Worsted Process Intelligent Decision and Its Application

摘要

The selection of raw materials is one of the most important steps in textile process planning, which still depends on the expert's knowledge and experience. However, with traditional techniques, a mass of computation has to be repeated and the optimization of process parameters is also getting more and more difficult. Recently, Case-based reasoning (CBR) and artificial neural networks (ANN) are all fast emerging artificial intelligence (AI) techniques. This study presents a novel intelligent decision model (IDM) simulating how domain experts routinely solve the problems in worsted process, by integral application of CBR and ANN techniques. Among them, from rich existing process database, CBR is able to retrieve and recommend the similar process case as a process template; then, by means of modification on these parameters in the existing cases, ANN model is used to predict the yarn quality and make the best process decision. The basic concept, model architecture, experiments and methods are presented in this paper, respectively. An applied case with IDM is given to demonstrate that the best process decision can be made and important process parameters such as for raw material optimized.