An AI-based adaptive production scheduling system

By constructing an AI-based adaptive production scheduling system, and utilizing directed acyclic graphs and dual-domain coupled decision modules to verify causal relationships, the system solves the problem of misidentification of non-systematic noise in traditional scheduling systems, achieves high-precision production scheduling decisions, and ensures the stability and continuity of production.

CN121504092BActive Publication Date: 2026-05-26FUJIAN MINGUANG SOFTWARE CO LTD
View PDF 1 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
FUJIAN MINGUANG SOFTWARE CO LTD
Filing Date
2026-01-12
Publication Date
2026-05-26

AI Technical Summary

Technical Problem

Existing production scheduling systems are prone to misidentifying non-systematic noise caused by sensor signal jitter, minor fluctuations in manual operation, or network latency as systematic disturbances, leading to frequent and meaningless scheduling jitters that disrupt the continuity and stability of production operations.

Method used

An AI-based adaptive production scheduling system is constructed. The system obtains a directed acyclic graph of production resource allocation and time-series flow through a data acquisition and benchmark construction module. Combined with a theoretical disturbance simulation module and a real deviation extraction module, the system uses a dual-domain coupled decision module to verify causal relationships and generate an adaptive scheduling scheme.

Benefits of technology

It effectively filters out non-systematic noise, ensuring that scheduling instructions only change real physical constraints, thereby improving the robustness and accuracy of scheduling decisions and maintaining the stability and continuity of production rhythm.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121504092B_ABST
    Figure CN121504092B_ABST
Patent Text Reader

Abstract

This invention relates to the field of intelligent manufacturing and production management technology, specifically to an artificial intelligence-based adaptive production scheduling system. The system includes a data acquisition and benchmark construction module, which analyzes process data to construct a directed acyclic graph representing a disturbance-free state as a benchmark graph; a theoretical disturbance simulation module, which converts disturbance rules into graph change instructions, generates a theoretical damaged state graph, and derives a theoretical difference feature vector; the theoretical difference feature vector is mathematically represented, including but not limited to, a vector form obtained by expanding the difference matrix by rows or columns; a real-world deviation extraction module, which collects real-time state data to construct a real-time operation state graph and calculates the real-world difference feature vector; a dual-domain coupled decision-making module; and an adaptive scheduling execution module. This invention verifies causal relationships by comparing theoretical deductions with real-world observations, effectively filtering non-systematic noise and achieving accurate responses to real-world faults while maintaining production rhythm stability.
Need to check novelty before this filing date? Find Prior Art