Predicting shrinkage of knitted fabrics using ANFIS.

Abstract

The project used ANFIS to predict the shrinkage of weft knitted fabrics comprising of cotton only and blend with polyester. GSM, stitch length, courses per inch and wares per inch were used as input parameters and shrinkage as the output for the model. Fabrics were produced using a circular knitting machine at Southern Range Nyanza Limited in Jinja, Uganda. Tests were carried out in the laboratories on the fabric samples to obtain the data. The data obtained was then used to build the ANFIS model. This model was tested and validated. The ANFIS model was successfully modeled to predict the shrinkage of knitted fabrics with the R-square of 0.9683, 0.9692 and 0.0013 for single jersey, rib and interlock respectively. The developed model was used to study the relationship between the inputs and the outputs and conclusion, recommendation made.