Evolutionary Algorithms for Function Model Synthesis
Gill, Amaninder Singh
MetadataShow full item record
Function modelling plays an essential role in the systematic design process. Designers are trained in the academia trained on function models, yet the acceptance of function models in the industry remains sparse. A possible reason is that there is a lack of computational support for synthesizing function models. The research presented in this dissertation aims to fill that gap. A conceptual proof of function model synthesis using a Genetic Algorithm (GA) is initially presented. Thereafter a priori rules to evaluate function model have been developed. These rules do not rely on a designer conveying designer intent to the algorithm, which was the case in the first proof of concept implementation. This meant that unique function models can be synthesized using this framework. Also, function models of differing sizes and differing vocabulary sizes can also be constructed. Finally, this approach has been extended to synthesize function models by decomposing a black box.