This study focuses on structural optimization of the orthotropic sandwich cementitious composite systems. In order to develop a sandwich panel with high structural performance, design optimization techniques must be utilized to achieve full composite action as well as light weight, and high thermal insulation. This study involves both linear and nonlinear finite element analyses and parametric optimization. The verification and calibration of the numerical models will be based on the experimental results of numerous full-scale tests that were performed on two types of commercially produced sandwich panels under different loading scenarios at University of California Irvine.

In order to minimize the number of design variables required for producing an optimum sandwich panel, the Taguchi statistical method for quality control is utilized. In this method, statistically planned experiments (or numerical simulation runs) are used to identify the settings of the sandwich panel design parameters that result in optimum design.

Additionally, the Genetic Algorithm (GA) is used as an alternative approach for optimization, in order to evaluate the optimum design and build further confidence in our optimum design. GA combines Darwin's principle of survival of the fittest and a structured information exchange using randomized crossover operators to evolve an optimum design for the cementitious sandwich panel.

Among the different initial parameters to be evaluated in the study are: (i) shear connectors’ geometry, volume fraction, and distribution; (ii) The thickness of exterior cementitious face sheets; (iii) The size and geometry of the exterior face sheets steel reinforcement details.

Ultimately, the proposed optimization method reduced the Cost of Material of CSP by the by almost 48% using GA. In the same time, alternative design for CSP have been proposed where the optimization process increased the Thermal Resistance of the CSP by 40% compare to the conventional models currently available in the market while meeting the design Criteria’s based on the ACI Code. Pareto-optimal front and Pareto-optimal solutions have been identified. Correlation between the design variables of CSP is verified and design recommendation have been proposed for CSP manufacturers and structural designers.