Portable Instruments Based on NIR Sensors and Multivariate Statistical Methods for a Semiautomatic Quality Control of Textiles

Near-infrared (NIR) spectroscopy is a widely used technique for determining the composition of textile fibers. This paper analyzes possibility using low-cost portable NIR sensors based on InGaAs PIN photodiode array detectors to acquire spectra samples. The are then processed by applying sequential application multivariate statistical methods (principal component analysis, canonical variate and k-nearest neighbor classifier) classify samples their composition. tries solve real problem faced knitwear manufacturer, which arose because different pieces same garment were made with “identical” acrylic yarns from two suppliers. sweaters had 50% acrylic, 45% wool, 5% viscose. occurred after garments dyed, where shades observed due origins yarns. challenging real-world reasons. First, there need differentiate between origins, experts say cannot be visually distinguished before dyed. Second, measurements in field rather than controlled laboratory sophisticated expensive benchtop spectrometers. experimental results obtained achieved classification accuracy 95%, slightly lower 100% high-performance spectrometer. presented this show that combined appropriate can effectively on-site quality control.