棉是一种重要的天然纤维，如果能根据废旧纺织品的棉含量对其进行分类回收利用，可极大地减少对天然纤维资源的消耗。但目前废旧纺织品的回收主要采用人工分拣方式，这种方式效率低、成本高，难以满足对废旧纺织品进行大规模精细分拣、分级的需要。本文使用近红外光谱分析方法对废旧纺织品的棉含量进行判定，用基于主成分分析的支持向量机方法建立了废旧纺织品的近红外光谱定性分析模型，模型能将含棉和不含棉的两类废旧纺织品很好地分开。对于含棉的废旧纺织品，又用多模型方法建立了废旧纺织品棉含量的近红外光谱分析模型，模型具有较好的预测结果。综合使用上述两个模型，能较好地判定废旧纺织品的棉含量。这种新方法有望用于废旧纺织品某些其它天然纤维含量的快速判定。

Cotton is an important natural fiber.If waste textiles can be classified and recycled according to its cotton content,the consumption of natural fiber resources can be greatly reduced.However,the current recycling of waste textiles mainly uses manual sorting method.This method has low efficiency and high cost.It is difficult to meet the needs of large-scale fine sorting and grading of waste textiles.Near infrared spectra analysis method was used in this paper to determine the cotton content of waste textiles.By using the support vector machine method based on the principal component analysis,a qualitative analysis model of near infrared spectroscopy of waste textiles was established.The model can well separate the two types of waste textiles,cotton-containing and cotton-free.For the waste textile samples that contain cotton,a near infrared spectra analysis model of the cotton content of waste textiles was built using a multi-model method.The model has good prediction results.Using the above two models in combination,the cotton content of the waste textile samples can be better determined.This new method is expected to be used for rapid determination of some other natural fiber content in waste textiles.