Hilmi Fairuz Faturrohman, . (2026) PERANCANGAN OTOMASI INDUSTRI BERBASIS MACHINE LEARNING PADA ALAT SORTIR BUAH KELAPA UNTUK PRODUKSI BIOAVTUR. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (111kB) |
|
Text
AWAL.pdf Download (3MB) |
|
Text
BAB 1.pdf Restricted to Repository UPNVJ Only Download (940kB) |
|
Text
BAB 2.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
Text
BAB 3.pdf Restricted to Repository UPNVJ Only Download (250kB) |
|
Text
BAB 4.pdf Restricted to Repository UPNVJ Only Download (4MB) |
|
Text
BAB 5.pdf Download (104kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (145kB) |
|
Text
RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (131kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (12MB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (39MB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (10MB) |
Abstract
The process of sorting coconuts as raw material for bioavtur in Indonesia is still largely done manually, making it prone to inconsistencies, subjective judgments, and human error, and requiring a relatively large amount of time and labor. This study aims to design a prototype of an automated coconut sorting device based on machine learning to improve the objectivity, consistency, and efficiency of the sorting process. The methods used include collecting a dataset of images of standard and non-standard coconuts, preprocessing, dividing the data into training, validation, and testing sets, and training five Convolutional Neural Network architectures: MobileNetV2, VGG16, VGG19, ResNet50, and Xception. The best model was then integrated with a webcam, an ESP32, a servo motor, and a conveyor system to enable real-time sorting. The research results show that ResNet50 delivers the best performance with a classification accuracy of 95.53%. Real-time testing of the prototype yielded an accuracy of 95.23% with an average sorting time of 1.33 seconds per object. The developed system reduces reliance on human labor, minimizes errors caused by subjective judgment, and improves the speed and consistency of the sorting process. These research results indicate that the application of CNNs and industrial automation has the potential to support the development of coconut sorting systems for the biofuel industry.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No.Panggil: 2210312101] [Pembimbing: Donny Montreano] [Penguji 1: Intan Novita Dewi] [Penguji 2: Amenda Septiala Tarigan] |
| Uncontrolled Keywords: | Convolutional Neural Network, Industrial Automation, Bioavtur |
| Subjects: | Q Science > Q Science (General) Q Science > QA Mathematics Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software T Technology > T Technology (General) T Technology > TS Manufactures |
| Divisions: | Fakultas Teknik > Program Studi Teknik Industri (S1) |
| Depositing User: | HILMI FAIRUZ FATURROHMAN |
| Date Deposited: | 29 Aug 2026 02:59 |
| Last Modified: | 29 Aug 2026 02:59 |
| URI: | http://repository.upnvj.ac.id/id/eprint/52980 |
Actions (login required)
 |
View Item |