Analytical Redundancy of Variable Cycle Engine Based on Proper Net considering Multiple Input Variables and the Whole Engine’s Degradation

In this paper, Proper net is proposed to construct variable cycle engine’s analytical redundancy, when all control variables and environmental change simultaneously, also accompanied with the whole degradation. another word, solve a multivariable, strongly nonlinear, dynamic, time-varying problem. order make topological structure of physically explainable, net’s designed according physical relationship between variables, by which means redundancy based on achieves higher accuracy less calculation time. Experiments were compared performance net, seven convolutional neural network structures, five shallow learning methods. Results demonstrate that under condition average relative error than 1.5%, most accurate least time-consuming one, proves not only effectiveness but feasibility structures’ design method relationship.