Research on Performance Prediction of Air Quality Assurance Systems for Gas Turbines Based on Novel Test Method

Abstract

The quality of air intake significantly impacts the overall performance of gas turbines. A new high-precision testing method for the air intake quality assurance system of gas turbines has been proposed, and the influence of typical intake conditions on the system was studied through this testing method. The research results indicate a positive correlation between filtration efficiency and particle size. Atmospheric temperature, particle concentration, filter differential pressure, and atmospheric humidity all affect filtration efficiency, with their influence decreasing in that order. Additionally, this paper presents a performance prediction model based on the LSTM neural network. The calculation results show that the errors of the filter pressure loss and filtration efficiency model test set are both less than 3%, reflecting the characteristics of pressure loss and efficiency well. The research results have significant engineering application value and provide experimental basis for establishing technical standards and high-precision detection systems for air quality assurance in gas turbines.