基于LS-SVM棉针织物轧烘轧蒸染色工艺的预测模型

为优化活性染料对棉针织物的轧烘轧蒸染色工艺,基于最小二乘支持向量机(LS-SVM),以氯化钠质量浓度、碳酸钠质量浓度、烘干时间和汽蒸时间作为预测模型的输入变量,染色织物K/S值作为输出变量,建立了多因素模型并进行预测。结果表明,织物实验K/S值和模型预测值的相关系数高达0.99996,平均相对误差小于0.5%,说明该模型具有较高的精度,该建模方法可用于染色织物K/S值的预测,可以用于棉针织物轧烘轧蒸染色工艺的预测和优化。

Pad-dry-pad-steam Dyeing Prediction Model of Cotton Knitting Fabric Based on LS-SVM

In order to optimize the pad-dry-pad-steam dyeing process with reactive dyes for cotton knitting fabrics,a multi-factor model based on least squares support vector machine(LS-SVM)was built with sodium chloride concentration,sodium carbonate concentration,drying time and steaming time as input variables and K/S value of dyed fabrics as output variable,and prediction was carried out with it.The results show that the correlation coefficient between the experimental K/S value and the predicted values of the model is up to 0.99996 with a mean relative error less than 0.5%,which indicates that the model is of high precision.The modeling method can be applied to predict K/S value of dyed fabric and to predict and optimize of pad-dry-pad-steam dyeing process for cotton knitted fabric.