Journal of Sensor Science and Technology (센서학회지)

The Korean Sensors Society (한국센서학회)
권호 표지
DOI QR코드

DOI QR Code

Performance Comparison of Neural Network Models for the Estimation of Instantaneous and Accumulated Powder Exhausts of a Bulk Trailer

벌크 트레일러의 순간 및 누적 분말 배출량 추정을 위한 신경망 모델 성능 비교

  • Chang June Lee (Department of Integrated Systems Engineering, Hankyong National University) ;
  • Jung Keun Lee (School of ICT, Robotics and Mechanical Engineering, Hankyong National University)
  • 이창준 (한경국립대학교 융합시스템공학과) ;
  • 이정근 (한경국립대학교 ICT로봇기계공학부)
  • Received : 2023.04.10
  • Accepted : 2023.05.04
  • Published : 2023.05.31
Download PDF
⟨ Previous Next ⟩

Abstract

Bulk trailers, used for the transportation of powdered materials, such as cement and fly ash, are crucial in the construction industry. The speedy exhaustion of powdered materials stored in the tank of bulk trailers is relevant to improving transportation efficiency and reducing transportation costs. The exhaust time can be reduced by developing an automatic control system to replace the manual exhaust operation. The instantaneous or accumulated exhausts of powdered materials must be measured for automatic control of the bulk trailer exhaust system. Accordingly, we previously proposed a recurrent neural network (RNN) model that estimated the instantaneous exhaust based on low-cost pressure sensor signals without an expensive flowmeter for powders. Although our previous study utilized only an RNN model, models such as multilayer perceptron (MLP) and convolutional neural network (CNN) are also widely utilized for time-series estimation. This study compares the performance of three neural network models (MLP, CNN, and RNN) in estimating instantaneous and accumulated exhausts. In terms of the instantaneous exhaust estimation, the difference in the performance of neural network models was insignificant (that is, 8.64, 8.62, and 8.56% for the MLP, CNN, and RNN, respectively, in terms of the normalized root mean squared error). However, in the case of the accumulated exhaust, the performance was excellent in the order of CNN (1.67%), MLP (2.03%), and RNN (2.20%).

Keywords

Acknowledgement

본 연구는 2022년도 과학기술정보통신부 ICT R&D혁신바우처지원사업 (No.2022-0-00408)의 지원을 받아 수행되었다. 벌크트레일러 배출 시스템 구축 관련하여 아이씨피(주)와 벽우(주)에게 감사드린다.

References

  1. J. S. Hahn, H. M. Sung, M. C. Park, S. Y. Kho, and D. K. Kim, "Empirical evaluation on the efficiency of the trucking industry in Korea", KSCE J. Civ. Eng., Vol. 19, No. 4, pp. 1088-1096, 2015. https://doi.org/10.1007/s12205-012-1009-7
  2. S. Lee, Y. J. Kim, K. T. Kim, Y. J. Kwon, and S. M. Kim, "Analysis of bulk freight transportation", Proc. of KSR Conf., pp. 3278-3288, 2011.
  3. V. Augiseau and S. Barles, "Studying construction materials flows and stock: A review", Resour. Conserv. Recycl., Vol. 123, pp. 153-164, 2017. https://doi.org/10.1016/j.resconrec.2016.09.002
  4. C. R. Gagg, "Cement and concrete as an engineering material: An historic appraisal and case study analysis", Eng. Fail. Anal., Vol. 40, pp. 114-140, 2014. https://doi.org/10.1016/j.engfailanal.2014.02.004
  5. The Korea Transport Institute, "2021 annual report of freight transport market trend", 2021.
  6. J. S. Lim, "A study on the mechanism and influencing factors for truck safety rates", Korea Logist. Rev., Vol. 28, No. 2, pp. 9-20, 2018. https://doi.org/10.17825/klr.2018.28.2.9
  7. J. G. Kim and J. G. Lee, "Static and dynamic finite element analyses of a bulk-cement trailer", Trans. Korean Soc. Mech. Eng. A, Vol. 36, No. 8, pp. 945-951, 2012. https://doi.org/10.3795/KSME-A.2012.36.8.945
  8. J. Kim, H. S. Roh, Y. Min, S. H. Hur, S. Shin, and I. G. Jang, "Lightweight design of a bulk trailer using topology optimization", Trans. Korean Soc. Automot. Eng., Vol. 25, No. 5, pp. 548-554, 2017. https://doi.org/10.7467/KSAE.2017.25.5.548
  9. C. J. Lee and J. K. Lee, "Pressure signal-based instantaneous exhaust estimation of a bulk trailer by using a recurrent neural network", J. Inst. Control. Robot. Syst., Vol. 29, No. 4, pp. 360-365, 2023. https://doi.org/10.5302/J.ICROS.2023.23.0005
  10. J. S. Choi and J. K. Lee, "Recurrent neural network for nine-axis IMU-based orientation estimation: 3D orientation estimation performance in disturbed conditions", J. Inst. Control. Robot. Syst., Vol. 28, No. 12, pp. 1216-1223, 2022. https://doi.org/10.5302/J.ICROS.2022.22.0127
  11. D. Weber, C. Guhmann, and T. Seel, "RIANN-a robust neural network outperforms attitude estimation filters", AI, Vol. 2, No. 3, pp. 444-463, 2021. https://doi.org/10.3390/ai2030028
  12. R. Velo, P. Lopez, and F. Maseda, "Wind speed estimation using multilayer perceptron", Energy Convers. Manag., Vol. 81, pp. 1-9, 2014. https://doi.org/10.1016/j.enconman.2014.02.017
  13. E. Dorschky, M. Nitschke, C. F. Martindale, A. J. Van den Bogert, A. D. Koelewijn, and B. M. Eskofier, "CNN-based estimation of sagittal plane walking and running biomechanics from measured and simulated inertial sensor data", Front. Bioeng. Biotechnol., Vol. 8, 604(1)-604(14), 2020. https://doi.org/10.3389/fbioe.2020.00001
  14. M. Mundt, W. R. Johnson, W. Potthast, B. Markert, A. Mian, and J. Alderson, "A comparison of three neural network approaches for estimating joint angles and moments from inertial measurement units", Sens., Vol. 21, No. 13, pp. 1-14, 2021. https://doi.org/10.3390/s21134535