Search

Heat energy retention and dissipation have become key points of global smart textiles in recent years. This study describes the designing of silicon resin by using a sol–gel process, which acts as the modifying agent for siloxane substrate. The modifying agent was effectively blocked by silicon resin mixed with the ethylene or aluminum bond group, to control the molecular weight. Advanced polymer chromatography confirmed that the number average molecular weight (Mn) of silicon resin is 41,301 g mol−1, the weight average molecular weight (Mw) is 47,982 g mol−1, and the molecular weight distribution is 1.1617, which is relatively narrow. When the addition of vinyl groups is 5%, the silicone resin Mn decreases to 18,906 g mol−1 and Mw decreases to 28,641 g mol−1. When the addition of aluminum bond groups is 5%, the silicone resin Mn decreases to 17,497 g mol−1 and Mw decreases to 27,114 g mol−1. The result of thermogravimetric analysis shows that the pyrolysis temperature rises from 265.43°C to 266.17°C after the ethylene is added to the silicon resin, and the index of heat tolerance increases from 179.14°C to 191.38°C. After the addition of aluminum bond groups, the pyrolysis temperature rises from 265.43°C to 309.37°C, and the index of heat tolerance increases from 179.14°C to 193.09°C, meaning the silicone resin has higher thermal stability. [ABSTRACT FROM AUTHOR]

We introduce a real-time machine vision system we developed with the aim of detecting defects in functional textile fabrics with good precision at relatively fast detection speeds to assist in textile industry quality control. The system consists of image acquisition hardware and image processing software. The software we developed uses data preprocessing techniques to break down raw images to smaller suitable sizes. Filtering is employed to denoise and enhance some features. To generalize and multiply the data to create robustness, we use data augmentation, which is followed by labeling where the defects in the images are labeled and tagged. Lastly, we utilize YOLOv4 for localization where the system is trained with weights of a pretrained model. Our software is deployed with the hardware that we designed to implement the detection system. The designed system shows strong performance in defect detection with precision of 95.3 % , and recall and F 1 scores of 93.6 % and 94.4 % , respectively. The detection speed is relatively fast at 34 fps with a prediction speed of 21.4 ms. Our system can automatically locate functional textile fabric defects with high confidence in real time. [ABSTRACT FROM AUTHOR]

Image inspection by wavelet packets and a neural network classifier is presented for non-defect and six kinds of defects in knitted fabrics. The types of defect include a hole, set mark (coarse), dropped stitch, oil stain, streak, and tight end. In this study, wavelet packet decomposition of a sample image is carried out based on the best-basis wavelet packet tree with three resolution levels. The lowest-two entropy among all sub-band images and the standard deviation for the original image are selected as feature inputs of the neural network classifier. These textural features are shown in seven groups, which are separately distributed in the feature space. We gathered a total of 112 experimental samples, with 16 samples in each of the seven aforementioned categories. The results demonstrate that with the three features, 56 test samples are correctly inspected. However, the lack of one of the three features yields wrong classification of some samples. Therefore, the three features selected are definitely suitable for recognition of our knitted fabric defects and also are the smallest number of features required to give accurate inspection. [ABSTRACT FROM AUTHOR]