ANALISIS PERBANDINGAN PADA DETEKSI GORESAN PERMUKAAN LOGAM BAJA DARI PROSES PICKLING DAN CARBON NANOTUBE BERBASIS DEEP LEARNING

Sandy Fauzan Prasaja, Andi Sunyoto

Abstract


Di zaman era Teknologi Industri 4.0 ini, Perusahaan industri manufaktur baja harus mengkuti trend teknologi yang bisa meminimalisir pengeluaran produksi yang berlebih. Untuk itu dengan mengikuti teknologi yang terbaru ini yaitu Artificial Intelligence (AI) dapat membantu peningkatan produksi yang maksimal. Dengan metode deteksi baja lempengan yang sudah di proses dari pickling atau proses pencucian dari baja berkarat. Selanjutnya baja siap untuk di proses ke tahapan berikutnya, detector baja ini dapat membantu inspector quality memberikan analisa proses dari pickling sudah bisa di lanjutkan ke proses tahapan produksi berikutnya. Disini penulis akan melakukan penelitian Deep Learning dengan metode berbasis Convolutional Neural Network (CNN) dan You Only Look Once (YOLO) yang sudah banyak digunakan dalam analisa citra, karena memiliki kemampuan pengenalan citra yang sangat baik. Dataset dibagi menjadi 2 direktori yaitu data training dan data validasi. Hasil pengujian model CNN dan YOLOv8 dengan epoch 30 dan batch size 120 mendapatkan hasil terabit yaitu YOLOv8 dengan nilai akurasi 91.05% precision 82,62%, recall 81,80%, dan f1-score 82,19%. Penelitian ini memberikan kontribusi pada pengembangan sistem deteksi goresan baja yang lebih efektif menggunakan pendekatan Deep Learning, dengan hasil evaluasi yang akurat.

Keywords


Industri 4.0, Artificial Intelligence, CNN, YOLOv8, Deep Learning

Full Text:

PDF

References


H. S. Lee and P. Park, “Implementation of Control Structure for Steel Pickling Process using Model Predictive Controller,” IFAC-PapersOnLine, vol. 55, no. 7, pp. 679–684, 2022, doi: 10.1016/j.ifacol.2022.07.522.

A. Anderez, F. J. Alguacil, and F. A. López, “Acid pickling of carbon steel,” Rev. Metal., vol. 58, no. 3, 2022, doi: 10.3989/revmetalm.226.

M. Aci and M. Avci, “Artificial neural network approach for atomic coordinate prediction of carbon nanotubes,” Appl. Phys. A Mater. Sci. Process., vol. 122, no. 7, 2016, doi: 10.1007/s00339-016-0153-1.

S. Yamacli and M. Avci, “Simple and accurate model for voltage-dependent resistance of metallic carbon nanotube interconnects: An ab initio study,” Phys. Lett. Sect. A Gen. At. Solid State Phys., vol. 374, no. 2, pp. 297–304, 2009, doi: 10.1016/j.physleta.2009.10.043.

G. G. Wildgoose, C. E. Banks, and R. G. Compton, “Metal nanoparticles and related materials supported on Carbon nanotubes: Methods and applications,” Small, vol. 2, no. 2, pp. 182–193, 2006, doi: 10.1002/smll.200500324.

S. Li, C. Wu, and N. Xiong, “Hybrid Architecture Based on CNN and Transformer for Strip Steel Surface Defect Classification,” Electron., vol. 11, no. 8, pp. 1–14, 2022, doi: 10.3390/electronics11081200.

T. Agustin and A. Sunyoto, “Optimization Convolutional Neural Network for Classification Diabetic Retinopathy Severity,” 2020 3rd Int. Conf. Inf. Commun. Technol. ICOIACT 2020, pp. 66–71, 2020, doi: 10.1109/ICOIACT50329.2020.9332087.

D. Soukup, C. Kapeller, B. Raml, and J. Ruisz, “Industry-Fit AI Usage for Crack Detection in Ground Steel,” Electron., vol. 11, no. 17, pp. 1–13, 2022, doi: 10.3390/electronics11172643.

H. Zhang, J. Li, J. Zhang, and Y. Dong, “Speeding up k-means clustering in high dimensions by pruning unnecessary distance computations,” Knowledge-Based Syst., vol. 284, no. August 2023, p. 111262, 2024, doi: 10.1016/j.knosys.2023.111262.

C. H. Bock, J. G. A. Barbedo, E. M. Del Ponte, D. Bohnenkamp, and A.-K. Mahlein, “From visual estimates to fully automated sensor-based measurements of plant disease severity: status and challenges for improving accuracy,” Phytopathol. Res., vol. 2, no. 1, 2020, doi: 10.1186/s42483-020-00049-8.

Z. Cai and N. Vasconcelos, “Cascade R-CNN: Delving into High Quality Object Detection,” in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2018, pp. 6154–6162. doi: 10.1109/CVPR.2018.00644.

S. Qiao, L. Chen, and A. Yuille, “DetectoRS : Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution,” pp. 10213–10224.

G. Plastiras, C. Kyrkou, and T. Theocharides, “Efficient convnet-based object detection for unmanned aerial vehicles by selective tile processing,” ACM Int. Conf. Proceeding Ser., 2018, doi: 10.1145/3243394.3243692.

R. Dwiyanto, D. W. Widodo, and P. Kasih, “Implementasi Metode You Only Look Once ( YOLOv5 ) Untuk Klasifikasi Kendaraan Pada CCTV Kabupaten Tulungagung,” Semin. Nas. Inov. Teknol., vol. 1, no. 1, pp. 102–104, 2022.

X. Zhai, A. Kolesnikov, N. Houlsby, and L. Beyer, “Scaling Vision Transformers,” Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., vol. 2022-June, pp. 12094–12103, 2022, doi: 10.1109/CVPR52688.2022.01179.

J. Cordonnier, A. Loukas, and M. Jaggi, “THE R ELATIONSHIP BETWEEN,” 2020.

Severstal: Steel Defect Detection, “No Title,” Alexey Grishin, BorisV, iBardintsev, inversion, Oleg. [Online]. Available: https://kaggle.com/competitions/severstal-steel-defect-detection




DOI: https://doi.org/10.29100/jipi.v11i2.7779

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika)
ISSN 2540-8984
Published by
Prodi Pendidikan Teknologi Informasi
Universitas Bhinneka PGRI

Website :https://jurnal.stkippgritulungagung.ac.id/index.php/jipi/index
Email: jipistkippti@gmail.com

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.