Visual identification and trend prediction method and system for wrinkles of continuous strip-shaped material

By acquiring images and synchronously obtaining the working status of continuous strip materials, combined with preprocessing and time-series modeling, real-time identification and trend prediction of wrinkles in continuous strip materials are realized, solving the problems of dynamism and false alarms/missed alarms in existing technologies, and improving production efficiency and intelligence level.

CN121884008AActive Publication Date: 2026-04-17SHANGHAI INST OF CERAMIC CHEM & TECH CHINESE ACAD OF SCI
8 Cites 2 Cited by

Patent Information

Application Number
CN202610337707.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-03-19
Publication Date
2026-04-17
Estimated Expiration
2046-03-19

AI Technical Summary

Technical Problem

Existing technologies for detecting wrinkles in continuous strip materials suffer from several drawbacks, including difficulty in adapting to dynamic and time-varying conditions, high false alarm and false negative rates, lack of closed-loop adaptive optimization mechanisms, risks associated with parameter adjustment, and difficulty in meeting the challenges of different working conditions.

Method used

By collecting continuous image sequences and working condition vectors, preprocessing them, and inputting them into the wrinkle recognition model, a multi-dimensional wrinkle index vector is constructed. Combined with Kalman filtering and time series modeling, future trends are predicted, and the optimal parameter package is solved within the set of safety constraints to achieve closed-loop adaptive adjustment.

Benefits of technology

It achieves real-time and reliable identification of wrinkle defects and accurate prediction of their development trends, reduces false alarm and missed alarm rates, improves production line response speed, reduces manual intervention costs, and has self-learning capabilities to adapt to dynamic changes in different materials and equipment conditions.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention relates to a visual identification and trend prediction method and system for wrinkles of a continuous strip-shaped material, and the method comprises the steps: collecting a continuous image sequence of the surface of the continuous strip-shaped material, obtaining a standardized image frame, and synchronously obtaining a working condition state vector; inputting the standardized image frame into a wrinkle identification model, and outputting wrinkle region information, wrinkle category information and corresponding confidence; constructing a wrinkle index vector at the current moment according to the wrinkle region information, the wrinkle category information and the corresponding confidence coefficient; filtering and time sequence modeling are carried out on the wrinkle index vectors at the current and historical moments, and wrinkle index prediction values, trend labels and prediction uncertainty at multiple moments in the future are output; and constructing a future risk index and security constraint set according to the wrinkle index prediction value, the prediction uncertainty and the working condition state vector, solving an optimal parameter packet, and mapping the optimal parameter packet into an executable control instruction for output.
Need to check novelty before this filing date? Find Prior Art