Composites Research

The Korean Society for Composite Materials (한국복합재료학회)
권호 표지
DOI QR코드

DOI QR Code

Load Fidelity Improvement of Piecewise Integrated Composite Beam by Construction Training Data of k-NN Classification Model

k-NN 분류 모델의 학습 데이터 구성에 따른 PIC 보의 하중 충실도 향상에 관한 연구

  • Ham, Seok Woo (Department of Mechanical Engineering, Graduated School, Kongju National University) ;
  • Cheon, Seong S. (Department of Mechanical Engineering, Graduated School, Kongju National University)
  • Received : 2019.12.26
  • Accepted : 2020.05.07
  • Published : 2020.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

Piecewise Integrated Composite (PIC) beam is composed of different stacking against loading type depending upon location. The aim of current study is to assign robust stacking sequences against external loading to every corresponding part of the PIC beam based on the value of stress triaxiality at generated reference points using the k-NN (k-Nearest Neighbor) classification, which is one of representative machine learning techniques, in order to excellent superior bending characteristics. The stress triaxiality at reference points is obtained by three-point bending analysis of the Al beam with training data categorizing the type of external loading, i.e., tension, compression or shear. Loading types of each plane of the beam were classified by independent plane scheme as well as total beam scheme. Also, loading fidelities were calibrated for each case with the variation of hyper-parameters. Most effective stacking sequences were mapped into the PIC beam based on the k-NN classification model with the highest loading fidelity. FE analysis result shows the PIC beam has superior external loading resistance and energy absorption compared to conventional beam.

Piecewise Integrated Composite (PIC) 보는 하중 유형에 따라 구간을 나누어, 각 구간마다 하중 유형에 강한 복합재료의 적층 순서를 배열한 보이다. 본 연구는 PIC 보의 구간을 머신 러닝의 일종인 k-NN(k-Nearest Neighbor) 분류를 통해 나누어 기존에 제시되었던 PIC 보에 비해 우수한 굽힘 특성을 갖게 하는 것이 목적이다. 먼저, 알루미늄 보의 3점 굽힘 해석을 통하여 참조점에서의 3축 특성(Triaxiality) 값 데이터를 얻었고, 이를 통해 인장, 전단, 압축의 레이블을 가진 학습 데이터가 만들어진다. 학습 데이터를 통해 각 면마다 독립적인 k-NN 분류 모델을 구성하는 방법(Each plane)과 전체 면에 대한 k-NN 분류 모델을 구성하는 방법(one part)을 이용하여 k-NN 분류 모델을 생성하였고, 하이퍼파라미터의 튜닝을 통하여 다양한 하중 충실도를 도출하였다. 가장 높은 하중 충실도를 가진 k-NN 분류 모델을 기반으로 보를 매핑(mapping)하였고, PIC 보에 대하여 유한요소 해석을 진행한 결과, 기존에 제시되었던 PIC 보에 비해 최대하중과 흡수 에너지가 커지는 특성을 보였다. 하중 충실도를 수동으로 조절하여 100%로 만든 PIC 보와 비교하였을 때, 최대하중과 흡수에너지가 미소한 차이가 나타났으며 이는 타당한 하중 충실도로 보여진다.

Keywords

References

  1. Na, H.J., Chun, J.S., and Cho, K.S., "Development of CFRP Tubes for the Light-Weight Propeller Shaft of 4WD SUV Vehicles," Journal of the Korean Society of Manufacturing Process Engineers, Vol. 17, No. 4, 2018, pp. 32-38. https://doi.org/10.14775/ksmpe.2018.17.4.032
  2. Chun, D.M., and Ahn, S.H., "Change of Mechanical Properties of Injection-Molded Glass-Fiber-Reinforced Plastic (GFRP) According to Temperature and Water Absorption for Vehicle Weight Reduction," Transactions of the Korean Society of Mechanical Engineers - A, Vol. 37, No. 2, 2013, pp. 199-204. https://doi.org/10.3795/KSME-A.2013.37.2.199
  3. Cheon, S.S., Choi, J.H., and Lee, D.G., "Development of the Composite Bumper Beam for Passenger Cars," Composite Structures, Vol. 32, No. 1-4, 1995, pp. 491-499. https://doi.org/10.1016/0263-8223(95)00078-X
  4. Belingardi, G., Beyene, A.T., and Koricho, E.G., "Geometrical Optimization of Bumper Beam Profile Made of Pultruded Composite by Numerical Simulation," Composite Structures, Vol. 102, 2013, pp. 217-225. https://doi.org/10.1016/j.compstruct.2013.02.013
  5. Kim, D.H., Kim, H.G., and Kim, H.S., "Design Optimization and Manufacture of Hybrid Glass/carbon Fiber Reinforced Composite Bumper Beam for Automobile Vehicle," Composite Structures, Vol. 131, 2015, pp. 742-752. https://doi.org/10.1016/j.compstruct.2015.06.028
  6. Jeong, C.H., Ham, S.W., Kim, G.S., and Cheon, S.S., "Development of the Piecewisely-integrated Composite Bumper Beam Based on the IIHS Crash Analysis," Composites Research, Vol. 31, No. 1, 2018, pp. 37-41. https://doi.org/10.7234/composres.2018.31.1.037
  7. Maeng, J.W., Bang, S.W., and Jhun, M.S., "On the Use of Modified Adaptive Nearest Neighbors for Classification," The Journal of Applied Statistics, Vol. 23, No. 6, 2010, pp. 1093-1102.
  8. Han, J.C., Kim, S.K., and Yoon, C.H., "A New Incremental Instance-Based Learning Using Recursive Partitioning," The KIPS Transactions : Part B, Vol. 13B, No. 2, 2006, pp. 127-132. https://doi.org/10.3745/KIPSTB.2006.13B.2.127
  9. Nguyen, B., Morell, C., and De Baets, B., "Distance Metric Learning for Ordinal Classification Based on Triplet Constraints," Knowledge-Based Systems, Vol. 142, 2018, pp. 17-28. https://doi.org/10.1016/j.knosys.2017.11.022
  10. Kwon, O.H., and Kang, J.W., "An Estimation of Deformation for Composites by DIC," Journal of the Korean Society for Power System Engineering, Vol. 18, No. 4, 2014, pp. 78-84. https://doi.org/10.9726/kspse.2014.18.4.078
  11. Ham, S.W., Cho, J.U., and Cheon, S.S., "Load Fidelity Improvement of Piecewise Integrated Composite Beam by Irregular Arrangement of Reference Points," Composites Research, Vol. 32, No. 5, 2019, pp. 216-221. https://doi.org/10.7234/composres.2019.32.5.216
  12. Bai, Y., and Wierzbicki, T., "A New Model of Metal Plasticity and Fracture with Pressure and Lode Dependence," International Journal of Plasticity, Vol. 24, No. 6, 2008, pp. 1071-1096. https://doi.org/10.1016/j.ijplas.2007.09.004