基于SVM理论的涤纶织物分散染料上染率模型研究  

Research on Modeling of Dye-Uptake Rate for Disperse Dyes on Polyester Fibers Based on SVM

作　　者：巫静[1] 田彦杰[2] 汪澜[1] 林俊雄[2] 

机构地区：[1]浙江理工大学先进纺织材料与制备技术教育部重点实验室,杭州310018 [2]浙江理工大学机械与自动控制学院,杭州310018

出　　处：《浙江理工大学学报（自然科学版）》2013年第1期16-20,共5页Journal of Zhejiang Sci-Tech University(Natural Sciences)

基　　金：国家自然科学基金(61074154)

摘　　要：以分散红FB对涤纶织物染色为例,利用在解决小样本、非线性及高维模式识别中表现出许多特有优点的支持向量机(SVM)理论,建立了涤纶织物分散染料染色工艺因素—上染率多因素模型。并通过实验进行验证,其结果表明:实验值与模型预测值的相关系数达到了0.9778,误差均在3%以内,说明该数学模型具有较高的精确度,能较准确地反映分散染料对涤纶织物的实际上染情况,并可预测染色结果。This paper takes the dyeing of polyester fabric at high temperature and pressure with Dis perse Red FB for example, uses support vector machine （SVM） theory which shows many special advanta- ges in solving small sample nonlinear and high dimensional pattern recognition as well as establishes the mathematical model of the relationship between dyeing process factors and dye-uptake rate. The experi- mental result shows that the correlation coefficient between predictive values and actual values reaches up to O, 977 8 and the errors are under 3%, which shows that the mathematical model has high accuracy and it can exactly reflect the dye-uptake rate in the dyeing process and meet the actual requirements of forecasting the dyeing results.

关 键 词：涤纶织物 分散染料 上染率 支持向量机 多因素模型 

分 类 号：TS190.9[轻工技术与工程—纺织化学与染整工程]