Journal of the Computational Structural Engineering Institute of Korea (한국전산구조공학회논문집)

Computational Structural Engineering Institute of Korea (한국전산구조공학회)
권호 표지
DOI QR코드

DOI QR Code

Analysis of Piezoresistive Properties of Cement Composites with Fly Ash and Carbon Nanotubes Using Transformer Algorithm

트랜스포머 알고리즘을 활용한 탄소나노튜브와 플라이애시 혼입 시멘트 복합재료의 압저항 특성 분석

  • Jonghyeok Kim (Department of Civil and Environmental Engineering, Hanbat National University) ;
  • Jinho Bang (School of Civil Engineering, Chungbuk National University) ;
  • Haemin Jeon (Department of Civil and Environmental Engineering, Hanbat National University)
  • 김종혁 (한밭대학교 건설환경공학과) ;
  • 방진호 (충북대학교 토목공학부) ;
  • 전해민 (한밭대학교 건설환경공학과)
  • Received : 2023.11.07
  • Accepted : 2023.11.09
  • Published : 2023.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

In this study, the piezoresistive properties of cementitious composites enhanced with carbon nanotubes for improved electrical conductivity were analyzed using a deep learning-based transformer algorithm. Experimental execution was performed in parallel for acquisition of training data. Previous studies on mixture design, specimen fabrication, chemical composition analysis, and piezoresistive performance testing are also reviewed in this paper. Notably, specimens in which fly ash substituted 50% of the binder material were fabricated and evaluated in this study, in addition to carbon nanotube-infused specimens, thereby exploring the potential enhancement of piezoresistive characteristics in conductive cementitious materials. The experimental results showed more stable piezoresistive responses in specimens with fly-ash substituted binder. The transformer model was trained using 80% of the gathered data, with the remaining 20% employed for validation. The analytical outcomes were generally consistent with empirical measurements, yielding an average absolute error and root mean square error between 0.069 to 0.074 and 0.124 to 0.132, respectively.

본 논문에서는 시멘트에 탄소나노튜브를 혼입하여 전기 전도성을 향상시킨 복합재료의 압저항 특성을 딥러닝 기반 트랜스포머 알고리즘을 적용하여 분석하였다. 훈련 데이터 확보를 위한 실험수행을 병행하였으며, 기존 연구문헌을 참조하여 배합설정, 시편제작, 화학조성 분석, 압저항 성능측정 실험을 수행하였다. 특히 본 연구에서는 탄소나노튜브 혼입 시편뿐 아니라 플라이애시를 바인더 대비 50% 대체한 시편에 대한 제작 및 성능평가를 함께 수행하여, 전도성 시멘트 복합재료의 압저항 특성 향상 가능성을 탐구하였다. 실험결과, 플라이애시 대체 바인더의 경우 보다 안정적인 압저항 특성결과가 관찰되었으며, 측정된 데이터의 80%를 이용하여 트랜스포머 모델을 훈련시키고 나머지 20%를 통해 검증하였다. 해석 결과는 실험적 측정과 대체로 부합하였으며, 평균 절대 오차 및 평균 제곱근 오차는 각각 0.069~0.074와 0.124~0.132을 나타내었다.

