轧制过程精轧机组的分布式数据驱动故障检测方法及系统
By improving the average consistency algorithm and sensor network topology, the data risk of centralized detection and the delay of distributed detection in the steel rolling process are solved, and efficient and reliable fault detection is achieved.
CN117428011BActive Publication Date: 2026-07-17SHUNDE INNOVATION SCHOOL UNIVERSITY OF SCIENCE & TECHNOLOGY BEIJING +1
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SHUNDE INNOVATION SCHOOL UNIVERSITY OF SCIENCE & TECHNOLOGY BEIJING
- Filing Date
- 2023-10-23
- Publication Date
- 2026-07-17
Smart Images
Figure CN117428011B_ABST
Abstract
本发明公开了一种轧制过程精轧机组的分布式数据驱动故障检测方法及系统，涉及工业轧钢过程的故障检测技术领域，该方法包括：对精轧机正常运行时的过程变量进行采集并存储；获取由精轧机各机架的压磁传感器组成的传感器网络通信拓扑结构；考虑相邻传感器节点间的数据传输，应用改良后的平均一致性算法来实现最优的分布式故障检测；其中，所述改良后的平均一致性算法包括分布式训练阶段和分布式检测阶段；所述改良后的平均一致性算法通过在分布式训练阶段确定分布式检测阶段所需执行一致性算法迭代的步数，减小检测阶段的检测延迟。采用本发明可有效解决轧钢过程精轧阶段分布式故障检测由于检测延迟而带来的检测性能下降问题。
Need to check novelty before this filing date? Find Prior Art