一种基于知识图谱的PDC钻头扭力故障诊断方法
By constructing a dynamic knowledge graph and combining trend similarity and fluctuation synergy to calculate dynamic association strength, the problem that graph convolutional neural networks cannot adapt to dynamic changes in drilling parameters is solved, enabling early warning and accurate diagnosis of PDC drill bit torque faults.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- WUHAN EASTAR TOOL
- Filing Date
- 2026-02-04
- Publication Date
- 2026-07-17
AI Technical Summary
In existing technologies, graph convolutional neural networks cannot capture the dynamic coupling relationships between drilling parameters due to the use of a fixed adjacency matrix, resulting in delayed and misjudged torque fault diagnosis of PDC drill bits.
A knowledge graph containing fault nodes of drilling pressure, rotation speed, torque, and drill bit torque is constructed. Dynamic association strength values are obtained by calculating trend similarity and fluctuation synergy. A dynamic adjacency matrix is constructed and combined with a graph convolutional network for fault diagnosis.
It significantly enhances the early identification capability of PDC drill bit torque faults, realizing the transformation from post-event alarm to pre-event warning, and improving the accuracy and robustness of diagnosis.
Smart Images
Figure CN121659261B_ABST