한국포장학회지 (KOREAN JOURNAL OF PACKAGING SCIENCE & TECHNOLOGY)

한국포장학회 (Korea Society of Packaging Science and Technology)
권호 표지
DOI QR코드

DOI QR Code

A Comparative Analysis of Artificial Neural Network (ANN) Architectures for Box Compression Strength Estimation

  • By Juan Gu (School of Packaging, Michigan State University) ;
  • Benjamin Frank (Packaging Corporation of America) ;
  • Euihark Lee (School of Packaging, Michigan State University)
  • 발행 : 2023.12.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Though box compression strength (BCS) is commonly used as a performance criterion for shipping containers, estimating BCS remains a challenge. In this study, artificial neural networks (ANN) are implemented as a new tool, with a focus on building up ANN architectures for BCS estimation. An Artificial Neural Network (ANN) model can be constructed by adjusting four modeling factors: hidden neuron numbers, epochs, number of modeling cycles, and number of data points. The four factors interact with each other to influence model accuracy and can be optimized by minimizing model's Mean Squared Error (MSE). Using both data from the literature and "synthetic" data based on the McKee equation, we find that model estimation accuracy remains limited due to the uncertainty in both the input parameters and the ANN process itself. The population size to build an ANN model has been identified based on different data sets. This study provides a methodology guide for future research exploring the applicability of ANN to address problems and answer questions in the corrugated industry.

