Complex device fault diagnosis method and system

Abstract

The invention relates to a complex device fault diagnosis method and system. The method includes a sample processing step comprising selecting monitoring performance parameters of a complex device andacquiring state data of the monitoring performance parameters for pre-treatment so as to generate normal samples and fault samples; a feature extraction step comprising randomly selecting a part of normal samples from all the normal samples for training of an SDAE model and utilizing the trained SDAE model for feature extraction on the rest normal samples and all the fault samples so as to obtaina feature set; a classification and identification step comprising classifying features based on the feature set by using a support vector machine. According to the invention, fault diagnosis can beperformed in a real small sample condition of the complex device, and the fault identification accuracy and generalization of the method provided by the invention are distinctively superior to those of a support vector machine based fault diagnosis method. In a process of establishing a complex device state feature model, a method of designing an SDAE model hidden layer node number according to single DAE feature extraction capability is proposed.

Description

technical field [0001] The invention relates to the technical field of aero-engines, in particular to a complex equipment fault diagnosis method and system. Background technique [0002] With the development of equipment in the direction of complexity, intelligence, and integration, its working environment and operating conditions are becoming more and more complex, which leads to easy damage to various components, which seriously affects the working performance and even leads to various failures. Therefore, it is very necessary to carry out fault diagnosis on complex equipment. Specifically, to carry out fault diagnosis on complex equipment can quickly and accurately determine the location and severity of the fault, thereby reducing the turnaround time of the equipment, which is conducive to the safe operation of the equipment and improving the quality of the equipment. work efficiency. [0003] As the data collected by the complex equipment monitoring system is getting la...

AI Technical Summary

Problems solved by technology

[0007] The technical problem to be solved by the present invention is to propose a complex equipment fault diagnosis method and system based on deep learning and support vector machines for at least one of the above defects in the existing complex equipment fault diagnosis

Images