Research Of Boiler Superheated Steam Temperature Control Based On Neural Network Predictive Control

The superheated steam temperature control is one of the most important tasks inautomatic control system in thermal power plants. The superheated steam temperature directlyaffects the safe and economic running of thermal power plants. While the traditional PIDalgorithm is mainly used in the process. And its effect is bad. So research of boilersuperheated steam temperature control is very significanceThis article analyzes the static and dynamic characteristics of the boiler superheatedsteam temperature system. And compares the advantages and disadvantages of double-loopcontrol with a differentiation and cascade control based on the PID. Analyzes the cause ofthat the traditional predictive control is difficult to apply in the boiler superheated steamtemperature system. So proposed a neural network predictive control algorithm that useneural network as prediction model on the basis of the traditional predictive control. It takesfull advantage of the capabilities of the neural network in nonlinear mapping approximationand the actual optimal control of receding-horizon in predictive control. And with an onlinereal-time correction capability. In addition, this article using a maximum error judgmentalgorithm in the link of online correction to reduces the computation. Quantitative analyzesthe main parameters of the neural network predictive controller and determine the effect fromeach parameter to controller. Finally, use the neural network predictive control algorithm intothe boiler superheated steam temperature control system, and compare the controlperformance of the neural network predictive control and traditional PID in attemperatingwater disturbance, flue gas disturbance and load disturbance. Simulate in Matlab, andachieved satisfactory resultsSimulation shows that the neural network predictive control is feasible in the superheatedsteam temperature control system. If it can be tested and verify in engineering practice,it will be widely used in this kind of process control.