VARIABLE CYCLE ENGINE INTELLIGENT CONTROL METHOD BASED ON DYNAMIC NEURAL NETWORK

摘要

A variable cycle engine intelligent control method based on a dynamic neural network. By means of adding a structural adjustment algorithm based on a gray relational analysis method to a neural network training algorithm, adjusting the structure of a neural network, and constructing a dynamic neural network controller, intelligent control of a variable cycle engine is realized. By means of performing dynamic neural network training by means of a network structure adjustment algorithm based on a gray relational analysis method, and by constructing a variable cycle engine dynamic intelligent controller based on a dynamic neural network, the problem of coupling between nonlinear multi-variables caused by the increase in control variables of a variable cycle engine and the problem of a traditional control method excessively depending on model precision are effectively solved. Moreover, structurally dynamic adjustment can be performed during a neural network training process, such that the structure of a network is simpler, and the operating speed and the control precision thereof are improved.