Journal of the Korean Society of Industry Convergence (한국산업융합학회 논문집)

The Korean Society of Industry Convergence (한국산업융합학회)
권호 표지
DOI QR코드

DOI QR Code

Load Prediction using Finite Element Analysis and Recurrent Neural Network

유한요소해석과 순환신경망을 활용한 하중 예측

  • Jung-Ho Kang (Dept. of Mechanical Engineering, Dong A University)
  • Received : 2024.01.10
  • Accepted : 2024.01.23
  • Published : 2024.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

Artificial Neural Networks that enabled Artificial Intelligence are being used in many fields. However, the application to mechanical structures has several problems and research is incomplete. One of the problems is that it is difficult to secure a large amount of data necessary for learning Artificial Neural Networks. In particular, it is important to detect and recognize external forces and forces for safety working and accident prevention of mechanical structures. This study examined the possibility by applying the Current Neural Network of Artificial Neural Networks to detect and recognize the load on the machine. Tens of thousands of data are required for general learning of Recurrent Neural Networks, and to secure large amounts of data, this paper derives load data from ANSYS structural analysis results and applies a stacked auto-encoder technique to secure the amount of data that can be learned. The usefulness of Stacked Auto-Encoder data was examined by comparing Stacked Auto-Encoder data and ANSYS data. In addition, in order to improve the accuracy of detection and recognition of load data with a Recurrent Neural Network, the optimal conditions are proposed by investigating the effects of related functions.

Keywords

References

  1. M. X. Bastidas-Rodriguez, L. Polania, A. Gruson, F. Prieto-Ortiz,"Deep Learning for fractographic classification in metallic materials", Engineering Failure Analysis, vol.113, (2020) DOI: 10.1016/j.engfailanal.2020.104532.
  2. I. Goodfellow, Y. Bengio, A. Courville, Deep Learning, MIT Press, pp. 161-309, (2017).
  3. J. Kim, I.-S. Jung, W.-G. Yun, J.-Y.Kim, & I.-S. Park, "Preliminary Analysis on Artificial Intelligence-based Methodology for Selecting Repair and Rehabilitation Methods of Bridges", Journal of the Korean Society of Industry Convergence, vol. 24(6_2), pp. 861-872. (2021). DOI: 10.21289/KSIC.2021.24.6.861
  4. K.-S. Lee, J.-U. Kim, S.-C. Cho, & B.-S. Shin, "Automated Inspection System for Micropattern Defection Using Artificial Intelligence", Journal of the Korean Society of Industry Convergence, vol. 24(6_2), pp. 729-735. (2021). DOI: 10.21289/KSIC.2021.24.6.729
  5. H. P.Jang, D. S. Han, "Compensation of Relation Formula between Luffing Wire Tension and Overturning Moment in a Crawler Crane Considering the Deflection of Boom", J. of KSMPE, vol. 10, no. 4, pp. 44-49, (2011).
  6. D. K. Lee, J. H. Kang, T. H. Kim, C. K. Oh, J. M. Kim, J. M. Kim, "Analysis of Roller Load by Boom Length and Rotation Angle of a Crawler Crane", J. of KSMPE, vol. 20, no. 3, pp. 83-91, (2021). https://doi.org/10.14775/ksmpe.2021.20.03.083
  7. J. S. Lee, B. J. Choi, M. G. Lee, J. S. Kim, S. W. Lee, Y. H. Jeon, "Defect Classification of Cross-section of Additive Manufacturing Using Image-Labeling", J. of KSMPE, vol. 19, no. 7, pp. 7-15,
  8. K. B. Prakash, R. K. Eluri, N. B. Naidum, S. H. Nallamala, P. Mishra, P. Dharani, "Accurate Hand Gesture Recognition using CNN and RNN Approaches", International Journal of Advanced Trends in Computer Science and Engineering, vol 9, no.3, (2020). DOI: 10.30534/ijatcse/2020/114932020
  9. S. M. Kasongo, "A deep learning technique for intrusion detection system using a Recurrent Neural Networks based framework", Computer Communications, vol. 199, pp. 113-125, (2023). DOI: 10.1016/j.comcom.2022.12.010.
  10. J. Dawani, Hands-On Mathematics for Deep Learning, Packt Publishing, Birmingham, pp. 247-255, (2020).
  11. I. Goodfellow, Y. Bengio and A. Courville, Deep Learning, MIT Press, pp. 363-408, (2017).
  12. J. S. Lee, B. J. Choi, M. G. Lee, J. S. Kim, S. W. Lee, Y. H. Jeon, " Defect Classification of Cross-section of Additive Manufacturing Using Image-Labeling", J. of KSMPE, vol. 19, no. 7, pp.7-15, (2020). https://doi.org/10.14775/ksmpe.2020.19.07.007
  13. J. Dawani, Hands-On Mathematics for Deep Learning, Packt Publishing, pp. 121-204, (2020).
  14. T. H. Kim, A Study on Hoisting Load Prediction through Deep Learning-Based Crawler Crane Roller Load, Master's Thesis, Dong-A University, (2021).
  15. D. K. Lee, Study on roller load analysis of crawler crane and elicitation of overturn risk rate applying machine learning, Master's Thesis, Dong-A University, (2020).
  16. D. K. Lee, J. H. Kang, T. H. Kim, C. K. Oh, J. M. Kim, J. M. Kim, "Analysis of Roller Load by Boom Length and Rotation Angle of a Crawler Crane", J. of KSMPE, vol. 20, no. 3, pp. 83-91, (2021). https://doi.org/10.14775/ksmpe.2021.20.03.083
  17. M. S. Kim, A study on hoisting load prediction through deep learning-based crawler crane roller load, Master's Thesis, Dong-A University, Republic of Korea, (2022).
  18. F. P. Beer, E. R. Johnston, J. T. DeWolf, D. Mazurek, S. Sanghi, Mechanics of materials, McGraw-Hill Education, New York, pp. 418-437, (2020).
  19. M. Alam, G. Liu, H. Bao, B. Han, "A Stacked Autoencoder-Based Deep Neural Network for Achieving Gearbox Fault Diagnosis", Mathematical Problems in Engineering, vol. 2018, Article ID 5105709, pp. 10, (2018). DOI: 10.1155/2018/5105709
  20. J. Dawani, Hands-on mathematics for deep learning, packt publishing 2020:283-304, (2020).
  21. I. Goodfellow, Y. Bengio and A. Courville, Deep Learning, MIT Press, pp. 493-515, (2017).
  22. H. Kim, and T. Lee, "Stacked Autoencoder Based Malware Feature Refinement Technology Research," Journal of the Korea Institute of Information Security & Cryptology, vol. 30, no. 4, pp. 593-603, (2020). DOI: 10.13089/JKIISC.2020.30.4.593
  23. Y. J. Yoo, D. H. Kim and J. K. Lee, " A performance comparison of super resolution model with different activation functions", KIPS 9, pp. 303-308, (2020). DOI: 10.3745/KTSDE.2020.9.10.303.
  24. J. Dawani, Hands-on mathematics for deep learning, packt publishing 2020:178-192. (2020).
  25. D. Chicco, M. J. Warrens and G. Jurman, "The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation", PeerJ Comput. Sci. 7, e623, (2021). DOI: 10.7717/peerj-cs.623.
  26. J. Dawani, Hands-on mathematics for deep learning, packt publishing 2020, pp. 192-196, (2020).
  27. I. Goodfellow, Y. Bengio and A. Courville, Deep Learning, MIT Press, pp. 267-320. (2017).
  28. J. Dawani, Hands-on mathematics for deep learning, packt publishing 2020, pp. 121-142, (2020).