ISSN Online: 2688-7231
ISBN Online: 978-1-56700-524-0
Proceedings of the 26thNational and 4th International ISHMT-ASTFE Heat and Mass Transfer Conference December 17-20, 2021, IIT Madras, Chennai-600036, Tamil Nadu, India
Design Optimization of Ejectors Using ANN and GA
摘要
Ejectors are devices that are based on the principle
of momentum transfer. A primary fluid passes through a
nozzle that is usually of converging-diverging cross-section
so that the flow reaches supersonic velocity at the exit.
Consequently, a low-pressure region is created just outside
the nozzle exit. This pressure gradient, draws out the
secondary fluid, into the ejector through the annular space
− a phenomenon known as entrainment. This paper outlines
the design and optimisation of an ejector with R141b as
the working fluid. The governing equations that accurately
predict the behaviour of the working fluid, have been
solved using finite volume method after the discretization
of the flow domain, using ANSYS Fluent. A database has
been created by recording the variation of a dimensionless
quantifier - entrainment ratio over several CFD simulations
varying the input parameter values namely - mixing chamber
radius, primary nozzle throat and exit radii. It has then
been used to define a function that can precisely predict
the output for an unknown set of input parameters. This
has been achieved through the implementation of artificial
neural networks − a surrogate modelling technique. The
objective function thus obtained has been optimised with the
help of genetic algorithm - a nature-inspired optimisation
technique. The optimal design of the ejector for a set of
operating conditions has been acquired at the output of the
genetic algorithm.