Detecting At-Fault Combustors via Pressure Spectrum Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Gas turbines face operational challenges due to combustor degradation from thermal cycling and pressure pulses, leading to performance issues and frequent scheduled outages, necessitating a method to detect and predict at-fault combustors during operation.
Innovation Solution
A system comprising sensors to capture combustion dynamics pressure data, which is converted into a frequency spectrum, segmented, and analyzed using machine learning algorithms to identify feature values and train a computing device to recognize behavior indicative of an at-fault combustor, enabling real-time detection and prediction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If regularly scheduled outages are executed for inspection and repair, then combustor reliability is maintained, but machine availability deteriorates
Solution Approach 1:
The system performs preliminary monitoring and detection of combustor health status during normal operation, identifying degradation trends before they lead to failure. This allows maintenance to be scheduled at optimal times rather than relying on fixed schedules, thereby maintaining reliability while improving availability by avoiding unnecessary outages
Solution Approach 2:
The system continuously monitors combustor parameters and provides feedback on health status, enabling dynamic adjustment of maintenance scheduling. This feedback loop allows the system to extend operation between outages when combustors are healthy while triggering early maintenance when degradation is detected, resolving the contradiction between reliability and availability
2Measurement precision
If combustor degradation is monitored between outages, then detection precision improves, but device complexity increases
Solution Approach 1:
The monitoring system is designed to serve multiple functions: it monitors combustor health, predicts failures, and provides data for maintenance scheduling. By making the system multi-functional, the increased complexity is justified by the multiple benefits gained, including improved detection precision and extended maintenance intervals
Solution Approach 2:
The system uses the combustor's own operational data and inherent physical responses to monitor its own health status. By leveraging existing operational parameters and the combustor's natural behavior under stress, the system achieves precise degradation detection without requiring extensive external monitoring equipment, thereby limiting the increase in device complexity
Data Source
AI summary
A system for detecting an at-fault combustor includes a sensor that is configured to sense combustion dynamics pressure data from the combustor and a computing device that is in electronic communication with the sensor and configured to receive the combustion dynamics pressure data from the sensor. The computing device is programmed to convert the combustion dynamics pressure data into a frequency spectrum, segment the frequency spectrum into a plurality of frequency intervals, extract a feature from the frequency spectrum, generate feature values for the feature within a corresponding frequency interval over a period of time, and to store the feature values to generate a historical database. The computing device is further programmed to execute a machine learning algorithm using the historical database of the feature values to train the computing device to recognize feature behavior that is indicative of an at-fault combustor.