At present,traditional image processing methods for identifying the density of knitted fabrics with different organizational structures faced problems such as poor adaptability and low accuracy.A method based on improved deep residual neural network model was proposed to detect the density of knitted fabrics.Firstly,a collection system for fabric images was established,and a fabric image data set was constructed.Secondly,all convolutional layers with a stride of 2 were replaced by SPD convolution layers to reduce the loss of fine-grained information.DWR module was added to the residual layer to enhance the network's ability to capture local and global features.Finally,the SmoothLoss function was introduced to improve the accuracy of detection while accelerating convergence.The experimental results showed that the method had an error of MAPE value less than 2%in detecting the density of various fabrics,and had stronger adaptability to different types.
为改善基于织物的柔性可穿戴压力传感器在使用时的灵敏度、可靠性和可持续性,采用直写工艺设计和制作纳米银线叉指电极,并将其作为底电极;采用浸泡工艺制作纳米银线导电织物,将其作为压阻层.将两者组装成为压阻式柔性织物压力传感器,并测试相关性能.结果表明:施加不同的压力,压力传感织物的电流都是随着施加电压的增加而线性增加;压力传感织物具有较好的传感稳定性和重现性,对外力具有较好的响应性能和较高的灵敏度;柔性织物压力传感器在0.1 V的低电压下实现了出色的开关比,5g砝码压力下快速响应性能较好.认为:制备的柔性压力传感器在可穿戴控制器和运动检测中具有潜在应用价值.
为了解决土种绵羊毛、牦牛绒等特种动物纤维与山羊绒因外观形态非常相似导致人工识别困难,不能准确、高效测定山羊绒含量的问题,采用图像处理技术和人工智能技术,采集大量不同加工形式、不同颜色、不同混纺比例的毛绒样品图像,提取分析不同动物纤维的直径、鳞片密度、鳞片面积、表面光滑度等特征值,经过大量样品的训练和验证优化,建立定性定量模型,开发出定量分析智能软件和全自动智能纤维分析仪.经过对不同颜色、不同形态、不同混纺比例的羊毛羊绒纤维的实际检测验证,该系统的检测误差在5%以内.认为:基于人工智能技术的羊毛羊绒混纺产品定量分析方法准确性和重现性高,符合国家标准要求,且自动化程度较高.
为推动绿色、智能纺织检测分析技术的应用,综述了显微计数法在纺织品成分定性定量分析中的系列关键技术.介绍了短纤维样片制作方法及图像采集技术的研究进展,阐述了纤维横截面参数测定、纵向形貌参数测定、纤维着色及偏光颜色鉴别、原位溶解鉴别、原位熔融鉴别等纤维定性定量分析技术的进展,简要分析了智能检测实际应用现状.认为:显微计数法成分分析技术已初步实现自动化和智能化,未来还需解决标样的快速、高质量制备,纤维特征物化性能的挖掘提取,适用品种的扩大,定量分析模型准确性的提高,全系统的自动化、智能化等问题.
