Intelligent design methods for smart materials

Abstract

The design process of modern smart materials often require the use of complex system models. These models cannot be derived easily due to the complex knowledge that describe the process. In some cases, model parameters can be gained using neural networks, but these systems allow only a one-way simulation from input values to learned output values. If evaluation in the other direction is needed, these models allow no direct evaluation. This task can be solved using modern techniques like evolutionary algorithms and fuzzy logic. The use of such a combination allows evaluation of the learned simulation models in the direction from output to the input. An example can be given from the field of screw rotor design.