Convolutional Neural Network을 이용한 액화 수소 밸브 설계 변수의 영향 예측
Prediction of the Effect on Liquid Hydrogen Valve Design Parameter using Convolution Neural Network
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Liquefied hydrogen is attracting attention as an energy source of the future due to its hydrogen storage rate and low risk. However, the disadvantage is that the unit price is high due to technical difficulties in production, transportation, and storage. This study was conducted to improve the design accuracy and development period of needle valves, which are important parts with a wide technical application range among liquefied hydrogen equipment. Since the needle valve must discharge an appropriate flow rate of the liquefied fluid, it is important to determine the needle valve design parameters suitable for the target flow rate. Computational Fluid Dynamics and Artificial Neural Network technology used to determine the design variables of fluid flow were applied to improve the setting and analysis time of the parameter. In addition, procedures and methods for applying the design parameter of needle valves to Convolutional Neural Networks were presented. The procedure and appropriate conditions for selecting parameters and functional conditions of the Convolutional Neural Network were presented, and the accuracy of predicting the flow coefficient according to the design parameter was secured 95%. It is judged that this method can be applied to other structures and machines.
Abstract
Liquefied hydrogen is attracting attention as an energy source of the future due to its hydrogen storage rate and low risk. However, the disadvantage is that the unit price is high due to technical difficulties in production, transportation, and storage. This study was conducted to improve the design accuracy and development period of needle valves, which are important parts with a wide technical application range among liquefied hydrogen equipment. Since the needle valve must discharge an appropriate flow rate of the liquefied fluid, it is important to determine the needle valve design parameters suitable for the target flow rate. Computational Fluid Dynamics and Artificial Neural Network technology used to determine the design variables of fluid flow were applied to improve the setting and analysis time of the parameter. In addition, procedures and methods for applying the design parameter of needle valves to Convolutional Neural Networks were presented. The procedure and appropriate conditions for selecting parameters and functional conditions of the Convolutional Neural Network were presented, and the accuracy of predicting the flow coefficient according to the design parameter was secured 95%. It is judged that this method can be applied to other structures and machines.
참고문헌 (14)
- J. W. Lee, "Performance Analysis Study for Stability of Butterfly Valve", Journal of korean society of mechanical technology, 23(4), pp.650~655 (2021)
- J. W. Lee, "A Study on the Numerical Analysis of the Pilot Valve of Gas Regulating Valve for LNG Fuel Propulsion Ships", Journal of korean society of mechanical technology, 25(5), pp.828~834 (2023)
- J. G. Kim, "A Study on Structural Analysis of Ball Valve for LNG Carrier", Journal of Korean Society of Mechanical Technology, 9(4), pp.1~7 (2007)[DOI]
- S. W. Kim, "Flow Characteristics of Cryogenic Butterfly Valve for LNG Carrier(Part 2 : Flow Characteristics under Cryogenic Condition)", Journal of fluid machinery and systems, 11(2), pp.20~28 (2008)
- J. H. Yoon, "Optimizations of Design Parameters of a EPPR Valve Solenoid using Artificial Neural Network", KSFC conference, pp.7~12 (2016), The Korea Fluid Power Systems Society
- S. J. kim, "Design of a Trim Part in the Safety Relief Valve by using Taguchi Method", KSPEC conference, pp.267~268 (2009)
- "KS B 2101 Test procedures for flow coefficient valves", 3~4 (2003)
- T. W. An, "A Study on the Characteristics of Flow in the Metal Touch Ball Valve according to the Opening degree", KSME Conference, pp.593~596 (2007), The Korean Society of Mechanical Engineers
- F. R. Menter, "Ten Years of Industrial Experience with the SST Turbulence Model", Journal of Turbulence, Heat and Mass Transfer, 4, pp.625~632 (2003)
- I. Goodfellow, "Deep Learning", pp.321~361 (2017), MIT Press
- Z. Yuan, "Vibrationbased damage detection of rail fastener clip using convolutional neural network Experiment and simulation", Journal of Eng. Fail. Anal, 119 (2021)
- J. H. Kang, "Detection of Overload by Convolutional Neural Network", 23(1), pp.83~90 (2024)[DOI]
- B. M. Yu, "A Study on Fault Classification for Condition-Based Maintenance of Auxiliary Pump in Ship’s Engine Systems Using HHT and CNN", Journal of applied reliability, 23(4), pp.366~374 (2023)[DOI]
- H. Kim, "Stacked Autoencoder Based Malware Featxire Refinement Technology-Research", Journal of the Korea Institute of Information Security & Cryptology, 30(4), pp.593~603 (2020)[DOI]