING. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (142kB) |
|
Text
AWAL.pdf Download (301kB) |
|
Text
BAB I.pdf Restricted to Repository UPNVJ Only Download (114kB) |
|
Text
BAB II.pdf Restricted to Repository UPNVJ Only Download (200kB) |
|
Text
BAB III.pdf Restricted to Repository UPNVJ Only Download (158kB) |
|
Text
BAB IV.pdf Restricted to Repository UPNVJ Only Download (353kB) |
|
Text
BAB V.pdf Download (89kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (188kB) |
|
Text
RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (91kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (29kB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (957kB) |
|
Text
ARTIKEL.pdf Restricted to Repository staff only Download (368kB) |
Abstract
This study aims to develop an early temperature anomaly detection system for nuclear reactors using a machine learning approach based on the Random Forest Regressor. By leveraging simulated temperature data from a hypothetical nuclear reactor cooling system, the model was designed to autonomously detect anomalies without human supervision. The data processing involved cleaning, feature engineering, and training the model using historical coolant temperature patterns. To evaluate model performance, a synthetic dataset with manually inserted anomalies and labelled ground truth was used. Evaluation utilized a Confusion Matrix and metrics such as accuracy, precision, recall, and F1-score. Results showed that while the model achieved high accuracy in detecting normal conditions, its sensitivity to anomalies was still limited. Visual analysis of prediction graphs confirmed the successful detection of most extreme anomalies. This research demonstrates that the Random Forest approach can serve as a foundational method for adaptive reactor temperature monitoring systems. However, further development is needed to improve anomaly sensitivity and model generalization capabilities.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No.Panggil: 2110511160] [Pembimbing 1:Didit Widiyanto] [Pembimbing 2: Kharisma Wiati Gusti] [Penguji 1: Musthofa Galih Pradana] [Penguji 2: I Wayan Rangga Pinastawa] |
| Uncontrolled Keywords: | Nuclear Reactor, Anomaly Detection, Random Forest, Machine Learning, Temperature Prediction |
| Subjects: | Q Science > QC Physics T Technology > TK Electrical engineering. Electronics Nuclear engineering |
| Divisions: | Fakultas Ilmu Komputer > Program Studi Informatika (S1) |
| Depositing User: | CADRASVA ARDHEVAN NOVITZA |
| Date Deposited: | 05 Aug 2025 06:52 |
| Last Modified: | 05 Aug 2025 06:52 |
| URI: | http://repository.upnvj.ac.id/id/eprint/37233 |
Actions (login required)
 |
View Item |