Optimal design of triangular side orifice using multi-objective optimization NSGA-II.

Area of Science:

• Fluid dynamics
• Engineering applications
• Computational modeling

Background:

• Triangular orifices are crucial for fluid metering and flow control in various industries.
• Existing empirical equations and computational fluid dynamics (CFD) have limitations in accuracy and computational cost.
• Artificial neural networks (ANNs) present a promising, efficient alternative for predicting orifice discharge.

Purpose of the Study:

• To develop and assess artificial neural network (ANN) models for predicting discharge through triangle orifices.
• To predict downstream velocity in the main channel using ANN models.
• To introduce a novel hybrid multi-objective optimization model (NSGA-II) for design parameter optimization.

Main Methods:

• Development of artificial neural network (ANN) models to predict discharge and velocity.
• Evaluation of ANN model performance against existing research.
• Implementation of the NSGA-II algorithm for multi-objective optimization.

Main Results:

• ANN models demonstrated effectiveness in predicting discharge and downstream velocity.
• The study validated the performance of the developed ANN models.
• The NSGA-II model successfully identified optimal design parameters for maximizing discharge and velocity.

Conclusions:

• ANNs provide a reliable and efficient method for predicting discharge through triangle orifices.
• The hybrid NSGA-II model offers a powerful tool for optimizing triangular orifice designs.
• This research enhances the accuracy and efficiency of fluid flow predictions in engineering applications.