Mechanical fault identification method for subspace embedding feature distribution alignment under different working conditions

Abstract

The invention relates to a mechanical fault identification method for subspace embedding feature distribution alignment under different working conditions. The method comprises the following steps: firstly, aligning a source domain feature with a target domain feature in a target domain subspace by utilizing a related alignment method so as to prevent domain offset; then, directly predicting a pseudo label for a target domain in the spatial training base classifier, and quantitatively estimating respective weights of edge distribution and conditional distribution of two domains so as to adaptto the distribution difference between a source domain and the target domain; and finally, transmitting the learning rules of the two steps through a structural risk minimization framework, constructing a kernel function to establish a classifier, and performing iterative updating to obtain a coefficient matrix of a final framework to complete fault diagnosis. Quantitative estimation of respectiveweights of two-domain edge distribution and conditional distribution is of great significance in cross-domain mechanical fault diagnosis, and feasibility and effectiveness of the method are proved through multi-class composite fault diagnosis examples. The method is suitable for the fields of state monitoring, fault diagnosis and the like of mechanical equipment.

Description

technical field [0001] The invention belongs to the technical field of mechanical detection, and relates to a method for identifying mechanical faults under different working conditions in which subspace embedded feature distributions are aligned; Background technique [0002] As rotating machinery becomes larger and more complex, the probability of compound failures also increases. In practical applications, the operating conditions of rotating machinery vary greatly. When a composite fault occurs, multiple fault features often interfere and couple with each other, which brings great challenges to its composite fault diagnosis. Especially under different working conditions, changes in working parameters such as rotating machine speed and load lead to obvious non-stationarity in vibration signals, making it difficult to effectively extract fault features. In recent years, transfer learning has been widely used in the field of fault diagnosis under different working conditio...

AI Technical Summary

Problems solved by technology

Existing methods can only set a fixed value, or manually adjust the value of μ (such as: Balanced Distribution Adaptation, BDA algorithm), the selection of the value of different data needs to be manually selected after cross-validation, which cannot satisfy the adaptive dynamic adjustment

Images