Grey soft-sensing modeling of oxygen content in electric power plant flue gas based on ASMO algorithm

Measuring oxygen content in flue gas timely and accurate is the assurance of the high combustion efficiency in power plant. This paper presents a Adaptive Sequential Minimal Optimization (ASMO) algorithm combined with selection parameter algorithm based on Support Vector Machine (SVM) and Sequential Minimal Optimization (SMO) algorithm. It build the grey soft-sensing model for oxygen content in flue gas of the electric power plant, does quadric screening for auxiliary variable using gray relationship analysis. The results of the simulation in different load show that the model is efficient and the method can excellent reduce the modeling time and provide the excellent soft-sensing accuracy.