DOI QR코드

DOI QR Code

Algorithm Improvement Through AI-Based Casting Process Parameter Optimization

AI 기반의 주조 공정 파라미터 최적화를 통한 알고리즘 개선

  • Received : 2023.05.02
  • Accepted : 2023.06.17
  • Published : 2023.06.30

Abstract

The quality of the casting process generates the largest source of defects in the manufacturing process, so its management is a key factor in productivity and quality evaluation. Based on the results of factor analysis, correlation analysis, and regression analysis with process data, this study aims to optimize the machine learning model to reduce the defect rate and verify the data suitability for smart factories.

제조 공정 데이터에 있어 주조 공정은 가장 중요한 공정이면서 높은 불량률의 원인을 발생시키는 공정이다. 주조 공정의 품질관리는 생산성과 품질평가의 핵심 요소라 할 수 있다. 본 연구에서는 공정 데이터를 통한 요인 분석, 상관 분석, 회귀 분석 결과를 기반으로 최적화 된 머신러닝 모델 알고리즘을 개발한다. 이를 적용한 주조공정을 통해서 불량률을 줄이고 스마트 팩토리의 데이터 적합성을 검증하고자 한다.

Keywords

Acknowledgement

이 논문은 2023년 순천대학교 교연비 사업에 의하여 연구되었음.

References

  1. Y. Choi and I. Cho, "Study on the quality prediction using AI in the iron casting process," The Korean Society of Manufacturing Technology Engineers, vol. 2022, no. 7, 2022, pp. 157-157.
  2. H. Chong, K. Bae, M. Lee, H. Kwon, and S. Hong, "Quality Strategy for Building a Smart Factory in the Fourth Industrial Revolution," Journal of Korean Society for Quality Management, vol. 48, no. 1, 2020, pp. 87-105. https://doi.org/10.7469/JKSQM.2020.48.1.87
  3. M. Kim and D. Kim, "IoT-Based Device Utilization Technology for Big Data Collection in Foundry," Journal of Korea Foundry Society, vol. 41, no. 6, 2021, pp. 550-557. https://doi.org/10.7777/JKFS.2021.41.6.550
  4. H. Yang, "Policy Measures for Revitalizing the Artificial Intelligence-Based Smart Factory," The Journal of Korean Institute of Communications and Information Sciences, vol. 45, no. 9, 2020, pp. 1659-1665. https://doi.org/10.7840/kics.2020.45.9.1659
  5. B. So and S. Shin, "The Built of Smart Factory Using Sensors and Virtual Process Design," Journal of the Korea Institute of Electronic Communication Sciences(KIECS), vol. 12, no. 6, 2017, pp. 1071-1080.
  6. S. Ha, W. Lee, K. Gu, and Y. Shin, "A Study on the Deep Learning-Based Defect Prediction Model Using Sensor Data of Semiconductor Equipment," Jounal of The Korea Society of Information Technology Policy & Management, vol.13, no.2, 2021, pp. 2375-2379.
  7. H. Sim, "Artificial intelligence-based harmful bird detection control system," Journal of the Korea Institute of Electronic Communication Sciences(KIECS), vol.16, no.1, 2021, pp. 175-182.
  8. G. Lee and J. Lee, "Data Analysis and AI Model for Defect Prediction in the Injection Process," Journal of Korea Academia-Industrial cooperation Society, vol. 23, no. 12, 2022, pp. 1001-1008. https://doi.org/10.5762/KAIS.2022.23.12.1001
  9. S. Byeon, C. Kang, and S. Sim, "Defect Type Prediction Method in Manufacturing Process Using Data Mining Technique," Journal of society of Korea industrial and systems engineering, vol. 27, no. 2, 2004, pp. 10-16.
  10. J. Ahn and J. Jung, "Predicting and Interpreting Quality of CMP Process for Semiconductor Wafers Using Machine Learning," The journal of Bigdata, vol. 4, no. 2, 2019, pp. 61-71. https://doi.org/10.36498/kbigdt.2019.4.2.61
  11. J. Yun, H. An, and Y. Choi, "A Machine Learning Based Facility Error Pattern Extraction Framework for Smart Manufacturing," The Journal of Society for e-Business Studies, vol. 23, no. 2, 2018, pp. 97-110. https://doi.org/10.7838/JSEBS.2018.23.2.097
  12. J. Moon and S. Kim, "Image Processing Processor Design for Artificial Intelligence Based Service Robot," Journal of the Korea Institute of Electronic Communication Sciences(KIECS), vol. 17, no. 4, 2022, pp. 633-640.
  13. D. Sung and H. Kim, "An Study on Identification of the Causing Factors for Defected Wafer Using CNN : Focusing on Semiconductor In-line Process," The Journal of Business Education, vol. 36, no. 2 2022, pp. 71-91.