Artificial neural network-supported selection of materials in ecodesign

Abstract

At the current rate of development in the industry, protecting the global environment is a priority. One of the ways to prevent environmental degradation is the manufacturing of recyclable products which can be disassembled and their materials and components processed for reuse. Recyclability of products can be taken into account as early as at the design stage. Appropriate selection of materials, connections and disassembly methods can facilitate and simplify recycling. This paper looks at an original method of material selection at the design stage, which takes into consideration recyclability of materials. An expert system based on artificial neural networks is presented. Analyses of input data for material selection have been conducted, the training file and neural network models have been developed, and the models have been assessed. Research has proven that artificial neural networks are suitable for supporting the selection of materials in ecodesign.