A method for identifying the processing status during heat treatment

CN115994326BActive Publication Date: 2026-06-30SHENYANG GOLDING NC & INTELLIGENCE TECH CO LTD
View PDF 1 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
SHENYANG GOLDING NC & INTELLIGENCE TECH CO LTD
Filing Date
2021-10-18
Publication Date
2026-06-30

AI Technical Summary

Technical Problem

During heat treatment, existing technologies struggle to effectively automate the identification of processing status, leading to lengthy data recording, difficulties in manual measurement, inconsistent measurement standards, data omissions, and increased safety risks, all of which affect workpiece quality and production efficiency.

Method used

A time-series segmentation-based approach is adopted, combining local and global features. Through inflection point extraction, trend segment division, bottom-up merging, and H-SVM classifiers, the processing status of the heat treatment process can be automatically identified.

Benefits of technology

It improves segmentation speed and accuracy, reduces manual intervention, enhances production efficiency and the accuracy of workpiece quality prediction, and reduces safety risks.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115994326B_ABST
    Figure CN115994326B_ABST
Patent Text Reader

Abstract

This invention discloses a method for identifying the processing status of heat treatment processes, belonging to the field of heat treatment process processing status identification. This invention proposes a status identification method based on a piecewise linear representation of time series data, targeting the trend changes in temperature during heat treatment. The method first extracts inflection points based on the angular changes in time-series temperature data, then uses these inflection points to divide the original data into trend segments. Next, it merges these trend segments from bottom to top to obtain a piecewise linear representation, and finally uses the statistical features of the segments for H-SVMs classification to obtain the processing status of the heat treatment process.
Need to check novelty before this filing date? Find Prior Art