Journals / Isı Bilimi ve Tekniği Dergisi / 2015 / Cilt: 35 - Sayı: 2

KAPAK GÜDÜMLÜ KAVİTE AKIŞLARINDA ZAMANA BAĞLI DAVRANIŞIN YAPAY SİNİR AĞLARI TABANLI TAHMİNİ

ARTIFICIAL NEURAL NETWORK BASED PREDICTION OF TIME-DEPENDENT BEHAVIOR FOR LID-DRIVEN CAVITY FLOWS

Pages
1–18
Publication Date
2022-10-18
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

POD results show that when the stream function formation is used as a data ensemble, about 99% of the total energy content can be modeled by considering only the most energetic first four POD modes; whereas, this value remains at a range between 9095% for the x-direction velocity data ensemble.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:In this study, computational fluid dynamics (CFD) analyses of the two-dimensional, time-dependent liddriven cavity flows, for Reynolds numbers ranging from 100 to 10000, are performed by using an in-house developed CFD code.
📊
Key Findings & Data:The flow structure is further investigated with the application of a reduced order modeling technique, Proper Orthogonal Decomposition (POD), and the structures present in the flow, are separated according to their frequency (energy) content.
💡
Conclusion & Impact:POD results show that when the stream function formation is used as a data ensemble, about 99% of the total energy content can be modeled by considering only the most energetic first four POD modes; whereas, this value remains at a range between 9095% for the x-direction velocity data ensemble.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Domain Parameters

Abstract

In this study, computational fluid dynamics (CFD) analyses of the two-dimensional, time-dependent liddriven cavity flows, for Reynolds numbers ranging from 100 to 10000, are performed by using an in-house developed CFD code. The unsteady behavior of the flow is triggered using a sinusoidal lid velocity profile. The flow structure is further investigated with the application of a reduced order modeling technique, Proper Orthogonal Decomposition (POD), and the structures present in the flow, are separated according to their frequency (energy) content. POD results show that when the stream function formation is used as a data ensemble, about 99% of the total energy content can be modeled by considering only the most energetic first four POD modes; whereas, this value remains at a range between 9095% for the x-direction velocity data ensemble. What is more, an Artificial Neural Network (ANN) based approach is developed to predict mode amplitudes for flows with different Reynolds numbers. Once enough information is obtained with the help of CFD of few flow cases, the ANN integrated approach presented herein helps to predict what is happening in the flow for different flow cases without requiring further CFD simulations, which are not practical in real-time flow control applications.

Özet

Bu çalışmada, Reynolds sayısının 100 ile 10000 arasında değiştiği, iki boyutlu ve zamana bağlı kapak güdümlü kavite akışlarının Hesaplamalı Akışkanlar Dinamiği (HAD) çalışmaları özgün olarak geliştirilen HAD kodlarının uygulanmasıyla incelenmiştir. Akışın zamana bağımlı davranışı sinüssel hız profili uygulanarak tetiklenmiştir. Akış alanında gözlemlenen yapılar düşük boyutlu modelleme tekniği olan Dikgen Ayrıştırma Yöntemi (DAY) kullanılarak incelenmiş olup, bu yapılar frekans derecelerine (akış alanının bütününü ifade etmeye yönelik olan katkılarına, enerji içeriklerine) göre ayrıştırılmıştır. DAY sonuçlarına göre, akım fonksiyonu veri grubu olarak kullanıldığında, toplam enerji içeriğinin %99a yakın kısmı sadece en yüksek enerji içeriğine sahip ilk dört DAY kipi kullanılarak ifade edilebilmektedir. Buna karşılık, x-yönündeki hız veri grubu kullanıldığında en yüksek enerji içeriğine sahip ilk dört kipin kullanılmasıyla toplam enerji içeriğinin % 9095lik bir kısmı ifade edilebilmektedir. Ayrıca, çalışmada değişik Reynolds sayılarının uygulandığı durumlar için Yapay Sinir Ağı (YSA) uygulaması yapılarak kip genlikleri de tahmin edilmiştir. HAD kullanılarak belirli akış durumları için yeterince bilgi toplandıktan sonra, YSA ile bütünleştirilen yaklaşım sayesinde farklı akış koşulları için gerçek zamanlı kontrol uygulamaları için pratik olmayan HAD analizlerine gerek duyulmadan akış alanında neler olduğuna ilişkin bilgileri tahmin etmek mümkün olmaktadır.

