Research On Modeling And Predictive Control Of Micro Gas Turbine

With the rapid development of China's economy,the pressure of energy consumption on the environment is becoming more and more serious.As a method of synthetic cascade utilization of energy,Combined Cooling,Heating and Power System can not only improve the efficiency of energy utilization,but also be conducive to environmental protection.As the main power equipment of CCHP system,micro gas turbine has the advantages of high efficiency,friendly environment and short start-up cycle.However,the micro gas turbine has a strong non-linearity,and its working process is more complex.In order to understand its dynamic characteristics,it is very important to study the modeling,simulation and control of micro gas turbine.In this paper,the mechanism of micro gas turbine is modeled,and dynamic simulation is carried out.Intelligent optimization algorithm is introduced into the identification process of control model.The traditional predictive control method is improved,and the improved predictive control algorithm is applied to the micro gas turbine.The simulation results show that the improvement effect is remarkable.Particle Swarm Optimization(PSO)is improved and applied to the identification of control model of micro gas turbine.Because the traditional particle swarm optimization algorithm is easy to fall into the local optimum in the search process,the simulated annealing algorithm is introduced into the particle swarm optimization algorithm,and the learning factor is improved accordingly.The test function experiments show that the improved particle swarm optimization algorithm has less search error and better probability jump ability,and can effectively prevent the particle swarm optimization from falling into local optimum too early.The mechanism model of micro gas turbine is built on the platform of MATALAB/Simulink,and the dynamic data of the unit is simulated dynamically.The more accurate control model is identified by the improved particle swarm optimization algorithm.The traditional predictive control method is improved accordingly.In the rolling optimization part,the improved particle swarm optimization algorithm with better optimization effect is used as the rolling optimization algorithm of the improved predictive control method.In the prediction model part,because the micro gas turbine has a certain degree of non-linearity,it is very important to find a non-linear prediction model.BP neural network has a strong ability of complex non-linear mapping.In this paper,BP neural network is used as the prediction model.The improved control algorithm is applied to the control simulation of micro gas turbine model.Compared with the traditional PID control algorithm,the improved control algorithm has more accurate control effect.