Modeling of Power Plant Superheated Steam Temperature Based on Least Squares Support Vector Machines

Aiming at the strong nonlinearity and large time-varying characteristics in controlling of super-heater temperature in plant, the method of LS-SVMs(Least Squares Support Vector Machines) based on radial basis function are used to model. Under the condition of modeling approximating to performance, the sparse modeling is gotten by the pruning algorithm. The merits of the algorithm are conforming to the least structural risk in training process and hardly leading to over-fitting. The simulation of a superheating system, in one supercritical concurrent 600MW boiler in one power plant, is taken. The result shows that the controlling system can be adapt to the variation of the object characteristic well with strong nonlinearity and large time-varying characteristics rapidly.