METHOD FOR DIAGNOSING AIRCRAFT ON-BOARD EQUIPMENT COMPLEX BASED ON MACHINE LEARNING Russian patent published in 2023 - IPC G06F11/00 B64F5/00 G06N20/00 G05B23/02 

FIELD: computer technology.

SUBSTANCE: method for diagnosing a complex of on-board equipment of aircraft based on machine learning, containing stages at which the collection and preparation of initial data is carried out, the transmitted information data included in the composition is determined, a neural network filter based on multilayer perceptrons is used, the method of reducing labelled data samples is used, creation of machine learning models K-means, SOM and DBSCAN, assignment of model training parameters, training of models on data according to the criteria for obtaining one cluster that characterizes the good state of each information-converting element, transmission of address data in real time to trained models, implementation of the majority principle of generating an integral signal of the technical condition of each channel of the information-converting element at the output using the two-out-of-three method, displaying the corresponding serviceability/failure messages and recording the information into the standard on-board automated control system of the aircraft.

EFFECT: increasing the accuracy of diagnostics of an industrial facility in terms of identifying pre-failure conditions.

1 cl, 7 dwg