Engine fault prediction method

Abstract

The invention discloses an engine fault prediction method. The method comprises the following steps that effective measurement data of a plurality of sensors of an engine are obtained; the effective measurement data are subjected to normalization processing; the effective measurement data obtained after normalization processing are sliced, and a plurality of slice samples are formed; the multiple slice samples are sent into a deep nerve network to be subjected to feature extraction, and after feature extraction, the slice samples are connected to a fully-connected network; and according to output of the fully-connected network, classification is conducted through a softmax classifier, and the left service life of the engine is determined. According to the provided engine fault prediction method, the process is small, operation is easy, and the engine fault prediction method can be widely applied to various engines of aircraft.

Description

technical field [0001] The invention relates to the field of aerospace vehicles, in particular to an engine failure prediction method. Background technique [0002] The engine is the core component in an aircraft, but it is also one of the most prone to failure. Once the aircraft fails, it will adversely affect the entire mechanical equipment. Therefore, it is very necessary to dig out an accurate and efficient engine failure prediction method to ensure the normal operation of the aircraft. [0003] At present, there are many methods for engine fault prediction, which can be mainly divided into model-based methods, data-based methods, etc. The effects of these methods largely depend on the preprocessing ability and feature extraction ability of the collected real data. Because different engines and different operating conditions produce different signal characteristics, it is difficult to find a general engine fault prediction method, and some fault prediction methods prop...

AI Technical Summary

Problems solved by technology

Since different engines and different operating conditions produce different signal characteristics, it is difficult to find a general engine fault prediction method. Some fault prediction methods currently proposed have certain limited application ranges.

Images