ENHANCING TEXTILE QUALITY CONTROL WITH IOT SENSORS: A CASE STUDY OF AUTOMATED DEFECT DETECTION

Abstract

The traditional approach to textile quality control, predominantly reliant on manual inspection, is fraught with precision, speed, and reliability challenges. This case study explores the deployment of an Internet of Things (IoT) based system, incorporating sophisticated image processing and machine learning techniques, aimed at automating fabric defect detection in a mid-sized textile manufacturing setting. The study reveals a notable enhancement in the accuracy of defect detection and considerable improvements in inspection speed and operational efficiency. Implementing this IoT system resulted in a marked reduction in manual labor requirements and provided a compelling cost-benefit ratio, underscoring the system's financial viability. Furthermore, the case study details significant operational benefits, such as a 94.25% accuracy in defect detection and a reduction in inspection time from 10.78 to 2.47 minutes per unit. These outcomes affirm the transformative potential of IoT technologies in refining textile quality control processes, advocating for a shift towards more sustainable, quality-focused, and efficient manufacturing paradigms.