A motor rotating shaft surface multi-modal defect intelligent monitoring method and system

CN121899242BActive Publication Date: 2026-05-29NINGDE NORMAL UNIV +1
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
NINGDE NORMAL UNIV
Filing Date
2026-03-23
Publication Date
2026-05-29

AI Technical Summary

Technical Problem

Existing technologies struggle to effectively isolate fluctuations in the relative distance between the probe and the shaft surface, as well as electromagnetic noise interference, in motor shaft defect monitoring. This results in inaccurate signal processing, wasted resources and data redundancy in multi-sensor systems, difficulty in distinguishing between real defects and environmental interference, and a lack of quantitative defect level information.

Method used

By collecting magnetic field signals around the motor shaft, analyzing the amplitude and phase information of the magnetic induction intensity in the orthogonal directions, and combining wavelet threshold denoising and polynomial fitting compensation, the infrared thermal imaging or vibration monitoring mode is adaptively selected, and a feature decision matrix is ​​constructed to determine the defect type.

Benefits of technology

It improves the accuracy and response speed of defect identification, reduces system overhead, provides accurate defect level information, and reduces the false alarm rate.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121899242B_ABST
    Figure CN121899242B_ABST
Patent Text Reader

Abstract

The present application belongs to the technical field of intelligent monitoring of defects, and relates to a kind of motor rotating shaft surface multi-modal defect intelligent monitoring method and system.The present application acquires the magnetic field signal of motor rotating shaft, analyzes the amplitude and phase information of orthogonal direction magnetic induction intensity, extracts amplitude, phase and spatial characteristics after denoising and lift compensation processing;According to the phase characteristic, dynamically select the activated infrared thermal image or vibration monitoring mode, and extract the corresponding temperature field mutation area or frequency domain impact component;When detecting characteristic energy aggregation or closed ring gradient distribution, confirm the existence of defects, then map multi-dimensional characteristics to characteristic decision matrix, output defect quantization level after row and column consistency check.The present application solves the problems of signal distortion, multi-modal resource waste, high false alarm rate and lack of quantitative diagnosis in the prior art, realizes high signal-to-noise ratio feature extraction, monitoring resource adaptive scheduling, reduces false alarm rate, and provides accurate defect attribute level information.
Need to check novelty before this filing date? Find Prior Art