一种燃气轮机叶顶动态间隙预估方法和装置
By establishing a temperature field and multi-field coupled calculation model and using neural network correction parameters, the change in blade tip clearance is accurately quantified, which solves the problem of accuracy in blade tip clearance control under high speed and high load transient conditions, reduces the risk of accidents, and improves the safety and reliability of gas turbines.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- SHENZHEN HIRISUN TECH INC
- Filing Date
- 2026-06-22
- Publication Date
- 2026-07-17
AI Technical Summary
Existing tip clearance control technologies are unable to accurately predict the evolution of clearance under dynamic conditions during transient operations at high speeds and high loads. This makes it easy for static tip clearance margin control strategies to cause accidents, such as blade coating peeling, damage to the gas seal structure, or even unplanned shutdowns.
By acquiring actual operating data of the gas turbine, a temperature field and multi-field coupled calculation model is established. The model parameters are corrected using a long short-term memory neural network (LSTM) and a radial basis function neural network (RBF-BPNN) to accurately quantify the change in blade tip clearance and predict the dynamic clearance under transient conditions.
It effectively reduces the risk of blade tip rubbing, reduces blade structural damage, improves the operational safety of the gas turbine, and avoids losses caused by unplanned shutdowns.
Smart Images
Figure CN122413625A_ABST