METHOD FOR DIAGNOSING INFORMATION-CONVERTING ELEMENTS OF AIRCRAFT ON-BOARD EQUIPMENT BASED ON MACHINE LEARNING Russian patent published in 2023 - IPC G06N3/02 G06F11/00 G05B23/00 

FIELD: aircraft engineering.

SUBSTANCE: method is based on the use of Kohonen artificial neural networks in a neural network state classifier for solving issues of diagnosing information-converting elements of aircraft on-board equipment based on machine learning, as well as multilayer unidirectional artificial neural networks of direct propagation with a sigmoid activation function of neurons in the hidden layer, and a linear function activation of neurons in the output layer in the neural controller.

EFFECT: solution to the problem of on-board equipment diagnostics, which allows to identify equipment malfunctions.

1 cl, 5 dwg