Rancang Bangun Aplikasi Intelligent Visual Scanner berbasis CNN untuk Identifikasi Cacat Pada Hasil Pengelasan
DOI:
https://doi.org/10.52435/complete.v4i2.393Keywords:
pengelasan, cacat, CNNAbstract
Pengelasan merupakan salah satu sektor yang berperan penting dalam mendukung pembangunan infrastruktur yang semakin pesat. Namun dalam proses pengelasan banyak muncul kesalahan - kesalahan atau cacat yang terkadang luput dari inspeksi dan menyebabkan kerusakan pada benda kerja. Tujuan diadakannya penitian ini untuk merancang aplikasi Intelligent Visual Scanner dengan menggunakan metode CNN untuk mendeteksi kelayakan hasil pengelasan berdasarkan 3 kondisi, yaitu Normal, Excess Reinforcement, dan Undercut. Daerah yang akan dideteksi merupakan bagian dari hasil pengelasan pada plat besi dengan ketebalan 4mm. Pemotretan dilakukan menggunakan kamera ponsel beresolusi 48 MP. Gambar yang diambil berukuran 3024 x 3024 piksel terlebih dahulu diproses dengan konversi RGB ke grayscale, kemudian gambar tersebut diperkecil (diubah ukurannya) ke skala yang lebih kecil yaitu 128 x 128 piksel untuk mempercepat proses training dan pada akhirnya proses training dan testing menggunakan model CNN. Model CNN ini menggunakan optimizer Adam. Untuk deteksi yang optimal, diperlukan dataset gambar sebanyak 300 gambar, dengan rincian 100 gambar normal, 100 gambar Excess Reinforcement dan 100 gambar Undercut. Data split training saat ini dibagi menjadi 75% data training dan 25% data validasi.
References
H. Pan, Z. Pang, Y. Wang, Y. Wang, and L. Chen, “A New Image Recognition and Classification Method Combining Transfer Learning Algorithm and MobileNet Model for Welding Defects,” IEEE Access, vol. 8, pp. 119951–119960, 2020, doi: 10.1109/ACCESS.2020.3005450.
A. Rizal Lucky Pradana, S. Khumaidi, M. T. St, R. Andiana, and S. St, “Identifikasi Penyebab Cacat Pada Hasil Pengelasan Dengan Image Processing Menggunakan Metode YOLO”, [Online]. Available: https://journal.trunojoyo.ac.id/triac
F. Kurniadi, F. Handoko, T. Priyasmanu, and P. Studi Teknik Industri S-, “ANALISIS WELDING DEFECT"RATE DAN PENANGANANNYA DENGAN"METODE"SIX SIGMA"DAN FMEA (STUDI KASUS: PT. MEINDO ELANG INDAH, MUARA JAWA, KUTAI KARTANEGARA, KALTIM),” Jurnal Mahasiswa Teknik Industri), vol. 5, no. 1, 2022.
N. V. R. Maganti and R. R. Potturi, “Investigation on Mechanical and Machinability Properties of Aluminium Metal Matrix Composite Reinforced with Titanium Oxide (TiO2) and Graphite (Gr) Particles,” Trends in Sciences, vol. 20, no. 11, p. 5682, Aug. 2023, doi: 10.48048/tis.2023.5682.
M. Bin Afan, B. Rahim Jurusan Teknik Mesin, F. Teknik, and U. Negeri Padang Jl Hamka, “Pengaruh Suhu Penyimpanan Elektroda Low Hydrogen E7016 terhadap Hasil Uji Tekuk Sambungan Las Pelat Baja Karbon SS400,” 2020. [Online]. Available: https://jurnal.polines.ac.id/index.php/rekayasa
A. Khatammi and A. W. Rizqi, “Analisis Kecacatan Produk Pada Hasil Pengelasan dengan Metode Failure Mode Effect Analysis,” Serambi Engineering, vol. VII, no. 2, 2022.
A. O. Igbinake, “FUPRE Journal of Scientific and Industrial Research Estimation of Undercuts in Mild Steel Weldment using Artificial Neural Network,” Journal Research Article / Review Article FUPRE JOURNAL, vol. 7, no. 1, pp. 138–147, 2023, [Online]. Available: http://fupre.edu.ng/journal
R. Miao et al., “Real-time defect identification of narrow overlap welds and application based on convolutional neural networks,” J Manuf Syst, vol. 62, pp. 800–810, Jan. 2022, doi: 10.1016/j.jmsy.2021.01.012.