Keywords

References

  1. Al-Selwi, S.M., Hassan, M.F., Abdulkadir, S.J., Muneer, A. (2023) LSTM Inefficiency in Long-Term Dependencies Regression Problems, J. Adv. Res. Appl. Sci. & Eng. Technol., 30(3), pp. 16~31. https://doi.org/10.37934/araset.30.3.1631
  2. Azhari, F. (2008) Cement-based Sensors for Structural Health Monitoring, Doctoral Dissertation, University of British Columbia.
  3. Bang, H., Yu, B., Jeon, H. (2022) Assembly Performance Evaluation for Prefabricated Steel Structures Using k-nearest Neighbor and Vision Sensor, J. Comput. Struct. Eng. Inst. Korea, 35(5), pp.259~266. https://doi.org/10.7734/COSEIK.2022.35.5.259
  4. Bona-Pellissier, J., Bachoc, F., Malgouyres, F. (2023) Parameter Identifiability of a Deep Feedforward ReLU Neural Network, Mach. Learn., 112(11), pp.4431~4493. https://doi.org/10.1007/s10994-023-06355-4
  5. Cho, K., Van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., Bengio, Y. (2014) Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation, arXiv preprint arXiv:1406.1078.
  6. Dinesh, A., Sudharsan, S.T., Haribala, S. (2021) Self-Sensing Cement-based Sensor with Carbon Nanotube: Fabrication and Properties-A Review. Mater. Today: Proc., 46, pp.5801~5807. https://doi.org/10.1016/j.matpr.2021.02.722
  7. Ding, S., Ruan, Y., Yu, X., Han, B., Ni, Y.Q. (2019) Self-Monitoring of Smart Concrete Column Incorporating CNT/NCB Composite Fillers Modified Cementitious Sensors, Constr. & Build. Mater., 201, pp.127~137. https://doi.org/10.1016/j.conbuildmat.2018.12.203
  8. Goodfellow, I., Bengio, Y., Courville, A. (2016) Deep learning, The MIT Press, 2016, ISBN: 0262035618.
  9. Hashemi, R., Weng, G.J. (2016) A Theoretical Treatment of Graphene Nanocomposites with Percolation Threshold, Tunneling-Assisted Conductivity and Microcapacitor Effect in AC and DC Electrical Settings, Carbon, 96, pp.474~490. https://doi.org/10.1016/j.carbon.2015.09.103
  10. Hochreiter, S., Schmidhuber, J. (1997) Long Short-Term Memory, Neural Computation, 9, pp.1735~1780. https://doi.org/10.1162/neco.1997.9.8.1735
  11. Jang, D., Yoon, H.N., Yang, B., Seo, J., Farooq, S.Z., Lee, H.K. (2022) Synergistic Effects of CNT and CB Inclusion on the Piezoresistive Sensing behaviors of Cementitious Composites Blended with Fly Ash, Smart Struct. & Syst., 29(2), pp.351~359.
  12. Kim, G.M., Nam, I.W., Yang, B., Yoon, H.N., Lee, H.K., Park, S. (2019) Carbon Nanotube (CNT) Incorporated Cementitious Composites for Functional Construction Materials: The State of the Art, Compos. Struct., 227, p.111244.
  13. Lipton, Z.C., Berkowitz, J., Elkan, C. (2015) A Critical Review of Recurrent Neural Networks for Sequence Learning, arXiv preprint arXiv:1506.00019.
  14. Luo, T., Wang, Q., Fang, Z. (2023) Effect of Graphite on the Self-Sensing Properties of Cement and Alkali-Activated Fly Ash/Slag based Composite Cementitious Materials, J. Build. Eng., 77, p.107493.
  15. Park, H.M., Park, S.M., Lee, S.M., Shon, I.J., Jeon, H., Yang, B.J. (2019) Automated Generation of Carbon Nanotube Morphology in Cement Composite Via Data-Driven Approaches, Compos. Part B: Eng., 167, pp.51~62. https://doi.org/10.1016/j.compositesb.2018.12.011
  16. Piro, N.S., Mohammed, A.S., Hamad, S.M. (2023) Electrical Resistivity Measurement, Piezoresistivity behavior and Compressive Strength of Concrete: A Comprehensive Review, Mater.s Today Commun., p.106573.
  17. Provis, J.L., Yong, C.Z., Duxson, P., van Deventer, J.S. (2009) Correlating Mechanical and Thermal Properties of Sodium Silicate-fly Ash Geopolymers, Colloids & Surf. A: Physicochem. & Eng. Aspect., 336(1-3), pp.57~63. https://doi.org/10.1016/j.colsurfa.2008.11.019
  18. Souri, H., Yu, J., Jeon, H., Kim, J.W., Yang, C.M., You, N.H., Yang, B.J. (2017) A Theoretical Study on the Piezoresistive Response of Carbon Nanotubes Embedded in Polymer Nanocomposites in an Elastic Region, Carbon, 120, pp.427~437. https://doi.org/10.1016/j.carbon.2017.05.059
  19. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, Polosukhin, I. (2017) Attention Is All You Need, Adv. Neural Inf. Proc. Syst., 30.
  20. Wang, L., Aslani, F. (2022) Self-Sensing Performance of Cementitious Composites with Functional Fillers at Macro, Micro and Nano Scales, Constr. & Build. Mater., 314, p.25679.
  21. Williams, R.J., Zipser, D. (1989) A Learning Algorithm for Continually Running Fully Recurrent Neural Networks, Neural Comput., 1, pp.270~280. https://doi.org/10.1162/neco.1989.1.2.270
  22. Yu, Y., Si, X., Hu, C., Zhang, J. (2019) A Review of Recurrent Neural Networks: LSTM Cells and Network Architectures, Neural Comput., 31, pp.1235~1270. https://doi.org/10.1162/neco_a_01199
  23. Zhang, Z., Provis, J. L., Reid, A., Wang, H. (2014) Fly Ash-based Geopolymers: The Relationship between Composition, Pore Structure and Efflorescence, Cement & Concr. Res., 64, pp.30~41. https://doi.org/10.1016/j.cemconres.2014.06.004