O 2 content in flue gas is a main factor that has great impacts on the safety and economical efficiency of boiler operation. Together with many other complicated factors. Building a model to predict O 2 content in flue gas is a good way to realize the normal operation of boiler. Using the data of boiler operation, a least square support vector machine (LSSVM) model of the boiler oxygen content property was developed based on gas oxygen characteristic. After that, combined with the particle swarm optimization algorithm (PSO), the O 2 content in flue gas of boiler was controlled. Simulation resu...