Sabar Sabar
Program Studi Rekayasa Instrumentasi dan Automasi, Fakultas Teknologi Industri, Institut Teknologi Sumatera, 35365, Lampung, Indonesia

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

Sistem Deteksi Cacat Pada Biji Kopi Melalui Model Algoritma Roboflow- Detection Transformer (RF-DTER) Sabar Sabar; Nazuwatussya’diyah Nazuwatussya’diyah; Kisna Pertiwi; Muhamad Fathurahman
Jurnal Otomasi Kontrol dan Instrumentasi Vol 18 No 1 (2026): Jurnal Otomasi Kontrol dan Instrumentasi
Publisher : Pusat Teknologi Instrumentasi dan Otomasi (PTIO) - Institut Teknologi Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5614/joki.2026.18.1.3

Abstract

Coffee bean quality control is a critical stage in processing industries to meet export and consumption standards. Traditional visual manual inspection often results in inconsistency, subjectivity, and reduced production throughput. This research implements the Roboflow Detection Transformer (RF-DETR), an end-to-end transformer-based object detection architecture, to identify subtle and complex coffee bean defects. The study uses image processing and machine learning with a labeled dataset of 2,010 coffee bean images classified into five defect categories: brown, black, unripe, broken black, and partially black. The data are split into 75% training, 17% validation, and 8% testing. Performance evaluation shows RF-DETR detects and classifies all defect types effectively, achieving a mean Average Precision (mAP) of 97,6%, with 95,7% precision, 91,0% recall, and an F1 score of 93,29%. These results indicate that RF-DETR balances accurate spatial localization with reliable class prediction, minimizes false positives, and maintains strong detection sensitivity. Therefore, RF-DETR provides a solid technological basis for high-precision, real-time automated coffee bean sorting in industrial settings. For deployment, it can be integrated with production cameras and conveyor sorting actuators to deliver fast, consistent decisions. Future work may optimize augmentation, lighting calibration, and edge computing deployment to improve robustness across varied production lines in practice.
Pemodelan Prediktif Berbasis Aspen HYSYS untuk Estimasi Kandungan Rhodinol pada Proses Distilasi Fraksinasi Vakum Minyak Sereh Wangi Skala Pilot: Evaluasi Kesesuaian terhadap Data Eksperimen Fadli Hastito; Yusuf Affandi; Sabar Sabar; Achmad Chalid Afif Alfajrin; Rhahmi Adni Pesma; Mardhiyatna Mardhiyatna; Rizki Yustisia Sari; Gelard Unthirta Pratama; Frida Yassar Maula
Jurnal Otomasi Kontrol dan Instrumentasi Vol 18 No 2 (2026): Jurnal Otomasi Kontrol dan Instrumentasi
Publisher : Pusat Teknologi Instrumentasi dan Otomasi (PTIO) - Institut Teknologi Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5614/joki.2026.18.2.6

Abstract

Citronella oil is an essential oil widely used in the perfume, cosmetic, pharmaceutical, and natural-product industries owing to its high-value rhodinol content (citronellol and geraniol). This study aims to develop and evaluate a vacuum fractional distillation process model based on Aspen HYSYS software to predictive the relative rhodinol content of citronella oil and evaluate its agreement with the actual pilot-scale process. Feedstock characterization used GCMS and physicochemical testing. Modeling was performed by varying vacuum pressure, reboiler temperature, and reflux ratio to determine operating conditions tested on a pilot-scale vacuum fractional distillation unit through three experiments, comparing the relative rhodinol content from the model and experiments based on percentage error. Results show the third experiment produced the highest relative rhodinol content of 66.51% at 26 mbar, a reboiler temperature of 134°C, and a reflux ratio of 6:1, with prediction error ranging from 25.01% to 42.80% and the lowest error in the third experiment. These findings indicate the Aspen HYSYS model provides a predictive trend supporting the design of operating conditions but still shows deviation from actual pilot-scale conditions, indicating the need to refine model parameters, operating conditions, and process assumptions to improve model reliability for larger-scale process development.