Journal of the Korea Society of Computer and Information (한국컴퓨터정보학회논문지)

Korean Society of Computer Information (한국컴퓨터정보학회)
권호 표지
DOI QR코드

DOI QR Code

The Method for Classifying Stainless Steel Grades in Products Using Portable NIR Spectrometer and CNN

  • Ju-Hoon Jang (Dept. of Computer Science, Kangnam University) ;
  • In-Yeop Choi (Dept. of Computer Science, Kangnam University)
  • Received : 2024.08.20
  • Accepted : 2024.09.25
  • Published : 2024.10.31
Download PDF
⟨ Previous Next ⟩

Abstract

This paper proposes a method for classifying the grade of stainless steel using a portable NIR(Near Infrared Ray) spectrometer and a CNN(Convolutional Neural Network) deep learning model. Traditionally, methods for classifying stainless steel grades have included chemical analysis, magnetic testing, molybdenum spot tests, and portable XRF devices. In addition, a classification method using a machine learning model with element concentration and heat treatment temperature as parameters was presented in the paper. However, these methods are limited in their application to everyday products, such as kitchenware and cookware, due to the need for reagents, specialized equipment, or reliance on professional services. To address these limitations, this paper proposes a simple method for classifying the grade of stainless steel using a NIR spectrometer and a CNN model. If the method presented in this paper is installed on a portable device as an on-device in the future, it will be possible to determine the grade of stainless steel used in the product, and to determine on-site whether a product made of low-cost material has been disguised as a high-cost product.

본 논문에서는 휴대용 NIR(Near Infrared Ray) 분광계와 CNN(Convolution Neural Network) 딥러닝 모델을 이용하여 스테인리스강(Stainless steel) 등급을 판별하는 방법을 제시한다. 기존에 스테인리스강 등급을 판별하는 방법은 화학분석 방법, 자기 테스트, 몰리브덴 스팟과 휴대용 XRF 장치를 이용한 분류 방법을 사용하였다. 또한 원소의 농도와 열처리 가열온도를 매개변수로하여 기계학습(Machine Learning) 모델을 이용한 분류 방법이 논문에서 제시되기도 했다. 하지만 이러한 방법들은 주방용품 및 조리도구 같은 실생활에서 사용되는 제품에 사용된 스테인리스강 등급을 판별하는데 사용하기에는 한계가 있다. 왜냐하면 이러한 방법들은 제품에 시약을 바르거나, 특수 장비가 필요하거나, 전문 지식이 필요하여 전문 업체에 의뢰해야 하기 때문이다. 이러한 한계점을 본 논문에서는 근적외선 분광계와 CNN 모델을 이용하여, 간편하게 제품의 스테인리스강 등급을 판별하는 방법을 제시한다. 본 논문에서 제시한 방법을 이용하여 추후 휴대용 기기에 On-Device로 탑재하면, 제품에 사용된 스테인리스강 등급을 판별하여 저가 재질로 만들어진 제품이 고가로 둔갑된 것을 현장에서 판별 할수 있다.

Keywords

References

  1. Stainless Steel Grades , https://continentalsteel.com/stainless-steel/grades/
  2. STEALDAILY 20, https://www.steeldaily.co.kr/news/articleView.html?idxno=12727
  3. Prime Economy, https://www.newsprime.co.kr/news/article/?no=575991
  4. 304 and 316 Stainless Steel? Know the difference between Stainless Steel Grades and use them, https://nosearch.com/contents/encyclopedia/child_care/milk_powder_port/460
  5. S. J. Park, C. G. Jung, "Reagent and Method for Identifying 200 Series Stainless Steel," https://patents.google.com/patent/KR100822752B1/ko, Korean Intellectual Property Office , KR100822752B1, Apr 2008.
  6. A. S. Fedorov, A. I. Zhitenev, D. A. Strekalovskaya, A. A. Kur and A. A. Alkhimenko, "Quantitative Description of Duplex Stainless Steels Microstructure Using Selective Etching," Metals, Vol. 11, No. 1750, Oct 2021, https://doi.org/10.3390/met11111750
  7. S. Heydarov, M. Aydin, C. Faydaci, S. Tuna and S. Ozturk, "Low-cost VIS/NIR range hand-held and portable photospectrometer and evaluation of machine learning algorithms for classification performance," Engineering Science and Technology an International Journal, Vol. 37, Jan 2023. https://doi.org/10.1016/j.jestch.2022.101302
  8. TESTING FOR GRADE CONFIRMATION, Australian Stainless Steel Development Assoc (ASSDA), https://www.researchgate.net/file.PostFileLoader.html?id=55570a776143254c3a8b4581&assetKey=AS%3A273777844260884%401442285132883.
  9. Testing for grade confirmation, https://www.assda.asn.au/blog/99-testing-for-grade-confirmation
  10. S. R. An, "In-situ Dry-cleaning Process Diagnosis for Plasma Enhanced Chemical Vapor Deposition Chamber," Myongji University Graduate School, Aug 2023.
  11. A. G. Revenko and G. V. Pashkova, "X-Ray Fluorescence Spectrometry: Current Status and Prospects of Development, " Journal of Analytical Chemistry, Vol. 78, pp. 1452-1468, Nov 2023.
  12. H. J. Kim, Y. M. Baek, G. H. Jeong, S. Y. Hong, H. J. Heo, J. W. Seong and J. C. Park, "Measurement of Heavy Metals Using Portable XRF in Children's Playing Goods," Korean Society of Environmental Sciences, Vol. 22, No. 4, pp. 471-479, Apr 2013.
  13. S. J. Ryu and K. R. Jung, "A Study on the Application of Metal-Based Forensic Evidence Using the Portable X-ray Fluorescence Spectrometer(PXRF)," Police Studies, Vol. 18, No. 32, pp. 190-206, Sept 2018.
  14. P. Korotaev and A. Yanilkin, "Steels classification by machine learning and Calphad methods," Engineering Science and Technology an International Journal, Vol. 82, Sept 2023. https://doi.org/10.1016/j.calphad.2023.102587
  15. H. G. Ahn and Y. H. Kim, "Discrimination of Korean Domestic and Foreign Soybeans using Near Infrared Reflectance Spectroscopy," Korean Journal Crop Sciences, Vol. 57, No. 3, pp. 296-300, Sept 2012.
  16. H. I. Jeong and H. J. Kim, "[Commentary] Principles of Near-Infrared Spectroscopy," Korean Society for Analytical Sciences, Vol. 13, No. 1, pp. 138-151, Feb 2000.
  17. LinkSquare NIR, https://linksquare.io/
  18. Keras, https://keras.io/