ABSTRACT

Neural networks algorithms are among the most popular data mining and machine learning techniques used today. As computers become faster, the neural net methodology is replacing many traditional tools in the field of knowledge discovery and some related fields. Neural networks tools are now used by many project engineers because - unlike most competing algorithms - the neural networks extrapolation does not require the mathematical model. We can perform the neural networks prediction without knowing what are the formulas, or laws. In this work we will use data mining technologies to strength the power of the preparation of the database and "neural networks" to extract "hidden" information from the 2001 Uster Statistics and textile spinning database. The goal of this study is to show how it is important the application of the data mining techniques namely neural networks in the optimization of combed yarn processing. The neural networks analysis will be used to develop non-linear predictive models that would better explain the relationships between the yarn specifications, than the classical statistical methods.