Slewing bearing state evaluation method based on multi-feature parameter fusion and FCM-HMM

Abstract

The invention provides a slewing bearing state evaluation method based on multi-feature parameter fusion and FCM-HMM, and the method comprises the following steps: carrying out preprocessing on a multi-physical signal, and carrying out noise reduction on an original signal by employing enhanced local mean decomposition; extracting multi-domain characteristics of a time domain, a frequency domain and a time-frequency domain of the signal; in order to avoid interference of feature redundancy or overlapping on a subsequent evaluation process, providing comprehensive evaluation indexes to screen superior features; constructing a multi-physical signal health index based on an equidistant mapping algorithm to make the performance degradation trend of the slewing bearing effectively represented; and in combination with a fuzzy C mean value and a hidden Markov model, identifying the degradation state transfer process of the slewing bearing, and determining an early fault point and a failure early warning point of the slewing bearing. According to the method, model verification is carried out by adopting the full-life acceleration test data of the slewing bearing, and the degradation state of the slewing bearing is effectively divided.

Description

technical field [0001] The invention relates to the field of parameter evaluation, in particular to a slewing bearing state evaluation method based on multi-feature parameter fusion and FCM-HMM. Background technique [0002] As the core component of rotating machinery, slewing bearings are widely used in various engineering practice fields, and their operational reliability directly affects the health of mechanical equipment. It is of great engineering significance to study methods that can accurately evaluate the life state of slewing bearings, provide guidance for active operation and maintenance, and effectively reduce economic and safety problems caused by slewing bearing failures or failures. Relying on the rapid development of artificial intelligence technology, the data-driven method does not need to rely on the damage mechanism of the slewing bearing, and the use of reliable data-driven modeling has become the mainstream method for scholars' research. For mechanical...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the characteristics of complex actual working conditions and weak acquisition signals of slewing bearings, the present invention proposes an FCM-HMM modeling strategy in combination with the existing problems in life state assessment of slewing bearings to efficiently identify the progressive degradation process during the operation of slewing bearings

Images