Predictive Gas Turbine Combustion Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Controlling gas turbine combustion dynamics to prevent damaging accelerations while minimizing impact on operating parameters such as output power and emissions is challenging due to the reactive nature of existing safety systems, which often disrupt fuel supply.
Innovation Solution
A predictive method that measures current combustion state variables to forecast future dynamics, allowing for proactive control signals to adjust fuel introduction and exhaust gas temperature, thereby mitigating accelerations without significantly affecting gas turbine operation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If safety systems intervene based on current measurements of combustion dynamics, then damage-free operation is ensured, but the gas turbine's operating parameters such as output power and emissions are massively impacted
Solution Approach 1:
The system performs preliminary action by predicting future combustion dynamics and high accelerations before they occur. The control device forecasts future states based on current and past measurements, and intervenes in advance by adjusting fuel supply or airflow, rather than reacting only after damage-threatening conditions are detected. This preliminary intervention prevents the need for massive corrective actions that would disrupt normal operation.
Solution Approach 2:
The system implements dynamic control by continuously adapting fuel supply or airflow based on predicted future combustion dynamics. Instead of static safety thresholds, the control device uses time-dependent prediction models to adjust operating parameters dynamically, allowing the gas turbine to maintain optimal performance while avoiding damaging acceleration peaks through smooth, progressive adjustments.
2Reliability
If safety systems reduce or interrupt fuel supply to prevent high accelerations, then gas turbine damage is avoided, but stable operation and emissions compliance are compromised
Solution Approach 1:
The control device takes preliminary action by predicting future combustion dynamics and intervening before dangerous acceleration peaks occur. This allows for gradual, controlled adjustments to fuel supply or airflow that maintain combustion stability, rather than sudden reductions that would disrupt operation. The prediction-based approach enables preventive control that preserves stable combustion while avoiding damage.
Solution Approach 2:
The system implements feedback control by continuously measuring combustion dynamics, comparing actual values with predicted future values, and adjusting fuel supply or airflow accordingly. This closed-loop control ensures that interventions are precisely targeted to prevent specific acceleration peaks while maintaining overall operational stability and emissions compliance through continuous adaptation.
3Reliability
If reactive safety systems are used to control combustion dynamics, then damage prevention is achieved, but the control has massive impact on operating parameters
Solution Approach 1:
The system replaces complex reactive control with simpler predictive control. By forecasting future combustion dynamics and high accelerations before they occur, the control device can make small, planned adjustments to fuel supply or airflow, avoiding the need for complex real-time reaction to dangerous conditions. This predictive approach simplifies the control logic while maintaining effective damage prevention.
Solution Approach 2:
The system substitutes mechanical/reactive control mechanisms with prediction-based control. Instead of relying on complex mechanical safety systems that react to detected dangerous conditions, the invention uses computational prediction models to forecast future states and guide control actions, replacing physical reaction mechanisms with intelligent prediction and prevention.
Data Source
Figure 1~3
Figure 4~5
AI summary
The invention relates to a method (100) for controlling a gas turbine, having a measurement step (101), a prediction step (102) which is carried out after the measurement step (101), and a control step (103) which is carried out after the prediction step. In the measurement step (101), a state variable of a combustion within a gas turbine is measured. In the prediction step (102), a future combustion dynamic is predicted using the measured state variable. In the control step (103), a control signal is output using the prediction of the future combustion dynamic.