An automatic control system and control method for precise cutting of flame-retardant fabric

By constructing a variance dispersion screening and clustering method for fabric attribute vectors, high-confidence fabric samples are generated, which solves the problem of unstable cutting quality caused by large parameter dispersion in flame retardant fabric cutting, and realizes precise control and improved yield rate of flame retardant fabric cutting.

CN122308077APending Publication Date: 2026-06-30HANGZHOU SEGURMAX YONGSHENG TEXTILE CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
HANGZHOU SEGURMAX YONGSHENG TEXTILE CO LTD
Filing Date
2026-03-26
Publication Date
2026-06-30

AI Technical Summary

Technical Problem

In existing flame-retardant fabric cutting control, the fabric properties are similar but the execution parameters have large dispersion, resulting in unstable cutting quality, large fluctuations in yield, and easy thermal damage to the flame-retardant layer.

Method used

Clustering is performed by constructing the variance dispersion of fabric attribute vectors to divide J high-confidence fabric attribute cluster screening units and obtain J high-state fabric samples; supervised training unit is used to generate output target cutting unit to control the cutting of fabric to be cut during the target cutting period.

Benefits of technology

It achieves precise control over the cutting of flame-retardant fabrics, improves the stability of yield rate under complex working conditions, and avoids quality defects caused by ambiguous parameters.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122308077A_ABST
    Figure CN122308077A_ABST
Patent Text Reader

Abstract

This invention discloses an automated control system and method for precise cutting of flame-retardant fabrics. The method includes: acquiring N fabric cutting events from a historical processing database, selecting M candidate cutting events, constructing event tuples for the M candidate cutting events, anchoring the fabric attribute vectors of the M event tuples, dividing the fabric into K fabric attribute clusters, selecting J high-confidence fabric attribute clusters from the K fabric attribute clusters, acquiring J high-state fabric samples based on the J high-confidence fabric attribute clusters, performing supervised training of the model based on the J high-state fabric samples, generating a parameter combination model that can output the execution parameter combination for the target cutting period; and using the parameter combination model to control the cutting of the fabric to be cut during the target cutting period. This invention significantly improves the yield stability of adaptive cutting control under complex working conditions.
Need to check novelty before this filing date? Find Prior Art