SELF-ORGANIZING NEURAL NETS - A NEW APPROACH TO QUALITY IN TEXTILES

Until recently, textile quality assessment has been very difficult and mostly done by human experts. In the search for a more objective meth odology, neural network techniques can be an excellent alternative. Th e first part of our paper presents a general introduction to neural ne twork modeling techniques and focuses more extensively on the ''topolo gical mapping'' model. The second part applies those techniques to tex tile quality assessment. Two problem cases are assessed-carpet wear an d set marks. Both are objectively analyzed using self-organizing Kohon en neural networks. In both cases, the results are good and the system also indicates the objectivity of the human experts.