한국생산제조학회 학술지 영문 홈페이지

Current Issue

Journal of the Korean Society of Manufacturing Technology Engineers - Vol. 29 , No. 2

[ Best Paper of This Month ]
Journal of the Korean Society of Manufacturing Technology Engineers - Vol. 29, No. 2, pp.83-88
Abbreviation: J. Korean Soc. Manuf. Technol. Eng.
ISSN: 2508-5107 (Online)
Print publication date 15 Apr 2020
Received 16 Mar 2020 Revised 26 Mar 2020 Accepted 27 Mar 2020
DOI: https://doi.org/10.7735/ksmte.2020.29.2.83

Random Forest 방법을 적용한 초저유량 하이드로싸이클론 설계 및 성능예측
김창원a ; 서영진b, *

Design and Performance Prediction of Ultra-low Flow Hydrocyclone Using the Random Forest Method
Changwon Kima ; Youngjin Seob, *
aDepartment of Medical Assistant Robot, Korea Institute of Machinery and Materials
bDepartment of Mechanical Engineering, Kumoh National Institute of Technology
Correspondence to : *Tel.: +82-54-478-7302 E-mail address: yjseo@kumoh.ac.kr (Youngjin Seo).


Abstract

A hydrocyclone is a particle separation device. Due to their simple shapes and real-time particle separation functions, hydrocyclones are used in several industrial sites. However, the design of a hydrocyclone through numerical analysis takes prolonged time. In this study, a machine learning method is utilized to reduce the hydrocyclone design time. By using a random forest-based learning algorithm, the following three tasks were accomplished: particle separation efficiency was predicted under given design parameters; design parameters were extracted for a given bid size and the corresponding separation efficiency; finally, an extrapolation-based separation efficiency was investigated. The performance of the proposed learning algorithm-based prediction is demonstrated by comparing the results with numerical analysis data.


Keywords: Hydro cyclone, Numerical analysis, Machine learning, Random forest, Design parameter prediction

Acknowledgments

본 연구는 금오공과대학교 교수연구년제에 의하여 연구된 실적물입니다.


References
1. Khalde, C. M., Samad, A., Sangwai, J. S., 2019, Computational and Experimental Study of Sand Entrapment in a Hydrocyclone During Desanding Operations in Oil Fields: Consequences for Leakage and Separation Efficiency, SPE Production & Operations, 34 520-535.
2. Medronho, R. A., Schuetze, J., Deckwer, W. D., 2005, Numerical Simulation of Hydrocyclones for Cell Separation, Latin American Applied Research, 35 1-8.
3. Zhang, C., Wei, D., Cui, B., Li, T., Luo, N., 2017, Effects of Curvature Radius on Separation Behaviors of the Hydrocyclone with a Tangent-circle Inlet, Powder Technology, 305 156-165.
4. Vega-Garcia, D., Brito-Parada, P. R., Cilliers, J. J., 2018, Optimising Small Hydrocyclone Design Using 3D Printing and CFD Simulations, Chemical Engineering Journal, 350 653-659.
5. Rokach, L., Maimon, O., 2005, Decision Trees, In Data Mining and Knowledge Discovery Handbook Springer, Boston, MA.
6. Müller, A. C., Guido, S., 2016, Introduction to Machine Learning with Python: A Guide for Data Scientists, O’Reilly Media, Inc., Sebastopol, CA.

Changwon Kim

Ph.D. Principal researcher in Korea Institute of Machinery and Materials.His research interest includes intelligent control, autonomous vehicle control and application of artificial intelligence.

E-mail: cwkim@kimm.re.kr


Youngjin Seo

Ph.D. Associate Professor, Kumoh National Institute of Technology.His research interest includes aerosol dynamics and thermal-fluid mechanics.

E-mail: yjseo@kumoh.ac.kr