PERANCANGAN SISTEM CONFORMAL COATING INSPECTION CIRCUIT BOARD MENGGUNAKAN METODE JARINGAN SARAF TIRUAN BERBASIS MATLAB

RAMLI, ADHI (2020) PERANCANGAN SISTEM CONFORMAL COATING INSPECTION CIRCUIT BOARD MENGGUNAKAN METODE JARINGAN SARAF TIRUAN BERBASIS MATLAB. S1 thesis, Universitas Mercu Buana Bekasi.

[img]
Preview
Text
1 Halaman Judul.pdf

Download (104kB) | Preview
[img]
Preview
Text
2 Abstrak.pdf

Download (106kB) | Preview
[img]
Preview
Text
3 Surat Pernyataan.pdf

Download (132kB) | Preview
[img]
Preview
Text
4 Lembar Pengesahan.pdf

Download (143kB) | Preview
[img]
Preview
Text
5 Kata Pengantar.pdf

Download (143kB) | Preview
[img]
Preview
Text
6 Daftar Isi.pdf

Download (196kB) | Preview
[img]
Preview
Text
7 Daftar Gambar.pdf

Download (114kB) | Preview
[img]
Preview
Text
8 Daftar Tabel.pdf

Download (111kB) | Preview
[img] Text
9 BAB 1.pdf
Restricted to Registered users only

Download (181kB)
[img] Text
10 BAB 2.pdf
Restricted to Registered users only

Download (566kB)
[img] Text
11 BAB 3.pdf
Restricted to Registered users only

Download (419kB)
[img] Text
12 BAB 4.pdf
Restricted to Registered users only

Download (1MB)
[img] Text
13 BAB 5.pdf
Restricted to Registered users only

Download (114kB)
[img] Text
14 Daftar Pustaka.pdf
Restricted to Registered users only

Download (270kB)
[img] Text
15 Lampiran.pdf
Restricted to Registered users only

Download (260kB)

Abstract

ABSTRAK Masalah Human-Error pada process manual inspection seperti pada proses conformal coating circuit board menjadi hal yang harus diperhatikan mengingat sangat pentingnya fungsi dari conformal coating untuk melindungi circuit board dari oksidasi dan pengaruh lingkungan. Sehingga diperlukan suatu sistem inspection yang bisa menggantikan peran manusia dalam pengecekannya sehingga dapat menghilangkan masalah human-error. Salah satunya adalah dengan memanfaatkan computer vision yaitu cabang ilmu yang mempelajari tentang bagaimana suatu sistem dapat mengenali suatu objek dengan kombinasi antara pengolahan citra dan pengenalan pola. Untuk memastikan level inspection system tersebut sama dengan yang dilakukan manusia bisa menggunakan Jaringan syaraf Tiruan untuk proses pengambilan keputusan. Berdasarkan hal tersebut, pada penelitian ini dibuat suatu prototype conformal coating inspection menggunakan Matlab yaitu suatu sistem inspection berbasis kamera webcam yang berfungsi untuk meng-capture citra dari kamera untuk diolah dan kemudian sistem akan menganalisa objek tersebut menggunakan metode Jaringan Syaraf Tiruan sehingga sistem bisa mengenali pola conformal coating. Pada penelitian ini juga penulis mencoba mengolah data input untuk JST dengan metode PCA (Principal Component Analysis) guna menghasilkan output yang lebih baik. Proses percobaan pada sistem ini dengan memberikan variasi pada komponen JST yaitu pada epoch, learning rate dan hidden layer sehingga bisa dilihat hubungannya terhadap nilai RMSE, processing time dan recognition rate. Berdasarkan hasil perancangan, implementasi dan pengujian yang dilakukan, maka dapat ditarik kesimpulan bahwa JST dengan PCA lebih baik karena tingkat akurasi 100%. Pada tahap learning process pun sistem menghasilkan nilai RMSE terendah yaitu 4 x 10-7 , recognition rate 100% dengan presentase 88.88%, dan processing time tercepat 696.4910 detik. Kata kunci : Human Error, Conformal Coating, Inspection System, Matlab, Computer Vision, Jaringan Syaraf Tiruan. Principal Component Analysis. ABSTRACT The human-error problem in the manual inspection process as in the conformal coatings circuit board process become must be considered due to this process is very importance to protect circuit board from oxidation and environmental influences .So that required a system inspection can replace the human in inspection process so we can eliminate human-error problems .One example is use computer vision that is the branch of science that studies about how a system can recognize an object by a combination of imagery and processing of recognition pattern .To ensure the level of inspection system the same to those performed by human we can use artificial neural network to the decision-making process . Based on that case, this research is made a prototype conformal coatings inspection using MATLAB even a webcam based camera inspection system that serves to capture image from the camera to process and then systems will be analyze the object was use of artificial neural network, so the system can recognize patterns conformal coatings .In this research also author trying to process data input with Principal Component Analysis to improve output from the system. Process experiment in this system by giving variation to ANN components on epoch, learning rate and hidden layers as can be seen to do on the RMSE, processing time and recognition rate.Based on the design, implementation and tests carried out, so conclusions may be drawn that ANN with PCA is better because the result is 100 % accuracy. On the learning process step the result of RMSE is 4x10-7, recognition rate 100 % with the percentage 88.88% & processing time is 696.4910 second. Keyword: Human Error, Conformal Coating, Inspection System, Matlab, Computer Vision, Artifical Neuron Network, Principal Component Analysis.

Item Type: Thesis (S1)
Call Number CD: FE/ELK 20 039
NIM/NIDN Creators: 41418320042
Uncontrolled Keywords: Kata kunci : Human Error, Conformal Coating, Inspection System, Matlab, Computer Vision, Jaringan Syaraf Tiruan. Principal Component Analysis.
Subjects: 600 Technology/Teknologi > 620 Engineering and Applied Operations/Ilmu Teknik dan operasi Terapan > 621 Applied Physics/Fisika terapan > 621.3 Electrical Engineering, Lighting, Superconductivity, Magnetic Engineering, Applied Optics, Paraphotic Technology, Electronics Communications Engineering, Computers/Teknik Elektro, Pencahayaan, Superkonduktivitas, Teknik Magnetik, Optik Terapan, Tekn
Divisions: Fakultas Teknik > Teknik Elektro
Depositing User: siti maisyaroh
Date Deposited: 16 Jun 2022 02:11
Last Modified: 16 Jun 2022 02:11
URI: http://repository.mercubuana.ac.id/id/eprint/63440

Actions (login required)

View Item View Item