Journal of Drive and Control (드라이브 ㆍ 컨트롤)

The Korean Society for Fluid Power and Construction Equipment (유공압건설기계학회)
권호 표지
DOI QR코드

DOI QR Code

An Experimental Study on the Estimation Flow-rate of Venturi Pump Using LightGBM

LightGBM을 이용한 수력 펌프 유량 추정의 실험적 연구

  • Jin Beom Jeong (Korea Construction Equipment Technology Institute) ;
  • Jihwan Lee (Korea Construction Equipment Technology Institute) ;
  • Myeongcheol Kang (Korea Construction Equipment Technology Institute)
  • 정진범 ;
  • 이지환 ;
  • 강명철
  • Received : 2023.11.15
  • Accepted : 2023.11.28
  • Published : 2023.12.01
Download PDF
⟨ Previous Next ⟩

Abstract

In disaster situations, to facilitate rapid drainage, electric underwater pumps are installed manually. This poses a high risk of electric shock accidents due to a short circuit, and a lot of time is required for hose connection and installation of electrical devices. To solve these problems, a Venturi pump using the venturi effect without external power is used. However, Venturi pumps that operate without external power make it difficult to install flow sensors such as electric devices; consequently, it is difficult to check the real-time flow rate. This paper proposes a flow estimation logic to replace the function of the flow sensor for the venturi pump . To develop the flow estimation logic, the flow characteristics of the venturi pump, according to the operating conditions, were checked. After that, the relationship with the flow rate of the venturi pump was defined using a pressure sensor corresponding to a low-cost sensor. Finally, an analysis of the estimation error was performed using the developed flow estimation logic.

Keywords

Acknowledgement

이 논문은 행정안전부 자연재난 정책연계형 기술개발사업의 지원을 받아 수행된 연구임. (RS-2022-ND629013)

References

  1. J. C. Botts and R. D. Wolford, "Water immersion testing of form-wound coil insulation," 1968 8th Electrical Insulation Conference, pp.132-135, 1968 
  2. C. Yung and J. Bryan, "Disaster recovery: What to do after the storm," 2014 IEEE Petroleum and Chemical Industry Technical Conference, pp.473-480, 2014 
  3. D. H. Lee and S. J. Bae, "A Study on Optimal Operation Conditions for an Electronic Device Alignment System by Using Design of Experiments", Journal of Korean Society for Quality Management, Vol.43, No.3, pp.453-466, 2015  https://doi.org/10.7469/JKSQM.2015.43.3.453
  4. S. K. Gwak and S. H. Hwang, "Validation of Semantic Segmentation Dataset for Autonomous Driving", Journal of Drive and Control, Vol.419, No.4, pp.104-109, 2022 
  5. Y. H. Choi and C. H. Lee, "Thermal Flow Analysis of an Engine Room using a Porous Media Model for Imitating Flow Rate Reduction at Outlet of Industrial Machines", Journal of Drive and Control, Vol.19, No.1, pp.62-68, 2022  https://doi.org/10.7839/KSFC.2022.19.1.062
  6. M. W. Kahng, "Some Remarks on Standardized Regression Coefficient", Journal of The Korean Data Analysis Society, Vol.19, No.1, pp.151-158, 2017  https://doi.org/10.37727/jkdas.2017.19.1.151
  7. Davide Chicco and Giuseppe Jurman G, "The Coefficient of Determination R-squared is More Informative than SMAPE, MAE, MAPE, MSE and RMSE in Regression Analysis Evaluation", PeerJ Computer Science, 2010 
  8. B. G. Senong and D. H Han, "Predicting the spray uniformity of pest control drone using multi-layer perceptron", Journal of Drive and Control, Vol.20, No,3, pp.25-34, 2023  https://doi.org/10.7839/KSFC.2023.20.3.025
  9. Guolin Ke and Tie-Yan Liu, "LightGBM: a highly efficient gradient boosting decision tree", Advances in Neural Information Processing Systems, pp.3146-3154, 2017. 
  10. D. H. Jang, "Applications of python package for statistical engineering", The Korean Journal of Applied Statistics, Vol.34, No.4, pp.633-658, 2021  https://doi.org/10.5351/KJAS.2021.34.4.633
  11. J. B. Jeong and K. S .Lee, "Analysis Outrigger Reaction Force for Roll Over Prediction of Aerial Ladder Vehicle", KSFC Conference, pp.119~121, 2021 
  12. J. H. Jung and K. Kim, "Fault Diagnosis Method for Excavator Hydraulic Axial Piston Pumps", Journal of Drive and Control, Vol.18, No.4, pp.98-103, 2021