Against the problem that carbon content in boiler fly ash is difficult to measure accurately

a soft sensor method based on support vector regression was proposed.Taking the ultra supercritical unit in Datang Chaozhou Power Plant as the research object

a support vector regression based model predicting the carbon content in fly ash was established

and cross validation method was applied to optimize the penalty parameter Cand kernel function parameter gfor the model.Moreover

the model's accuracy and generalization capability were verified by using the test data and random data obtained under three unit load conditions.The simulation results show that the soft sensor model of the carbon content in fly ash has higher prediction accuracy and better generalization ability

which provides an effective way for measurement of the carbon content in boiler fly ash.