🔖

Cite This Article

PAKSOY, A., ARADAG, S. (2022). KAPAK GÜDÜMLÜ KAVİTE AKIŞLARINDA ZAMANA BAĞLI DAVRANIŞIN YAPAY SİNİR AĞLARI TABANLI TAHMİNİ. Isı Bilimi ve Tekniği Dergisi, Cilt: 35 - Sayı: 2, 1–18. https://ajindex.com/articles/542532

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (9)

  1. Ahadian S., Mizuseki H. and Kawazoe Y., 2009, An Efficient Tool for Modeling and Predicting Fluid Flow in Nanochannels, Journal of Chemical Physics, 131. Ahlman D., Söderlund F., Jackson J., Kurdila A. and Shyy W., 2002, Proper Orthogonal Decomposition for Time-Dependent Lid-Driven Cavity Flows, Numerical Heat Transfer, Part B: Fundamentals, 42, 285-306.
  2. Apacoglu B., Paksoy A. and Aradag S., 2011, CFD Analysis and Reduced Order Modeling of Uncontrolled and Controlled Laminar Flow over a Circular Cylinder, Engineering Applications of Computational Fluid Mechanics, 5, 67-82.
  3. Aubry N., Holmes P., Lumley J. L. and Stone E., 1988, The Dynamics of Coherent Structures in the Wall Region of a Turbulent Boundary Layer, Journal of Fluid Mechanics, 192, 115-173. Bishop C. M., 1994, Neural Networks and Their Applications, Review Article, Review of Scientific Instruments, 65, 1803-1832.
  4. Cao Y., Zhu J., Luo Z. and Navon I., 2006, Reduced Order Modeling of the Upper Tropical Pacific Ocean Model Using Proper Orthogonal Decomposition, Computer and Mathematics with Applications, 52, 1373-1386.
  5. Cazemier W., Verstappen R. W. C. P. and Veldman A. E. P., 1998, Proper Orthogonal Decomposition and Low-Dimensional Models for Driven Cavity Flows, Physics of Fluids, 10 (7), 1685-1699. Connell R. and Kulasiri D., 2005, Modeling Velocity Structures in Turbulent Floods Using Proper Orthogonal Decomposition, International Congress on Modeling and Simulation, Melbourne, Australia, 1237-1242.
  6. Deane A. E., Kevrekidis I. G., Karniadakis G. E. and Orszag S. A., 1991, Low-Dimensional Models for Complex Geometry Flows: Application to Grooved Channels and Circular Cylinders, Physics of Fluids, 3, 2337-2354.
  7. Emang D., Shitan M., Ghani A. N. A. and Noor K. M., 2010, Forecasting with Univariate Time Series Models: A Case of Export Demand for Peninsular Malaysia’s Moulding and Chipboard, Journal of Sustainable Development, 3, 157-161.
  8. Erturk E., Corke T. C. and Gokcol C., 2005, Numerical Solutions of 2-D Steady Incompressible Driven Cavity Flow at High Reynolds Numbers, International Journal for Numerical Methods in Fluids, 45, 747-774.
  9. Fitzpatrick K., Feng Y., Lind R., Kurdila A. J. and Mikolaitis D. W., 2005, Flow Control in a Driven Cavity Incorporating Excitation Phase Differential, Journal of Guidance, Control, and Dynamics, 28, 63-70. Gracia M. M., 2010, Reduced Models to Calculate Stationary Solutions for the Lid-Driven Cavity Problem, M.S. Thesis, Polytechnic University of Catalonia, Barcel