Muhammad Raffy Akbarsyah, . (2025) PENGEMBANGAN SISTEM INSPECTION-BOX BERBASIS YOLOV8 UNTUK DETEKSI DINI PADA MAKROSTRUKTUR PRODUK PENGELASAN WAAM. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (178kB) |
|
Text
AWAL.pdf Download (951kB) |
|
Text
BAB 1.pdf Restricted to Repository UPNVJ Only Download (251kB) |
|
Text
BAB 2.pdf Restricted to Repository UPNVJ Only Download (763kB) |
|
Text
BAB 3.pdf Restricted to Repository UPNVJ Only Download (967kB) |
|
Text
BAB 4.pdf Restricted to Repository UPNVJ Only Download (738kB) |
|
Text
BAB 5.pdf Download (224kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (303kB) |
|
Text
RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (134kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (584kB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (15MB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (692kB) |
Abstract
Wire Arc Additive Manufacturing (WAAM) is an additive manufacturing technology that forms metal components layer by layer but is prone to defects such as porosity, cracks, and spatters. Visual inspection of WAAM is typically conducted manually, which has drawbacks such as inconsistency and lack of objectivity due to human error. This study aims to develop an automated system to detect surface defects in WAAM. The system is designed with consistent LED strip lighting, a Flask-based graphical user interface (GUI), and a YOLOv8 algorithm trained on 5,187 images over 150 epochs using the AdamW optimizer and a learning rate of 0,0001. The developed YOLOv8 model achieved a mean Average Precision (mAP) of 50-95 of 77% and an F1-Score of 88%. Experiments were conducted on WAAM specimens with and without an inspection box, resulting in a 20% improvement in F1-Score and a 8% increase in mAP 50-95 when using the inspection box. These results demonstrate that the inspection box significantly enhances the model's detection performance.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No.Panggil: 2010311046] [Pembimbing: Armansyah] [Penguji 1: Sigit Pradana] [Penguji 2: Muhammad Arifudin Lukmana] |
| Uncontrolled Keywords: | YOLOv8, Inspection-Box, Wire Arc Additive Manufacturing (WAAM), macrostructural defects, porosity, cracks, spatter. |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science T Technology > T Technology (General) T Technology > TJ Mechanical engineering and machinery |
| Divisions: | Fakultas Teknik > Program Studi Teknik Mesin (S1) |
| Depositing User: | MUHAMMAD RAFFY AKBARSYAH |
| Date Deposited: | 07 Feb 2025 09:12 |
| Last Modified: | 07 Feb 2025 09:12 |
| URI: | http://repository.upnvj.ac.id/id/eprint/36025 |
Actions (login required)
 |
View Item |