키워드

참고문헌

  1. Frank, B., Corrugated Box Compression-A Literature Survey. Packaging Technology and Science 2014. 27(2): 105.
  2. Kellicutt, K.Q., & Landt, E. F, Basic design data for the use of fiberboard in shipping containers. Fibre Containers, 1951. 36(12): 62-80.
  3. Batelka, J.J. and C.N. Smith, Package compression model. Project 3746, final report to the Containerboard and Kraft Paper Group of the American Forest and Paper Association. 1993.
  4. Nordstrand, T., Analysis and testing of corrugated board panels into the post-buckling regime. Composite Structures, 2004. 63(2): 189-199. https://doi.org/10.1016/S0263-8223(03)00155-7
  5. Zhou, Y.H., B.Q. Zhong, and R.H. Guo. The multiple linear regression model on compression strength of corrugated boxes. in Applied Mechanics and Materials. 2012. Trans Tech Publ.
  6. Urbanik, T.J. and B. Frank, Box compression analysis of world-wide data spanning 46 years. Wood and fiber science, 2006: 399-416.
  7. Maltenfort, G., Revision of top to bottom compression equations for doublewall corrugated. Paperboard Packaging 48 (11),
  8. Coffin, D.W., Some observations towards improved predictive models for box compression strength. TAPPI J, 2015. 14: 537-545. https://doi.org/10.32964/TJ14.8.537
  9. McKee, R., J. Gander, and J. Wachuta, Compression strength formula for corrugated boxes. Paperboard packaging, 1963. 48(8): 149-159.
  10. Frank, B. and K. Kruger, Assessing variation in package modeling. TAPPI JOURNAL, 2021. 20(4): 231-238. https://doi.org/10.32964/TJ20.4.231
  11. Park, J., et al., Finite element-based simulation for edgewise compression behavior of corrugated paperboard for packaging of agricultural products. Applied Sciences, 2020. 10(19): 6716.
  12. Park, J., S. Chang, and H.M. Jung, Numerical prediction of equivalent mechanical properties of corrugated paperboard by 3D finite element analysis. Applied Sciences, 2020. 10(22): 7973.
  13. Park, J.-M., T.-Y. Park, and H.-M. Jung, Prediction of Deflection Due to Multistage Loading of a Corrugated Package. Applied Sciences, 2023. 13(7): 4236.
  14. Molina, E. and L. Horvath, Development of a Gaussian Process Model as a Surrogate to Study Load Bridging Performance in Racked Pallets. Applied Sciences, 2021. 11(24): 11865.
  15. Haj-Ali, R., et al., Refined nonlinear finite element models for corrugated fiberboards. Composite Structures, 2009. 87(4): 321-333. https://doi.org/10.1016/j.compstruct.2008.02.001
  16. Hua, G., et al., Experimental and numerical analysis of the edge effect for corrugated and honeycomb fiberboard. Strength of Materials, 2017. 49(1): 188-197. https://doi.org/10.1007/s11223-017-9857-5
  17. Garbowski, T., T. Gajewski, and J.K. Grabski, Estimation of the compressive strength of corrugated cardboard boxes with various perforations. Energies, 2021. 14(4): 1095.
  18. Jimenez-Caballero, M., et al. Design of different types of corrugated board packages using finite element tools. in SIMULIA customer conference. 2009.
  19. Garbowski, T., T. Gajewski, and J.K. Grabski, Estimation of the compressive strength of corrugated cardboard boxes with various openings. Energies, 2020. 14(1): 155.
  20. Han, J. and J.M. Park, Finite element analysis of vent/hand hole designs for corrugated fibreboard boxes. Packaging Technology and Science: An International Journal, 2007. 20(1): 39-47. https://doi.org/10.1002/pts.741
  21. Biancolini, M. and C. Brutti, Numerical and experimental investigation of the strength of corrugated board packages. Packaging Technology and Science: An International Journal, 2003. 16(2): 47-60. https://doi.org/10.1002/pts.609
  22. Garbowski, T., et al., Crushing of single-walled corrugated board during converting: Experimental and numerical study. Energies, 2021. 14(11): 3203.
  23. Marin, G., et al., Experimental and finite element simulated box compression tests on paperboard packages at different moisture levels. Packaging Technology and Science, 2021. 34(4): 229-243. https://doi.org/10.1002/pts.2554
  24. Kobayashi, T., Numerical Simulation for Compressive Strength of Corrugated Fiberboard Box. JAPAN TAPPI JOURNAL, 2019. 73(8): 793-800. https://doi.org/10.2524/jtappij.73.793
  25. Fadiji, T., et al., The efficacy of finite element analysis (FEA) as a design tool for food packaging: A review. Biosystems Engineering, 2018. 174: 20-40. https://doi.org/10.1016/j.biosystemseng.2018.06.015
  26. Kleene, S.C., Representation of events in nerve nets and finite automata. Automata studies, 1956. 34: 3-41. https://doi.org/10.1515/9781400882618-002
  27. Abiodun, O.I., et al., State-of-the-art in artificial neural network applications: A survey. Heliyon, 2018. 4(11): e00938.
  28. Mitic, V. Benefits of artificial intelligence and machine learning in marketing. in Sinteza 2019-International scientific conference on information technology and data related research. 2019. Singidunum University.
  29. Sun, A.Y. and B.R. Scanlon, How can Big Data and machine learning benefit environment and water management: a survey of methods, applications, and future directions. Environmental Research Letters, 2019. 14(7): 073001.
  30. Pi, Y., Machine learning in governments: Benefits, challenges and future directions. JeDEM-eJournal of eDemocracy and Open Government, 2021. 13(1): 203-219. https://doi.org/10.29379/jedem.v13i1.625
  31. Kalogirou, S.A., Artificial neural networks in renewable energy systems applications: a review. Renewable and sustainable energy reviews, 2001. 5(4): 373-401. https://doi.org/10.1016/S1364-0321(01)00006-5
  32. Aylak, B.L., et al., Application of machine learning methods for pallet loading problem. Applied Sciences, 2021. 11(18): 8304.
  33. Garbowski T, Knitter-Piatkowska A, Grabski JK. Estimation of the Edge Crush Resistance of Corrugated Board Using Artificial Intelligence. Materials, 2023, 16, 1631.
  34. Lisboa, P.J., A review of evidence of health benefit from artificial neural networks in medical intervention. Neural networks, 2002. 15(1): 11-39. https://doi.org/10.1016/S0893-6080(01)00111-3
  35. Smith, J., Advances in neural networks and potential for their application to steel metallurgy. Materials Science and Technology, 2020. 36(17): 1805-1819. https://doi.org/10.1080/02670836.2020.1839206
  36. Sheikhtaheri, A., F. Sadoughi, and Z. Hashemi Dehaghi, Developing and using expert systems and neural networks in medicine: a review on benefits and challenges. Journal of medical systems, 2014. 38: 1-6. https://doi.org/10.1007/s10916-014-0110-5
  37. Adamopoulos, S., et al., Predicting the properties of corrugated base papers using multiple linear regression and artificial neural networks. Drewno: prace naukowe, doniesienia, komunikaty, 2016. 59.
  38. Malasri, S., P. Rayapati, and D. Kondeti, Predicting Corrugated Box Compression Strength Using an Artificial Neural Network. International Journal, 2016. 4(1): 169-176. https://doi.org/10.23953/cloud.ijapt.21
  39. Archaviboonyobul, T., et al., An analysis of the influence of hand hole and ventilation hole design on compressive strength of corrugated fiberboard boxes by an artificial neural network model. Packaging Technology and Science, 2020. 33(4-5): 171-181. https://doi.org/10.1002/pts.2495
  40. Goodfellow, I., Y. Bengio, and A. Courville, Deep learning. 2016: MIT press.
  41. Roodschild, M., J. Gotay Sardinas, and A. Will, A new approach for the vanishing gradient problem on sigmoid activation. Progress in Artificial Intelligence, 2020. 9(4): 351-360. https://doi.org/10.1007/s13748-020-00218-y
  42. Kubat, M. and M. Kubat, Artificial neural networks. An Introduction to Machine Learning, 2021: 117-143.
  43. Hang, H.M. and Y.M. Chou, Chapter 5 - Motion Estimation for Image Sequence Compression. This work was supported in part by the NSC grant 83-0408-E009012, in Handbook of Visual Communications, H.-M. Hang and J.W. Woods, Editors. 1995, Academic Press: San Diego. 147-188. ISBN: 9780123230508.
  44. Hyndman, Rob J. Moving Averages. International Encyclopedia of Statistical Science. 2nd ed.; Editors: Lovric, Miodrag. Publisher: Springer. (2011); 866-869.