After the lean fuel premixed combustion technology is applied to aero engines, severe combustion oscillations will be cased and led to hidden safety hazards such as engine vibration, further energy waste and other problems. Therefore, it is increasingly important to actively control combustion oscillations. In this paper, a multispectral radiation thermometry (MRT) is used to analyze the hydroxyl group, which is a measurable research object in the combustion chamber of an aero engine, and to fit the functional relationship between the radiation intensity ratio and the temperature in different bands. The theoretical value of the error is <2%. At the same time, in order to solve the problem of weak detection signal and excessive interference signal, an improved frequency domain filtering method based on fast Fourier transform is designed. Besides, the FPGA platform is used to ensure the real-time performance of the temperature measurement system, and simulations and experiments are performed. An oscillating signal with an oscillation frequency of 315 Hz is obtained on the established test platform, and the error is only 1.42%.
Deep Neural Network and Polynomial Chaos Expansion-Based Surrogate Models for Sensitivity and Uncertainty Propagation: An Application to a Rockfill Dam