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.
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
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.
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.
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.
Smart Images

Figure CN121504092B_ABST