Abstract
This chapter presents the scope of application of hybrid neuro-fuzzy inference systems for the prediction of yarn properties. The chapter begins with a brief introduction to artificial neural networks (ANNs) and fuzzy logic. This is followed by a description of adaptive neuro-fuzzy inference systems which amalgamates the advantages of both the ANN and fuzzy logic. Finally, application of an adaptive neuro-fuzzy system is demonstrated to predict the tenacity and unevenness of spun yarns using the cotton fibre properties as the input variables. The prediction accuracy of the hybrid neuro-fuzzy model is compared with those of the statistical regression model and virgin ANN models. The linguistic rules extracted by the neuro-fuzzy model give better understanding about the spinning process by revealing some important information about the role of input variables on yarn properties.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
