Aero-engine fault diagnosis method based on 5G edge calculation and deep learning

Abstract

The invention relates to an aero-engine fault diagnosis method based on 5G edge calculation and deep learning. The aero-engine fault diagnosis method comprises the following steps: data acquisition, preprocessing and storage are performed based on a 5G novel cloud edge network architecture; a machine learning module is constructed in the edge cloud, and historical data stored in the aero-engine fault database management system provides training samples for the machine learning module; and the aero-engine gear fault simulation platform and the aero-engine fault database management system perform intelligent self-management. The invention has the advantages that limited aero-engine fault data resources under a 5G emerging network architecture are utilized, calculation and storage resources are combined, the storage and transmission speed of mass operation data of the aero-engine can be increased, and a reliable basis is provided for aero-engine fault recognition; according to the invention, the convolutional neural network operation is directly carried out on the original one-dimensional vibration signal, the process is simple, rich signal processing expert experience is not needed, and the recognition effect is ideal.

Description

technical field [0001] The invention relates to the field of complex equipment fault diagnosis, in particular to the field of aero-engine fault diagnosis, and in particular to an aero-engine fault diagnosis method based on 5G edge computing and deep learning. Background technique [0002] Since the end of the 20th century, with the continuous development of 5G information technology, artificial neural networks have been increasingly used in the aerospace field due to their powerful parallel processing capabilities, nonlinear function approximation capabilities, and self-organization, self-learning, and self-adaptation characteristics. It has become one of the key means of fault diagnosis of aviation aircraft at this stage. [0003] As the most important power component of an aircraft, aero-engines are prone to mechanical damage to their internal parts after a long period of use due to their complex mechanical structure and harsh working environment, which will greatly reduce...

AI Technical Summary

Problems solved by technology

[0003] As the most important power component of an aero-engine, due to its complex mechanical structure and harsh working environment, its internal parts are prone to mechanical damage after a long period of use, which will greatly reduce its working performance. For example, its rotating mechanism Shafting parts (such as gears, bearings, etc.), under the failure of surface wear and other problems, it is easy to cause huge vibration and noise of engine components, reduce operating efficiency, and seriously cause damage to the entire unit, resulting in huge economic losses

Failure to accurately detect the occurrence of faults in real time will have a huge hidden danger to the safety and efficiency of aerial operations

Images