A Nitrogen Oxides Emission Prediction Model for Gas Turbines Based on Interpretable Multilayer Perceptron Neural Networks

Gas turbines, an important energy conversion equipment, produce Nitrogen Oxides (NOx) emissions, endangering human health and forming air pollution. With the increasingly stringent NOx emission standards, it is more significant to ascertain NOx emission characteristics to reduce pollutant emissions. Establishing an emission prediction model is an effective way for real-time and accurate monitoring of the NOx discharge amount. Compared with the traditional emission monitoring methods, the emission prediction model has higher accuracy and faster calculation efficiency and can obtain believable NOx emission prediction results for various operating conditions of gas turbines. Based on the multi-layer perceptron neural networks, an interpretable emission prediction model with a monitorable middle layer is designed to monitor NOx emission by taking the boundary conditions, working conditions and performance parameters originated from the simulation model of gas turbines as the network inputs. The outlet temperatures and pressures of the compressors and high-pressure turbines are selected as the monitorable measuring parameters of the middle layer. The emission prediction model is trained by historical operation data under different working conditions. According to the errors between the predicted values and measured values of the middle layer and output layer, the weights of the emission prediction model are optimized by the back-propagation algorithm, and the optimal NOx emission prediction model is established for gas turbines under the various working conditions. Furthermore, the mechanism of predicting NOx emission value is explained on the basis of known parameter influence laws between the input layer, middle layer and output layer, which helps to reveal the main measurement parameters affecting NOx emission value, adjust the model parameters and obtain more accurate prediction results. Compared with existing prediction methods, the proposed interpretable emission prediction model can achieve higher accuracy, reliability, real-time and adaptability with fewer samples for different operating conditions, and can improve operational efficiency and reduce NOx emission.