Khairy Elsayed

Robust parameter design optimization using Kriging, RBF and RBFNN with gradient-based and evolutionary optimization techniques

Abstract The dual response surface methodology is one of the most commonly used approaches in robust parameter design to simultaneously optimize the mean value and keep the variance minimum. The commonly used meta-model is the quadratic polynomial regression. For highly nonlinear input/output relationship, the accuracy of the fitted model is limited. Many researchers recommended to use more complicated surrogate models. In this study, three surrogate models will replace the second order polynomial regression, namely, ordinary Kriging, radial basis function approximation (RBF) and radial basis function artificial neural network (RBFNN). The results show that the three surrogate model present superior accuracy in comparison with the quadratic polynomial regression. The mean squared error (MSE) approach is widely used to link the mean and variance in one cost function. In this study, a new approach has been proposed using multi-objective optimization. The new approach has two main advantages over the classical method. First, the conflicting nature of the two objectives can be efficiently handled. Second, the decision maker will have a set of Pareto-front design points to select from.

Multi-objective geometry optimization of a gas cyclone using triple-fidelity co-kriging surrogate models

Cyclone separators are widely used in a variety of industrial applications. A low-mass loading gas cyclone is characterized by two performance parameters, namely the Euler and Stokes numbers. These parameters are highly sensitive to the geometrical design parameters defining the cyclone. Optimizing the cyclone geometry therefore is a complex problem. Testing a large number of cyclone geometries is impractical due to time constraints. Experimental data and even computational fluid dynamics simulations are time-consuming to perform, with a single simulation or experiment taking several weeks. Simpler analytical models are therefore often used to expedite the design process. However, this comes at the cost of model accuracy. Existing techniques used for cyclone shape optimization in literature do not take multiple fidelities into account. This work combines cheap-to-evaluate well-known mathematical models of cyclones, available data from computational fluid dynamics simulations and experimental data to build a triple-fidelity recursive co-Kriging model. This model can be used as a surrogate with a multi-objective optimization algorithm to identify a Pareto set of a finite number of solutions. The proposed scheme is applied to optimize the cyclone geometry, parametrized by seven design variables.

Analysis and Optimisation of Cyclone Separators Geometry Using RANS and LES Methodologies

The flow field pattern and gas cyclone performance have been investigated using both RANS and LES methodologies. The solid phase has been simulated using the one-way coupling approach. Both the RSM model and LES can be used efficiently to simulate the main features flow field pattern and estimate the performance. However, when looking at the flow details, LES can more accurately capture the unsteady flow phenomena of the highly swirling flow. Two different optimisation techniques have been applied (namely, the Nelder-Mead and the genetic algorithms) to obtain the cyclone geometry for minimum pressure drop. Two sources of data for the objective function have been used, mathematical models and experimental data. Starting from a Stairmand design an improved cyclone geometry is found using seven geometrical design variables. A CFD comparison between the original design and the new design has been performed. The simulations confirm the superior performance of the new design.

Multi-Objective Surrogate Based Optimization of Gas Cyclones Using Support Vector Machines and CFD Simulations

In order to accurately predict the complex nonlinear relationships between the cyclone performance parameters (The Euler and Stokes numbers) and the four significant geometrical dimensions (the inlet section height and width, the vortex finder diameter and the cyclone total height), the support vector machines approach has been used. Two support vector regression surrogates (SVR) have been trained and tested by CFD datasets. The result demonstrates that SVR can offer an alternative and powerful approach to model the performance parameters. The SVR model parameters have been optimized to obtain the most accurate results from the cross validation steps. SVR (with optimized parameters) can offer an alternative and powerful approach to model the performance parameters better than Kriging. SVR surrogates have been employed to study the effect of the four geometrical parameters on the cyclone performance. The genetic algorithms optimization technique has been applied to obtain a new geometrical ratio for minimum Euler number and for minimum Euler and Stokes numbers. New cyclones over-perform the standard Stairmand design performance. Pareto optimal solutions have been obtained and a new correlation between the Euler and Stokes numbers is fitted.