INNOVATIVE METHODS FOR AUTOMATED WARP YARN QUALITY CONTROL AND THEIR IMPACT ON WEAVING EFFICIENCY

Abstract

This study investigates the implementation of an integrated automated control system for warp yarn quality, combining computer vision and multi-sensor data fusion. Traditional manual inspection methods are prone to subjectivity and inefficiency, leading to undetected defects that cause yarn breaks and loom stoppages. The proposed system utilizes high-resolution line-scan cameras and tension sensors to continuously monitor yarn diameter, hairiness, and tension in real-time. A machine learning-based algorithm classifies defects and predicts potential breakage points. Experimental results demonstrate a 45% reduction in warp breaks and a 15% increase in overall equipment effectiveness (OEE) compared to conventional methods, highlighting the significant potential of automated systems for enhancing weaving productivity and product quality.