A novel approach for modelling of an injector powered transonic wind tunnel

A mathematical model of an injector powered transonic wind tunnel is developed in this paper. The whole running process is divided into three stages and the model of each child processes is established respectively. The data applied to the parameter identification is obtained from the actual running process. The NARMAX model is adopted as the structure of model and the parameters including the order and sampling interval are identified by means of the false nearest neighbors algorithm and the mutual information algorithm accordingly. The non-linear mapping between the inputs and the outputs is completed by the BP neural network. The total pressure at stagnation and the static pressure at test section are calculated via the model and the Mach number can be obtained by the relationship between the pressure and Mach number. The simulation result shows that the mathematical model established by the above method has a better performance compared with modelling the whole process.