Neural network technologies in hardware-in-the-loop simulation: principles of gas turbine digital twin development

Abstract

The principle of gas turbine digital twin development,  the creation of a mathematical model of a gas turbine engine based on the recurrent neural network and its application in complex hardware-in-the-loop modeling for tuning automatic control, condition-monitoring and diagnostic systems, is considered. The technique of creation a neural network model of the complex technical object and the features of its integration in the hardware-in-the-loop test-bed are described. The results of modelling and hardware-in-the-loop simulation of aircraft engine parameters are presented. The accuracy and adequacy of the constructed model is analyzed. It is shown that the development of such methodologies solves the problem of analysis and synthesis of control systems, their functional optimization and reliability improvement on a completely different technological level.