AHMAD MUZAKKY, . (2025) INTEGRASI KAMERA INDUSTRI DAN KONTROL MESIN BLISTER DALAM DETEKSI PRODUK SUNTIK PT X. Diploma thesis, TEKNOLOGI REKAYASA OTOMASI.
![[img]](http://repository.unj.ac.id/style/images/fileicons/text.png) |
Text
Cover.pdf Download (2MB) |
|
Text
BAB 1.pdf Download (267kB) |
|
Text
BAB 2.pdf Restricted to Registered users only Download (2MB) |
|
Text
BAB 3.pdf Restricted to Registered users only Download (2MB) |
|
Text
BAB 4.pdf Restricted to Registered users only Download (2MB) |
|
Text
BAB 5.pdf Restricted to Registered users only Download (252kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (587kB) |
|
Text
LAMPIRAN.pdf Restricted to Registered users only Download (2MB) |
Abstract
Industri manufaktur, khususnya di bidang farmasi, memerlukan sistem inspeksi visual otomatis untuk menjamin kualitas produk secara konsisten dan efisien. Penelitian ini merancang dan mengimplementasikan sistem inspeksi visual menggunakan sensor kamera Keyence IV3-G600CA yang terintegrasi dengan modul amplifier IV3-G120, PLC Mitsubishi FX3U, serta HMI sebagai tampilan monitoring. Sistem ini memanfaatkan metode machine learning berbasis supervised learning dengan pendekatan nearest neighbor classification untuk membedakan kondisi poket blister (OK atau NG) berdasarkan master image. Tiga tools utama yang digunakan dalam pengujian adalah Outline, Blob Count, dan Color Prohibit dengan pengaturan parameter threshold dan ROI melalui IV3 Navigator. Pengujian dilakukan sebanyak 100 siklus produksi dengan total 2400 syringe dalam 100 poket blister, menghasilkan akurasi sistem sebesar 92% dengan performa terbaik ditunjukkan oleh tools Blob Count. Penerapan pencahayaan backlight terbukti lebih efektif dibandingkan pencahayaan frontal karena menghasilkan kontras dan kontur visual yang lebih stabil. Selain itu, waktu respon sistem rata-rata sebesar 205 ms menunjukkan performa yang sesuai dengan standar industri. Sistem inspeksi visual ini mampu bekerja secara otomatis dan real-time serta terintegrasi penuh dengan sistem mesin blister, sehingga diharapkan dapat meningkatkan efisiensi produksi dan menjamin mutu produk secara berkelanjutan. ***** The manufacturing industry, particularly in the pharmaceutical sector, requires automated visual inspection systems to ensure consistent and efficient product quality. This research designs and implements a visual inspection system using the Keyence IV3-G600CA camera sensor integrated with the IV3-G120 amplifier module, Mitsubishi FX3U PLC, and HMI as the monitoring i nterface. The system employs a supervised machine learning method with a nearest neighbor classification approach to distinguish blister pocket conditions (OK or NG) based on a master image. Three main tools used in the inspection process are Outline, Blob Count, and Color Prohibit, with parameter settings such as threshold and ROI configured via IV3 Navigator. Testing was conducted over 100 production cycles, inspecting a total of 2400 syringes in 100 blister pockets, resulting in an overall system accuracy of 92%, with Blob Count demonstrating the highest performance. The application of backlight illumination proved more effective than frontal lighting, providing better contrast and contour stability. Furthermore, the system's average response time of 205 ms aligns with industrial performance standards. This visual inspection system operates automatically and in real-time, fully integrated with the blister packaging system, and is expected to improve production efficiency and ensure consistent product quality.
| Item Type: | Thesis (Diploma) |
|---|---|
| Additional Information: | 1). Ir. Heri Firmansyah, S.T., M.T. |
| Subjects: | Teknologi dan Ilmu Terapan > Konstruksi Bangunan Teknologi dan Ilmu Terapan > Teknik Elektronika Teknologi dan Ilmu Terapan > Teknik Komputer |
| Divisions: | FT > D IV Teknologi Rekayasa Otomasi |
| Depositing User: | Ahmad Muzakky . |
| Date Deposited: | 14 Aug 2025 01:45 |
| Last Modified: | 14 Aug 2025 01:45 |
| URI: | http://repository.unj.ac.id/id/eprint/60816 |
Actions (login required)
 |
View Item |
