A process index correlation calculation method, device, equipment and storage medium
By acquiring process data from a time-series database, processing outliers and missing values, performing data alignment and stability interval calculation, and combining a voter fusion of multiple correlation methods, the problem of relying on human experience to judge the correlation of process indicators is solved. This enables fast and accurate calculation of the correlation of process indicators, supporting process optimization and production efficiency improvement.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHINA ORDNANCE EQUIP GRP AUTOMATION RES INST CO LTD
- Filing Date
- 2022-10-27
- Publication Date
- 2026-07-07
AI Technical Summary
In existing technologies, the determination of correlations between process indicators in industrial manufacturing relies heavily on workers' professional experience, resulting in low accuracy. In particular, it is difficult to quickly and accurately identify correlations in complex situations, which affects process optimization and production efficiency.
By acquiring process data from a time-series database, detecting and processing outliers and missing values, performing data alignment and stability interval calculation, and employing multiple correlation calculation methods combined with a voter for fusion, the system achieves automated calculation of the correlation of process indicators.
It enables rapid and accurate mining of the correlation between process indicators, reduces the limitations of manual judgment, provides effective data support for process production efficiency prediction and parameter optimization, and improves decision support for the production process.
Smart Images

Figure CN115511374B_ABST