Fault diagnosis method and system for valve actuating mechanism of steam turbine
By collecting and predicting the working parameters and motion state of the steam turbine valve actuator, combined with continuous error counter and model training, the problem that existing fault diagnosis methods are difficult to accurately find the cause of the fault is solved, achieving more accurate fault diagnosis and prediction, and improving system safety.
Patent Information
- Application Number
- CN202411892473.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-20
- Publication Date
- 2025-04-04
- Estimated Expiration
- 2044-12-20
AI Technical Summary
The existing methods of steam turbine valve actuators are difficult to achieve accurate fault cause search, and status maintenance or even fault prediction cannot be achieved.
By collecting the current working parameters of the actuator, inputting the motion state prediction model, predicting the motion state of the actuator in the future time period, and determining the fault through the continuous error counter. At the same time, a working parameter prediction model and state classification model are constructed and trained, data reconstruction and model training are carried out to achieve accurate prediction of the motion state of the actuator.
It realizes online judgment of the movement status of the actuator, accurately classify faults, and early detection of system safety hazards, improving the safety of steam valve work, and ensuring the safe operation of coal-electric units.