Rotating machinery health assessment method for deep self-encoding network

Abstract

The invention discloses a rotary mechanical health assessment method for a deep self-encoding network. The method comprises the steps of (1) vibration signal acquisition, (2) original feature extraction, (3) feature dimension reduction by using a deep auto-encoder (DAE) network, (4) feature selection, (5) health indicator construction by using an unsupervised SOM algorithm, and (6) health indicator evaluation by using a fusion evaluation criterion based on a genetic algorithm. According to the method, the advantages of the powerful feature extraction ability of deep learning are combined, deepself-encoding and minimum quantization error methods are combined. In addition, an evaluation criterion based on one metric often has a bias problem, and the invention provides the fusion evaluationcriterion based on the genetic algorithm. According to the method, the health state of rotary machinery can be accurately evaluated, the method can be widely applied to the health assessment of rotarymachinery in the fields of chemical engineering, metallurgy, electric power, aviation and the like, the dynamic process of performance degradation of these components can be accurately described, anda remaining life also can be predicted.

Description

technical field [0001] The invention relates to a rotating machinery health assessment technology, in particular to a rotating machinery health assessment method based on a deep self-encoding network. Background technique [0002] Due to the development of advanced sensor and computer technology, a large amount of condition monitoring data has been accumulated in industrial production, and data-driven methods have been widely used in bearing prediction because they are able to use condition monitoring data to quantify the degradation process instead of establishing a Accurate system models are not readily available. [0003] Generally, a data-driven prediction method usually consists of the following three steps: data acquisition, health indicator construction, and remaining life prediction. Health indicators attempt to identify and quantify historical and ongoing degradation processes by extracting characteristic information from acquired data. Therefore, the quality of t...

AI Technical Summary

Problems solved by technology

However, PCA is a linear dimension reduction method, and the bearing degradation process is a nonlinear degradation process, so it cannot be used to accurately evaluate the health indicators of rotating machinery

In addition, the health indicators constructed by the combination of PCA and time-frequency domain feature extraction methods need to be improved in terms of monotonicity, trend, and robustness

Images