M. Karim Al Amin et al., “Analysis of Optimizer Effects on CNN Model for Defect Identification in Welding Results of A 106 Grade B Carbon Steel Pipe.”, ICEEI 2023.
M. Defriani and I. J. Jaelani, “Recognition of Regional Traditional House in Indonesia Using Convolutional Neural Network (CNN) Method,” Journal of Computer Networks, Architecture and High Performance Computing, vol. 4, no. 2, pp. 104–115, Jul. 2022, doi: 10.47709/cnahpc.v4i2.1562.
P. Adi Nugroho, I. Fenriana, and R. Arijanto, “IMPLEMENTASI DEEP LEARNING MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORK ( CNN ) PADA EKSPRESI MANUSIA,” JURNAL ALGOR, vol. 2, no. 1, 2020, [Online]. Available: https://jurnal.buddhidharma.ac.id/index.php/algor/index
M. D. Pramita, B. Kurniawan, and N. P. Utama, “Mask Wearing Classification using CNN,” in 2020 7th International Conference on Advanced Informatics: Concepts, Theory and Applications, ICAICTA 2020, Institute of Electrical and Electronics Engineers Inc., Sep. 2020. doi: 10.1109/ICAICTA49861.2020.9429029.
A. F. Anavyanto, M. Maimunah, M. R. A. Yudianto, and P. Sukmasetya, “EfficientNetV2M for Image Classification of Tomato Leaf Deseases," PIKSEL Penelitian Ilmu Komputer Sistem Embedded and Logic, vol. 11, no. 1, pp. 55–76, Mar. 2023, doi: 10.33558/piksel.v11i1.5925.
G. Xie, A. Shangguan, R. Fei, W. Ji, W. Ma, and X. Hei, “Motion trajectory prediction based on a CNN-LSTM sequential model,” Science China Information Sciences, vol. 63, no. 11, Nov. 2020, doi: 10.1007/s11432-019-2761-y.
IEEE Communications Society. Indonesia Chapter., Universitas Telkom., and Institute of Electrical and Electronics Engineers, Proceedings, the 2020 IEEE International Conference on Industry 4.0, Artificial Intelligence, and Communications Technology, July 7-8, 2020, Bali, Indonesia.
T. Purwaningsih, T. Nurhikmat, and P. B. Utami, “Image Classification of Golek Puppet Images using Convolutional Neural Networks Algorithm,” Int. J. Advance Soft Compu. Appl, vol. 11, no. 1, 2019.
STMIK AKAKOM Yogyakarta, Institute of Electrical and Electronics Engineers. Indonesia Section, and Institute of Electrical and Electronics Engineers, 2nd ISRITI 2019 proceeding, the 2nd International Seminar on Research of Information Technology and Intelligent Systems 2019, “The future & challenges of extended intelligence”, Yogyakarta, Indonesia, 05-06 December 2019.
S. Bhattacharyya, RCC Institute of Information Technology. Department of Information Technology, and Institute of Electrical and Electronics Engineers, Proceedings, 2018 Fourth IEEE International Conference on Research in Computational Intelligence and Communication Networks (ICRCICN), 22nd and 23rd November, 2018, Kolkata, India.
S. Kanungo, “ANALYSIS OF IMAGE CLASSIFICATION DEEP LEARNING ALGORITHM.”
M. H. Saleem, J. Potgieter, and K. M. Arif, “Plant disease classification: A comparative evaluation of convolutional neural networks and deep learning optimizers,” Plants, vol. 9, no. 10, pp. 1–17, Oct. 2020, doi: 10.3390/plants9101319.
Downloads
Published
Issue
Section
License
Copyright (c) 2023 Ryan yudha Adhitya; Mochammad Karim Al Amin , Mohammad Miftachul Munir , Mohammad Thoriq Wahyudi, Dika Anggara , Eka Cahya Septian , Eka Cahya Septian , Muhammad Ainul Yaqin , Muhammad Ilham Safrudin
This work is licensed under a Creative Commons Attribution 4.0 International License.
