The Research Of Ultra-supercritical Unit Nonlinear Dynamic Modeling

With China's thermal power unit to develop large capacity, high parameter ultra-supercritical unit, the unit's strong nonlinear, strong uncertainty and strong coupling characteristic are more apparent, it is difficult to build the unit's dynamic model. Based on the dynamic characteristics analysis of ultra-supercritical units, this paper presents a simulation study on modeling of a 1000MW ultra supercritical once-through boiler unit by BP neural network, Elman neural network and Fuzzy neural network respectively, and also compare with the linear model of the units. The simulation results show the validity.The main contributions of this dissertation are summarized as follows:1. On the basic of the dynamic characteristics analysis of ultra-supercritical unit, this paper simply ultra-supercritical unit to three inputs and three outputs nonlinear model. 2. In this dissertation, all the data used to model identifying and testing is sampled from the production field. This has pretty high engineering utility values.3.Based on the field data, many different neural networks are used to build three inputs and three outputs nonlinear model. It validates the efficiency of the neural networks in modeling the 1000MW ultra-supercritical unit QIN Junbo (Control Theory and Control Engineering)...