一种基于条码数据的发动机零部件生产追溯方法及系统
By using an improved time-series graph attention network model, frequency parameters and bandwidth factors are adaptively adjusted, solving the problem of insufficient monitoring of dynamic changes in parts in traditional traceability methods, and realizing accurate traceability and intelligent management of engine parts production processes.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- XIAN CUMMINS ENGINE COMPANY
- Filing Date
- 2026-04-29
- Publication Date
- 2026-07-17
AI Technical Summary
Traditional engine component production traceability methods lack real-time monitoring capabilities and are unable to accurately reflect the dynamic changes of components at different process stages, resulting in information omissions and incomplete traceability links, which cannot meet the high requirements of intelligent manufacturing.
An improved time-series graph attention network model is adopted. By adaptively adjusting the frequency parameters and bandwidth factors, the attention weights are dynamically adjusted to identify key and abnormal processes, thereby achieving accurate reconstruction and traceability of the parts production chain.
It improves the completeness, continuity, and reliability of component traceability results, enhances the sensitivity to production anomalies, enables visualized monitoring and intelligent scheduling of the production process, and provides highly reliable data support for quality management.
Smart Images
Figure CN122114759B_ABST