Gas Turbine Combustion Profile Monitoring

Systems and methods for gas turbine combustion profile monitoring are disclosed. In one embodiment, a method (400) for detecting an anomaly in a combustion section (10) of a gas turbine (4) is disclosed. The method (400) includes receiving, from a plurality of thermal sensors (50) disposed around an exhaust section (22) of a gas turbine (4), exhaust profile data of the gas turbine. The method (400) further analyzes the exhaust profile data to calculate statistical features associated with a peak-trough pattern. The method (400) further determines, using a machine learning algorithm, that the statistical features are abnormal. In response to the determination, the method (400) processes the exhaust profile data for a predetermined period of time and reports an anomaly in a combustion section (10) of the gas turbine (4) if the statistical features remain abnormal for the predetermined period of time. 公开用于燃气涡轮燃烧分布监测的系统和方法。在个实施例中，公开用于检测燃气涡轮(4)的燃烧区段(10)中的异常的方法(400)。方法(400)包括从围绕燃气涡轮(4)的排气区段(22)设置的多个热传感器(50)接收燃气涡轮(4