Classification and prediction of gas turbine gas path degradation based on deep neural networks

This paper mainly analyzes the performance degradation of turbomachinery in gas turbines, classifies the main types of degradation: increased tip clearance, corrosion/wear, fouling, and multiple degradation, and predicts the degradation trend through deep neural networks. The deep feedforward neural network is used to build the regression model and two classification models. The regression model uses a back propagation algorithm optimized by Lenvenberg Marquardt to convert the efficiency and flow capacity calculated by the thermodynamic model into the values under full load and ISO conditions to ensure that the comparison is performed on the same performance benchmark. Compared with deep feedforward neural network and random forest regression, the optimized model has higher accuracy and no overfitting. The data after the overhaul is selected as the performance benchmark, and the efficiency and flow capacity of different degradation types are calculated according to the benchmark and classified by the classification model. By testing the simulated data, the classification accuracy of the compressor and the turbine exceeds 99.9% and 99.5% respectively. Long short-term memory is used to predict the degradation trends and the degradation of the predictions is classified by the classification model. The degradation classification accuracy of the prediction reached 93.65% and 81.65% in compressor and turbine, which shows that the prediction model has high accuracy.

Automated summary

This paper analyzes the performance degradation of turbomachinery in gas turbines, predicts degradation trends through deep neural networks, builds regression and classification models. The optimized model shows higher accuracy and no overfitting, and the prediction model achieves high accuracy in classifying degradation.