Aero-engine thrust estimation algorithm through adaptive RBF neural network

Abstract

The invention discloses an aero-engine thrust estimation algorithm through an adaptive RBF neural network. According to the algorithm, an improved particle swarm optimization algorithm is utilized tooptimize centers, width, connection weights and other neural network parameters of all nodes of the radial basis function (RBF) neural network, and meanwhile the network scale is optimized, so that the neural network is compacter under the condition of meeting a precision requirement. The algorithm can be used for medium and small-scale data regression and can be applied to estimation of thrust and other parameters in terms of aero-engine. Through the algorithm, the adaptive RBF neural network is provided based on the particle swarm optimization algorithm; in the improved particle swarm optimization algorithm, according to different network hidden layer node numbers, locally optimal solutions in the same number as types of the hidden layer node numbers are set; and the algorithm provides anew thought for aero-engine thrust estimation and is easy to understand, simple in parameter adjustment, easy to realize, high in applicability and capable of realizing high-precision thrust estimation.

Description

technical field [0001] The invention relates to a method for estimating thrust of an aeroengine, and belongs to the technical fields of data regression analysis, engine control, thrust control and estimation, and the like. Background technique [0002] In the design of the aircraft control system, the main purpose of controlling the aeroengine is to control its thrust, but the engine thrust is an unmeasurable quantity in flight. The estimation of unmeasurable performance parameters of aero-engines has always been a subject of much concern in the aviation field. The commonly used thrust estimation methods in traditional control include direct thrust estimation method and indirect thrust estimation method. The direct thrust estimation method obtains the estimated thrust value of the engine directly from the measurable parameters of the engine through a certain algorithm, such as using a neural network to realize the direct estimation of the thrust. The indirect thrust estima...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the problem that the current aero-engine thrust estimation method is single and has limited precision, the present invention proposes a new method of thrust estimation, provides a new idea for aero-engine thrust estimation, and at the same time improves the accuracy of thrust estimation

Images