DOI QR코드

DOI QR Code

Prediction of Multi-Physical Analysis Using Machine Learning

기계학습을 이용한 다중물리해석 결과 예측

  • Received : 2016.02.12
  • Accepted : 2016.03.22
  • Published : 2016.03.31

Abstract

This paper proposes a new prediction method to reduce times and labor of repetitive multi-physics simulation. To achieve exact results from the whole simulation processes, complex modeling and huge amounts of time are required. Current multi-physics analysis focuses on the simulation method itself and the simulation environment to reduce times and labor. However this paper proposes an alternative way to reduce simulation times and labor by exploiting machine learning algorithm trained with data set from simulation results. Through comparing each machine learning algorithm, Gaussian Process Regression showed the best performance with under 100 training data and how similar results can be achieved through machine-learning without a complex simulation process. Given trained machine learning algorithm, it's possible to predict the result after changing some features of the simulation model just in a few second. This new method will be helpful to effectively reduce simulation times and labor because it can predict the results before more simulation.

본 논문에서는 기계학습 알고리즘을 이용하여 다중물리(Multi-physics) 시뮬레이션의 반복 횟수를 획기적으로 줄일 수 있는 다중물리해석 예측 방법을 제안한다. 기존의 다중물리해석 시뮬레이션의 경우 소요되는 시간과 노력을 줄이기 위해 시뮬레이션 자체에 대한 방법과 환경 개선에 초점이 맞추어져 있으나 본 논문에서는 다중물리 시뮬레이션 결과를 기계학습 알고리즘으로 학습하여 추가적인 시뮬레이션을 수행하지 않고 학습된 기계학습 알고리즘을 사용하여 수십분에서 수시간에 걸리는 다중 물리 해석과 유사한 결과를 수초 내에 예측할 수 있음을 보였다. 기계학습 알고리즘 간의 성능을 비교하여 다중물리해석에 적합한 기계학습 알고리즘을 확인하였으며 가장 우수한 성능을 보인 가우시안 프로세스 회귀(Gaussian Process Regression)의 경우 100개 이하의 학습 샘플만으로도 우수한 예측 결과를 얻어낼 수 있음을 확인하였다. 제안하는 방식을 통해 시뮬레이션을 하고자 하는 모델의 형상이나 재질이 변경될 경우 기존의 시뮬레이션 결과로 학습된 알고리즘이 있다면 시뮬레이션을 반복 수행하기 전에 알고리즘을 이용하여 결과를 예측할 수 있어 시뮬레이션의 반복 횟수를 줄일 수 있을 것으로 기대한다.

Keywords

References

  1. Youngtaek Im, "Multi-physics analysis case using ANSYS software", Journal of KSME, Vol. 54, No. 6, p46, June 2014
  2. http://www.ansys.com/About-ANSYS
  3. ANSYS Product Brochure, "ansys-hfss-brochure-16.0.pdf", ANSYS Incorporated, 2016
  4. ANSYS Product Brochure, "ansys-icepak-brochure-14.0.pdf", ANSYS Incorporated, 2011
  5. ANSYS Product Brochure, "ansys-mechanical-suite-brochure.pdf", ANSYS Incorporated, 2011
  6. ANSYS Product Brochure, "workbench-plat form-12.1.pdf", ANSYS Incorporated, 2011
  7. https://en.wikipedia.org/wiki/Parallel_coordinates
  8. http://www.cs.waikato.ac.nz/ml/weka/
  9. Cheolho HanO, Hanock Kwak, Sangwoong Yoon, Munbo Shim, Byoung-Tak Zhang, "Optimization by Neural Networks Learned from Minimum Function Evaluations", Korea Computer Congress 2015 (KCC 2015), pp867-869, CheJu Island, Korea, June 2015
  10. Ross J. Quinlan, "Learning with Continuous Classes", 5th Australian Joint Conference on Artificial Intelligence, pp343-348, Singapore, Nov 1992
  11. Wang ,Y., Witten, I. H., "Induction of model trees for predicting continuous classes", 9th European Conference on Machine Learning, Prague, Czech Republic, April 1997
  12. Chengjun Zhan, Albert Gan, and Mohammed Hadi, "Prediction of Lane Clearance Time of Freeway Incidents Using the M5P Tree Algorithm", IEEE Transactions on Intelligent Systems, Vol. 12, No. 4, Dec 2011
  13. Khaled Bashir Shaban, Abdullah Kadri, Eman Rezk, "Urban Air Pollution Monitoring System with Forecasting Models", Sensors Journal, IEEE, Vol.PP, Issue.99, pp1, Jan 2016
  14. E. K. Onyari, F. M. Ilunga, "Application of MLP Neural Network and M5P Model Tree in Predicting Streamflow: A Case Study of Luvuvhu Catchment, South Africa", International Journal of Innovation, Management and Technology, Vol.4, No. 1, p15, Feb 2013
  15. Seung-Woo Kim, Kyung-Duck Suh, "Prediction of Stability Number for Tetrapod Armour Block Using Artificial Neural Network and M5' Model Tree", Journal of Korean Society of Coastal and Ocean Engineers, Vol.23, No.1, pp109-117, Feb 2011 https://doi.org/10.9765/KSCOE.2011.23.1.109
  16. Park sunho, Seungjin Choi, "Hierarchical Gaussian process model for regression", Korea Computer Congress 2010 (KCC 2010), pp66-67, CheJu Island, Korea, July 2010

Cited by

  1. Heat Exposure Information at Screen Level for an Impact-Based Forecasting and Warning Service for Heat-Wave Disasters vol.11, pp.9, 2016, https://doi.org/10.3390/atmos11090920