Application of SVM Based on Improved Grid Search in Quantitative Analysis of CO2 Gas

According to the difficult in selecting parameter of SVM when modeling on the gas quantitative analysis,and existing methods need long time,SVM optimized by improved grid search method was proposed to built an infrared spectrum quantitative analysis of gas.According to this method,the spectrum data of CO2 is optimized.The kernel function leads SVM and calculate the concentration.By using improved grid search, quantitatively analyzed 18 different concentrations of CO2 in the range between 1%~25%. The experiment results show that this method gets c=1,g=1,cvMSE=0.00413.And the prediction error is less than 4%, in line with national standards for exhaust emissions.