... for the power turbine simulation module, gas generator working parameters and power turbine inlet parameters are calculated by RBF neural network; there is no need for solutions to nonlinear equations, so the model still has good real-time performance. Fig. 6 Structure diagram of HMRC model...

... , “ Analytical and Neural Network Models for Gas Turbine Design and Off-Design Simulation ,” Int. J. Appl. Thermodyn. , 4 ( 4 ), pp. 173 – 182 . https://www.researchgate.net/publication/42539804_Analytical_and_Neural_Network_Models_for_Gas_Turbine_Design_and_Off-Design_Simulation [3] Ogaji , S. O. T...

... at TOC 0.4 0.8 FPT_RPM Design speed of constant speed FPT 9600 16,000 Fig. 8 Artificial neural network surrogate model fit quality, cruise ESFC The goal of the initial DoE is to provide adequate sampling of the physics-based engine model to allow for quality surrogate model fits...

... learning approach is used for the misfiring detection. The features used as inputs for the classifier are extracted from measurements incorporating physical knowledge about the given setup. To this end, a neural network is trained based on labeled data which is then used for classification purposes, i.e...

..., with the maximum exergy efficiency and the lowest cost per power (k$/kW) as its objectives. Artificial neural network (ANN) is chosen to accelerate the parameters query process. It is shown that the cycle parameters such as heat source temperature, turbine inlet temperature, cycle pressure ratio, and pinch...

...Krzysztof Dominiczak; Romuald Rządkowski; Wojciech Radulski; Ryszard Szczepanik Considered here are nonlinear autoregressive neural networks (NETs) with exogenous inputs (NARX) as a mathematical model of a steam turbine rotor used for the online prediction of turbine temperature and stress...

... ], neural network (NN) models [ 39–41 ], and ANFIS models [ 42 , 43 ]. As was mentioned earlier, the present paper attempts to introduce an innovative method for gray-box identification of the Wiener models for gas turbine engines. To evaluate the proposed model, its performance is going to be compared...

...” data. These models of different details are used in a specific diagnostic process employing model-based diagnostic methods, namely the probabilistic neural network (PNN) method and the deterioration tracking method. The results demonstrate the level of diagnostic information that can be obtained...