Composite fault feature extraction method for gear system, and fault test device

Abstract

The invention relates to a composite fault feature extraction method for a gear system, and a fault test device, and belongs to the field of mechanical equipment fault diagnosis. A gear system vibration signal f in a time domain is acquired through an acceleration sensor arranged on the surface of a gear box body, and an adaptive optimization-based variable mode decomposition method is used to decompose the acquired gear system vibration signal f; and envelope power spectrum analysis is performed on all sub-signals obtained after decomposition, all the sub-signals are converted from the time domain to a frequency domain, and a frequency distribution condition of all the sub-signals on an envelope power spectrum is obtained, so that the extraction of fault features is realized. The defect that an existing VMD method is unlikely to determine optimal parameters is overcome; the composite fault features of the gear system can be more effectively extracted; the economic cost and the time cost of a test can be greatly reduced; and an alternative test condition is provided for fault diagnosis of the gear system under the condition that the industrial field actual measurement is not conveniently carried out.

Description

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine

Login to View More

AI Technical Summary

Benefits of technology

This patented technology allows for efficient identification of complex systems with potential failures caused due to external factors like temperature or load changes without requiring extensive labor-intensive effort manually selecting optimal values during testing. It uses an ensemble learning approach called ABC to learn how different variables affect each other's behavior when subjected to varying environmental conditions. By analyzing this data, we aim to extract important characteristic patterns related to these interactions and identify any possible failure modes within them. Overall, our technical effect lies at improving the accuracy and efficiency of identifying complicated mechanical structures while reducing their complexity.

Problems solved by technology

This technical problem addressed in this patented text relates to the development of efficient testing tools for gear train failings due to various factors like component defects and environmental impact caused by external environments during normal operations. Current solutions require manual adjustment and evaluation before selecting suitable models, leading to errors and reduced efficiency.

Images