AI Powered Anomaly Detection and IoT Automation for Improving Textile Manufacturing Quality Management and Productivity Levels

Abstract

The textile industry is embracing Industry 4.0 through automation and the Internet of Things (IoT) to enhance productivity, minimize operational costs, and improve quality control. Traditional manufacturing processes remain inefficient due to labour-intensive practices and quality inconsistencies caused by human intervention. IoT-driven real-time monitoring enables predictive maintenance, data-driven decision-making, and sustainable manufacturing, ensuring greater efficiency and consistency in textile production. This research focuses on integrating an IoT-enabled smart sensor network for real-time process monitoring and quality control across spinning, weaving, dyeing, and finishing stages for various fabric types, including cotton, polyester, wool, silk, rayon, and denim. Data collection was conducted from textile hubs in Tirupur, Coimbatore, Surat, Ludhiana, and Bhilwara, covering 50 textile units, with sensor data recorded over six months. The IoT framework utilizes RFID tags, optical sensors, humidity sensors, and vibration monitoring to detect fabric defects, yarn tension, and moisture levels. Data is processed via edge computing for real-time analysis, while cloud analytics enables predictive insights. An AI-powered anomaly detection system identifies irregularities in fabric texture, dye consistency, and fiber strength, reducing defects and enhancing production yield. Automated control loops adjust machine parameters in real time, ensuring consistent product quality. The research introduces a digital twin model to simulate manufacturing conditions, facilitating predictive maintenance and reducing material wastage. Evaluation results indicate a 32% reduction in defects, a 28% increase in first-pass yield, and a 25% decrease in operational downtime. By leveraging IoT-based automation, this study enhances efficiency, reduces wastage, and accelerates Industry 4.0 adoption in textiles, paving the way for smart, sustainable factories.