Fan master control PLC fault diagnosis method and system based on digital twinning
By constructing a PLC source code graph and a timing graph attention network, combined with high-frequency timing data, the false alarm problem in the fault diagnosis of wind turbine main control PLC in the existing technology is solved, realizing efficient and accurate fault location and cause tracing, and improving the interpretability of diagnosis and operation and maintenance efficiency.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- HUANENG RENEWABLES CORP LTD HEBEI BRANCH
- Filing Date
- 2026-03-25
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies fail to effectively utilize the deterministic control logic and causal relationships within the PLC in wind turbine main control PLC fault diagnosis. This results in the diagnostic model generating numerous false alarms under varying operating conditions, lacking interpretability, and making it difficult to trace the underlying causes of the fault.
By constructing a control logic diagram based on PLC source code, combining high-frequency timing data, and using a timing diagram attention network for fault diagnosis, the deterministic control logic of the PLC and real-time data are integrated to perform residual calculation and anomaly scoring, thereby achieving fault location and cause tracing.
It improves the accuracy and interpretability of fault diagnosis, reduces the false alarm rate, provides actionable guidance for fault diagnosis, and improves operation and maintenance efficiency.
Smart Images
Figure CN122411366A_ABST