第1种方法，为了进一步验证各输入因子与输出因子间的线性相关性，提出了一

In the first method, in order to further verify the linear correlation between each input factor and output factor, a yarn quality prediction method combining grey correlation and linear regression is proposed. This method selects the influencing factors with larger coefficients as the input variables of the model according to the correlation coefficients of yarn quality indicators with key process factors and raw cotton quality factors, so as to improve the linear correlation between input variables and output variables Small errors in forecast data, improve the accuracy of forecast data.

The first method, in order to further verify the linear correlation between the input factors and the output factors, a method of yarn quality prediction that combines gray correlation with linear regression is proposed. Based on the correlation coefficient between each quality index of yarn and key process factors and raw cotton quality factors, this method selects the influencing factorwiths with large coefficients as the input variables of the model, so as to improve the linear correlation between the input variables and the output variables, reduce the error of the prediction data and improve the accuracy of the prediction data.

In the first method, in order to further verify the linear correlation between the input factors and the output factors, a yarn quality prediction method combining grey correlation and linear regression is proposed. According to the correlation coefficient of yarn quality index, key process factors and raw cotton quality factors, the influential factors with larger coefficient are selected as the input variables of the model, so as to improve the linear correlation between input variables and output variables, reduce the error of prediction data and improve the accuracy of prediction data.<br>