Method and system for identifying defects in fine wire based on eddy current detection

By introducing a dual-channel detection architecture and multi-factor fusion technology into the fine wire detector, combined with a convolutional neural network, the problem of insufficient accuracy of eddy current detection events in existing technologies is solved, and efficient and accurate identification and dynamic early warning of fine wire defects are achieved.

CN121878017BActive Publication Date: 2026-06-26SHANGHAI TFLOCK PRECISION FASTENER CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
SHANGHAI TFLOCK PRECISION FASTENER CO LTD
Filing Date
2026-03-18
Publication Date
2026-06-26

AI Technical Summary

Technical Problem

Existing wire detectors cannot integrate detection information from different dimensions when detecting defects with complex shapes, resulting in insufficient accuracy of eddy current detection events, especially low sensitivity to short-lived defects such as micro-cracks on the surface.

Method used

A method for identifying defects in fine wire based on eddy current detection is adopted. By determining a dual-channel detection architecture in the fine wire detector, the absolute coil channel and the differential coil channel are combined with multiple factors. By combining the synchronous detection of the absolute coil channel and the differential coil channel, transient pulse features and defect frequency response features are extracted and multi-factor fusion is performed. The feature map is then intelligently compared with a convolutional neural network to achieve dynamic early warning.

Benefits of technology

It improves the accuracy and robustness of eddy current detection events, can accurately distinguish between surface stains and actual structural defects, realizes the transition from qualitative detection to quantitative risk assessment, reduces reliance on human experience, and enhances the automation and response efficiency of maintenance decisions.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121878017B_ABST
    Figure CN121878017B_ABST
Patent Text Reader

Abstract

The application discloses a kind of based on eddy current detection fine wire defect identification method and system, the present application relates to the technical field of defect identification, according to the synchronous detection of absolute coil channel and differential coil channel and determine multiple fine wire detection data, multiple fine wire detection data are aligned, to extract transient pulse feature in time domain and extract defect frequency response feature in frequency domain, and according to transient pulse feature, defect frequency response feature carries out multi-factor fusion and determines eddy current detection event, improve the accuracy of eddy current detection event.According to the comparison of the characteristic map of each sub eddy current detection project and the preset standard characteristic map determines multiple defect characteristics;Based on the feature position of each defect feature, corresponding feature morphology and the structure form of fine wire determine the defect grade of each defect feature, and along the superposition of the defect grade of each defect feature determines dynamic early warning level, realizes the dynamic early warning of fine wire detector to fine wire.
Need to check novelty before this filing date? Find Prior Art