Abstract:Based on the computational fluid dynamics (CFD) method, a quenching tank with two agitator systems and two flow-equilibrating devices was selected to simulate flow distribution using Fluent software. A numerical example was used to testify the validity of the quenching tank model. In order to take tank parameters (agitation speed, position of directional flow baffle and coordinate position in quench zone) into account, an approach that combines the artificial neural network (ANN) with CFD method was developed to study the flow distribution in the quenching tank. The flow rate of the quenching medium shows a very good agreement between the ANN predicted results and the Fluent simulated data. Methods for the optimal design of the quenching tank can be used as technical support for industrial production.

Key words: A357 aluminum alloy; computational fluid dynamics; quenching tank; flow distribution; artificial neural network