Prediction of shockwave location in supersonic nozzle separation using self-organizing map classification and artificial neural network modeling

Niknam, Pouriya H.; Mokhtarani, Babak; Mortaheb, Hamid Reza

doi:10.1016/j.jngse.2016.07.061

Cited by 26 publications

(9 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to its adaptability and applicability, several types of research have applied the topological network to practical applications. 28,43 However, since these models insert new nodes permanently into the network, they have a potential to cause catastrophic forgetting. This trade-off is called the plasticity-stability dilemma.…”

Section: Literature Reviewmentioning

confidence: 99%

A Kernel Bayesian Adaptive Resonance Theory with A Topological Structure

Masuyama

Loo

Wermter

2019

Int. J. Neur. Syst.

View full text Add to dashboard Cite

This paper attempts to solve the typical problems of self-organizing growing network models, i.e. (a) an influence of the order of input data on the self-organizing ability, (b) an instability to high-dimensional data and an excessive sensitivity to noise, and (c) an expensive computational cost by integrating Kernel Bayes Rule (KBR) and Correntropy-Induced Metric (CIM) into Adaptive Resonance Theory (ART) framework. KBR performs a covariance-free Bayesian computation which is able to maintain a fast and stable computation. CIM is a generalized similarity measurement which can maintain a high-noise reduction ability even in a high-dimensional space. In addition, a Growing Neural Gas (GNG)-based topology construction process is integrated into the ART framework to enhance its self-organizing ability. The simulation experiments with synthetic and real-world datasets show that the proposed model has an outstanding stable self-organizing ability for various test environments.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

A Kernel Bayesian Adaptive Resonance Theory with A Topological Structure

Masuyama

Loo

Wermter

2019

Int. J. Neur. Syst.

View full text Add to dashboard Cite

show abstract

“…The tangential component of velocity is created by the static vanes at the inlet and the subsequent centrifugal force is the main action that accomplishes the separation. In this way, the liquid droplets can settle on the wall of the nozzle to be physically removed downstream.…”

Section: Introductionmentioning

confidence: 99%

Numerical investigation of multiphase flow in supersonic separator considering inner body effect

Niknam

Fiaschi

Mortaheb

et al. 2019

Asia-Pacific J Chem Eng

Self Cite

View full text Add to dashboard Cite

This paper presents research on the supersonic nozzle geometry with particular emphasis on the effect of the internal body of the nozzle that largely affects the separation efficiency. A numerical investigation of the supersonic nozzle with an internal solid body, which forms an annular flow inside the convergent–divergent nozzle is carried out. The present study revealed different hydrodynamic behaviors of the nozzle, exploring different shapes of the inner body, and the computational fluid dynamic simulations of the supersonic nozzle is utilized to find out the best geometrical design. Utilizing a coupled pressure–velocity scheme with high order of discretization of the governing equation yielded to find the shockwave positions in different conditions. The turbulent behavior of the fluid in the shockwave zone is well discussed and the phase‐change phenomena for the natural gas application are studied considering both water condensation and hydrocarbon condensation simultaneously. Different nozzle configuration elucidates the physical mechanisms of the supersonic flow inside the nozzle. Shockwave position, swirling velocity stability, and mass flow capacity are investigated. The lower the inner body radius, the less the change of shockwave position in the gas is found. Also, the higher stability of swirling velocity magnitude is found for the convergent–divergent inner body, which brings enhanced physical phase separation.

show abstract

“…The phenomenon has been studied with various configurations such as ducts, wind tunnels, ramps, and vortex tubes . In our previous studies, the estimation of shock wave position, controlling the shock wave position in unsteady conditions of feed composition or feed pressure, and the effects of two‐phase conditions on supersonic nozzles have been reported.…”

Section: Introductionmentioning

confidence: 99%

Effects of fluid type and pressure order on performance of convergent–divergent nozzles: An efficiency model for supersonic separation

Niknam

Mortaheb

Mokhtarani

2018

Asia-Pacific J Chem Eng

Self Cite

View full text Add to dashboard Cite

A deep analysis on the hydrodynamics of convergent–divergent nozzles is performed by changing the working conditions and fluid type. The nozzle geometry lowers the temperature of the flowing fluid, which contributes to condensation and phase change. The focus of this paper is to evaluate the nozzle performance and cooling capacity in terms of temperature, pressure, and gas type in a fixed geometry of Sajben Laval nozzle. The analysis has been conducted via a 2‐dimensional turbulent computational fluid dynamics simulation for illustrating the behavior of the fluid. A criterion for the nozzle performance is provided by prediction of exact shock wave position. An investigation on 6 different gas types demonstrates that heat capacity and thermal conductivity are the most rolling fluid properties of the nozzle performance. Furthermore, it is found that the shock wave position is unchanged during alteration of fluid type or pressure scale. A new model is provided for prediction of convergent–divergent nozzle performance in the supersonic conditions for dehydration of natural gas as a well‐known industrial application of the nozzles. The model is developed by the genetic algorithm as a multivariable optimization method.

show abstract

Prediction of shockwave location in supersonic nozzle separation using self-organizing map classification and artificial neural network modeling

Cited by 26 publications

References 17 publications

A Kernel Bayesian Adaptive Resonance Theory with A Topological Structure

A Kernel Bayesian Adaptive Resonance Theory with A Topological Structure

Numerical investigation of multiphase flow in supersonic separator considering inner body effect

Effects of fluid type and pressure order on performance of convergent–divergent nozzles: An efficiency model for supersonic separation

Contact Info

Product

Resources

About