Early fault monitoring and diagnosis method and system for rolling bearing

Abstract

The invention discloses an early fault monitoring and diagnosis method for a rolling bearing. The problem of missed detection or delayed detection of early faults in the prior art is solved. The operation state of the rolling bearing can be monitored on line; and the early fault of the rolling bearing can be timely and accurately monitored. Concretely, the method comprises the following steps: acquiring a vibration signal when a bearing operates, dividing the acquired vibration signal into a plurality of signal segments by using a non-overlapping sliding window, and decomposing each signal segment by using a wavelet packet decomposition technology with adaptive time-frequency resolution to obtain wavelet packet coefficients of each segment in different frequency bands; and performing graphmodeling on each wavelet packet coefficient sequence by means of graph modeling capable of capturing data correlation to form a wavelet packet coefficient graph set, and performing fault monitoring and fault diagnosis according to graph modeling.

Description

technical field [0001] The invention belongs to the technical field of state monitoring and fault diagnosis in mechanical systems, in particular to a method and system for early fault monitoring and diagnosis of rolling bearings. Background technique [0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art. [0003] Early fault monitoring and diagnosis of rolling bearings is a hotspot in the field of industrial research, especially with the development of intelligent technology, the degree of automation of mechanical equipment is getting higher and higher, and rolling bearings are key components of mechanical equipment. Operational condition monitoring also puts forward higher requirements. The faults of rolling bearings in operation are relatively weak in the early stage, and the signals collected at this stage are weak signals. The inventors found that if the current commonly...

AI Technical Summary

Problems solved by technology

The faults of rolling bearings in operation are relatively weak in the early stage, and the signals collected at this stage are weak signals. The inventors found that if the current commonly used frequency domain monitoring technology is used to process the signals, the effective fault information will be The dilution of the entire frequency band leads to the missed detection of early faults, so that they are detected only when the rolling bearings have obvious faults, which may cause economic and property losses in serious cases; at the same time, in the fault diagnosis stage, it is necessary to accurately establish the dynamics of the bearing structure The structural parameters of the dynamic model need to be very accurate during the establishment process, otherwise the accuracy of the model establishment will be affected, and the models established by different bearings are also quite different, which is not conducive to the establishment of intelligent and automated systems; If the short-time Fourier change of the time-frequency method is used, the weak information of early faults is also affected by the time-frequency resolution, and the effective fault information will be weakened for a fixed time-frequency resolution, resulting in missed detection or delayed detection of early faults. failure, resulting in economic loss

Images