Modified Searchless Method for Identification of Helicopters Turboshaft Engines at Flight Modes Using Neural Networks
Serhii Vladov, Yurii Shmelov, Ruslan Yakovliev
Abstract
This work is devoted to the improvement of the automatic control system of helicopters turboshaft engines through the introduction of a block of signal adaptation of engine parameters into it using a modified method of searchless identification. The implementation of the proposed solutions is carried out using the NEWFF multilayer neural network, which made it possible to significantly reduce the maximum absolute error compared to the least squares method.
Topics & Concepts
Artificial neural networkComputer scienceIdentification (biology)Block (permutation group theory)Control engineeringSIGNAL (programming language)Control theory (sociology)EngineeringArtificial intelligenceControl (management)MathematicsBiologyGeometryProgramming languageBotanyTechnical Engine Diagnostics and MonitoringControl Systems and IdentificationAdvanced Control and Stabilization in Aerospace Systems