Building a Rule Set for the Fiber-to-Yarn Production Process by Means of Soft Computing Techniques

An important aspect of the spinning process is the ability to predict the spinnability of a yam and its resulting strength based on the fiber quality and machine settings. Currently available fiber-to-yarn models are limited to the so-called "black box" approach, gener ating an output (spinnability) without containing physical, interpretable information about the process itself. This paper presents a method to predict the spinnability and strength of a yam with a set of IF-THEN rules. The rule set is automatically generated using the available data by means of a new learning classifier system called a fuzzy efficiency-based classifier system (FECS), which enhances the original learning classifier algorithm of Goldberg [5] by defining several rule efficiencies and introducing them into the learning strategy of the system. Furthermore, FECS allows the introduction of continuous (fiber and yarn) parameters, which broaden the application fields considerably in contrast to discrete parameters alone. To this end, the generated rules are expanded to represent fuzzy classes with corresponding membership degrees toward each fiber-to-yarn data sample. Rule efficiencies and the reward mechanism are modified to account for the membership degree of each data sample. The paper demonstrates that the resulting prediction accuracy is good and, more importantly, also delivers additional qualitative information about the fiber-to- yarn process behavior. The generated rule set allows almost 100% acceptable classifica tion of yarn strength in three classes. The methodologies described in this paper are conveniently classified as "soft computing."