Abstract
Neural networks have gained prominence as a viable means of expanding a finite data set of experimental measurements in recent times to improve the understanding of any complex phenomenon. In this study, a generalized feed forward neural network is used to reconstruct experimentally obtained turbulence data of a turbulent free jet. The turbulence variables investigated are the axial and radial velocities, normal and shear stress, and higher order statistical moments in addition to turbulence budgets. The study revealed that the optimum Generalized Feed-forward Neural Network should be constructed with one hidden layer having 18 neurons which utilize a hyperbolic tangent activation function. The network is trained using the Levenberg-Marquardt learning algorithm. Validation studies are conducted to assess the merits of the proposed Neural Network. This investigation showed that artificial neural networks are suitable for predicting the characteristics of a turbulent free jet.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: International Review of Mechanical Engineering (IREME)
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
