한국안전학회지 (Journal of the Korean Society of Safety)

  • 제38권1호
  • /
  • Pages.1-8
  • /
  • 2023
  • /
  • 1738-3803(pISSN)
  • /
  • 2383-9953(eISSN)
한국안전학회 (The Korean Society of Safety)
권호 표지
DOI QR코드

DOI QR Code

신경회로망 기반 우리나라 산업안전시스템의 모델링

Neural Network-based Modeling of Industrial Safety System in Korea

  • 최기흥 (한성대학교 기계시스템공학과)
  • Gi Heung Choi (Department of Mechanical Systems Engineering, Hansung University)
  • 투고 : 2022.05.17
  • 심사 : 2023.02.03
  • 발행 : 2023.02.28
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

It is extremely important to design safety-guaranteed industrial processes because such process determine the ultimate outcomes of industrial activities, including worker safety. Application of artificial intelligence (AI) in industrial safety involves modeling industrial safety systems by using vast amounts of safety-related data, accident prediction, and accident prevention based on predictions. As a preliminary step toward realizing AI-based industrial safety in Korea, this study discusses neural network-based modeling of industrial safety systems. The input variables that are the most discriminatory relative to the output variables of industrial safety processes are selected using two information-theoretic measures, namely entropy and cross entropy. Normalized frequency and severity of industrial accidents are selected as the output variables. Our simulation results confirm the effectiveness of the proposed neural network model and, therefore, the feasibility of extending the model to include more input and output variables.

키워드

과제정보

This study was supported by Hansung University.

참고문헌

  1. Artificial Intelligence, https://ko.wikipedia.org/
  2. G. H. Choi, "Cause Analysis of Accidents Associated with Dangerous Machines and Devices Subject to Safety Certification", J. Korean Soc. Saf., Vol. 35, No. 4, pp. 1-8, 2020.
  3. G. H. Choi, "Improvement of Reliability in Cause Analysis of Industrial Accidents", J. Korean Soc. Saf., Vol. 29, No. 6, pp. 1-8, 2014. https://doi.org/10.14346/JKOSOS.2014.29.6.001
  4. G. H. Choi, "Application of Information -theoretic Measure (Entropy) to Safety Assessment in Manufacturing Processes", Int. J. Safety, Vol. 4, No. 1, pp. 8-13, 2005.
  5. G. H. Choi and B. H. Ryu, "Application of Discrimination Information (Cross Entropy) as Information-theoretic Measure to Safety Assessment in Manufacturing Processes", Int. J. Safety, Vol. 4, No. 2, pp. 1-5, 2005.
  6. J. Shore, "Minimum Cross Entropy Spectral Analysis, Naval Research Laboratory Memorandum Report 3921, NRL, 1979.
  7. John Shore and Rodney Johnson, "Properties of Cross Entropy Minimization", Transaction on Information Theory, Vol IT-27, No. 4, IEEE, pp. 472-482, 1981. https://doi.org/10.1109/TIT.1981.1056373
  8. J. E. Shore and R. M. Gray, "Minimum Cross-Entropy Pattern Classification and Cluster Analysis", IEEE Trans. On Pattern Analysis and Machine Intelligence, Vol. PAMI-4, No. 1, pp. 11-1103, 1982. https://doi.org/10.1109/TPAMI.1982.4767189
  9. Neural Network, http://www.aistudy.com
  10. TensorFlow, https://www.tensorflow.org/
  11. https://stats.stackexchange.com/questions/181/how-to-choose-the-number-of-hidden-layers-and-nodes-in-a-feedforward-neural-netw
  12. G. H. Choi, "Cause Analysis of Accidents at Workplaces in Korea", J. Korean Soc. Saf. (Submitted for publication)