Sistem Pengenalan Karat Pada Besi Menggunakan CNN

Risky Ramadhani

doi:10.30736/jti.v11i1.1584

Sistem Pengenalan Karat Pada Besi Menggunakan CNN

Authors

Risky Ramadhani Universitas Nusantara PGRI Kediri

DOI:

https://doi.org/10.30736/jti.v11i1.1584

Keywords:

Sistem Pengenalan Karat, Convolutional Neural Network (CNN), Korosi Besi, Deteksi Citra, Klasifikasi

Abstract

Besi adalah material krusial dalam kehidupan modern, mulai dari konstruksi hingga peralatan dapur, dihargai karena kekuatan dan ketersediaannya. Namun, kelemahan mendasarnya adalah kerentanan terhadap korosi—proses yang dipicu oleh oksigen dan air—yang bisa menyebabkan kerugian besar jika tidak ditangani. Solusi yang diangkat dalam penelitian ini adalah menciptakan sebuah sistem pengenalan karat dini menggunakan Convolutional Neural Network (CNN) dengan arsitektur MobileNetV2, sebuah pendekatan yang menjanjikan akurasi tinggi dalam klasifikasi citra. Sistem ini dilatih menggunakan dataset kecil sebanyak 1279 gambar (terdiri dari 693 besi berkarat dan 586 tidak berkarat), Hasil eksperimen menunjukkan bahwa model mampu mencapai tingkat akurasi yang sangat tinggi, yakni 0.98 untuk kelas "Berkarat" dan 0.97 untuk kelas "Tidak Berkarat". Hasil ini menunjukkan bahwa model yang diusulkan efektif dalam mengenali karat pada besi, sehingga diharapkan dapat membantu dalam perawatan material besi sejak dini

Downloads

Download data is not yet available.

References

[1] D. M. Clatterbuck, D. C. Chrzan, and J. W. Morris, “The ideal strength of iron in tension and shear,” Acta Mater., vol. 51, no. 8, pp. 2271–2283, May 2003, doi: 10.1016/S1359-6454(03)00033-8.

[2] D. M. Clatterbuck, D. C. Chrzan, and J. W. Morris, “THE IDEAL STRENGTH OF IRON,” Nano Microstruct. Des. Adv. Mater. A Commem. Vol. Profr. G. Thomas’ Seventieth Birthd., pp. 173–190, Jan. 2003, doi: 10.1016/B978-008044373-7/50043-7.

[3] M. Ghasempour-Mouziraji, J. Lagarinhos, D. Afonso, and R. Alves de Sousa, “A review study on metal powder materials and processing parameters in Laser Metal Deposition,” Opt. Laser Technol., vol. 170, no. 7, p. 110226, Mar. 2024, doi: 10.1016/j.optlastec.2023.110226.

[4] D. Banerjee and A. Gopalan, “Towards Reliable Alignment: Uncertainty-aware RLHF,” Oct. 2024, Accessed: Jan. 21, 2026. [Online]. Available: http://arxiv.org/abs/2410.23726

[5] T. Soga, “Advances in capillary electrophoresis mass spectrometry for metabolomics,” TrAC - Trends Anal. Chem., vol. 158, Jan. 2023, doi: 10.1016/j.trac.2022.116883.

[6] D. Dowson and A. Neville, “Tribology and corrosion in hip joint replacements: Materials and engineering,” Jt. Replace. Technol., pp. 401–442, Jan. 2014, doi: 10.1533/9780857098474.3.401.

[7] J. G. Speight, “Corrosion,” Subsea Deep. Oil Gas Sci. Technol., pp. 213–256, 2015, doi: 10.1016/B978-1-85617-558-6.00008-8.

[8] M. Wojtkowska et al., “The Influence of Water Quality Change on the Corrosion Process in Galvanized Pipes of Fire Protection Installations,” Sustain. 2022, Vol. 14, vol. 14, no. 13, Jun. 2022, doi: 10.3390/su14137708.

[9] “Mengenal Karakteristik dan Jenis Tanah-Tanah Pertanian di Indonesia - Jejak ... - Haidar Fari Aditya, Fitri Wijayanti - Google Books.” Accessed: Feb. 27, 2026. [Online]. Available: https://books.google.co.id/books?hl=en&lr=&id=smffEAAAQBAJ&oi=fnd&pg=PA1&dq=Jenis+Tanah:+Proses+Pembentukan+hingga+Persebarannya+di+Indonesia&ots=ER11m5ixs0&sig=eLBAmgPJY-jidKxe918luYyYNMg&redir_esc=y&safe=strict#v=onepage&q&f=false

[10] K. L. Guintu et al., “ChecKuko: Non-Invasive Early Detection of Iron Deficiency Nail Symptoms through Image Processing Using Faster R-CNN,” 2022 IEEE Glob. Conf. Artif. Intell. Internet Things, GCAIoT 2022, pp. 82–87, 2022, doi: 10.1109/GCAIoT57150.2022.10019199.

[11] Y. Dong, Y. Pan, D. Wang, and T. Cheng, “Corrosion detection and evaluation for steel wires based on a multi-vision scanning system,” Constr. Build. Mater., vol. 322, p. 125877, Mar. 2022, doi: 10.1016/j.conbuildmat.2021.125877.

[12] R. P. De Figueiredo and S. Bogh, “Vision-Based Corrosion Identification Using Data-Driven Semantic Segmentation Techniques,” IST 2023 - IEEE Int. Conf. Imaging Syst. Tech. Proc., 2023, doi: 10.1109/IST59124.2023.10355698.

[13] “Rust-Iron-Dataset.” Accessed: Mar. 06, 2026. [Online]. Available: https://www.kaggle.com/datasets/benpepperpots/rust-iron-dataset

[14] W. T. Nash, C. J. Powell, T. Drummond, and N. Birbilis, “Automated Corrosion Detection Using Crowd Sourced Training for Deep Learning,” Corrosion, vol. 76, no. 2, pp. 135–141, Aug. 2019, Accessed: Mar. 06, 2026. [Online]. Available: http://arxiv.org/abs/1908.02548

[15] S. S. Aljameel et al., “A Deep Learning Approach to Industrial Corrosion Detection,” Comput. Mater. Contin., vol. 81, no. 2, pp. 2587–2605, Nov. 2024, doi: 10.18280/ijsse.140310.

[16] N. Xin, W. Zhuojun, Z. Yanyong, X. Shanzhi, Z. Zhaoying, and S. Tengcheng, “Research on the Quality Improvement Strategy of Inspection and Testing Institutions Based on AI Vision Systems,” 2025 IEEE 3rd Int. Conf. Control. Electron. Comput. Technol., pp. 1552–1556, Apr. 2025, doi: 10.1109/ICCECT64621.2025.11339644.

Downloads

Published

2026-04-04

How to Cite

Ramadhani, R. (2026). Sistem Pengenalan Karat Pada Besi Menggunakan CNN. Joutica, 11(1), 51–56. https://doi.org/10.30736/jti.v11i1.1584

Download Citation

Issue

Vol. 11 No. 1 (2026): MARET

Section

editorial

License

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

Joutica : Journal of Informatic Unisla is licensed under an Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) license. You are free to:

Share copy and redistribute the material in any medium or format
Adapt remix, transform, and build upon the material for any purpose, even commercially. This license is acceptable for Free Cultural Works.

The licensor cannot revoke these freedoms as long as you follow the license terms.

Attribution You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
Share Alike If you remix, transform, or build upon the material, you must distribute your contributions under the same license as the original.
No additional restrictions You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.

Copyright

Authors who publish with this journal agree to the following terms:

Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under an Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).