1 March 2019 in Aerospace Science and Technology
1 January 2020 in Applied Thermal Engineering
13 October 2023 in Energy Reviews
24 May 2018 in Journal of Engineering for Gas Turbines and Power
This paper proposes a hybrid method (HMRC) comprised of a radial basis function (RBF) neural net algorithm and component-level modeling method (CMM) as a real-time simulation model for triaxial gas turbines with variable power turbine guide vanes in matlab/simulink. The sample size is decreased substantially after analyzing the relationship between high and low pressure shaft rotational speeds under dynamic working conditions, which reduces the computational burden of the simulation. The effects of the power turbine rotational speed on overall performance are also properly accounted for in the model. The RBF neural net algorithm and CMM are used to simulate the gas generator and power turbine working conditions, respectively, in the HMRC. The reliability and accuracy of both the traditional single CMM model (SCMM) and HMRC model are verified using gas turbine experiment data. The simulation models serve as a controlled object to replace the real gas turbine in a hardware-in-the-loop simulation experiment. The HMRC model shows better real-time performance than the traditional SCMM model, suggesting that it can be readily applied to hardware-in-the-loop simulation experiments.
22 December 2022 in Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science
The loss prediction model plays a crucial role in turbine design for fast performance prediction and a shorter design cycle. Owing to the design requirements of high-efficiency turbines under a wide range of operating conditions, the loss prediction of the off-design incidence is increasingly important. However, limited by the modeling database and traditional modeling methods, the accuracy and adaptability of the existing off-design incidence loss predictions are insufficient. This paper proposes an adaptive prediction method based on machine learning and develops a multi-objective optimization process based on adaptive prediction. Machine learning (neural network) is applied for more flexible and accurate loss predictions over a wide incidence range. Compared with two classic loss models (Ainley and Mathieson model and Benner model), the adaptive prediction model significantly improves the ability to predict turbine profile loss with off-design incidence, particularly under large incidence conditions. The prediction root mean square error can be reduced by up to 73.8% (absolute value: 0.063). Furthermore, the multi-objective optimization method based on adaptive prediction is applied to the aerodynamic optimization of the original cascades with a wide incidence range. The weighted objective of the optimized cascade (Cri = 0.211) is reduced by 8.7% compared with that of the original cascade (Cri = 0.231). Within the range of full incidence angle (−40° to +20°), the variation of profile loss is reduced by 24.0%. This study is a preliminary exploration aimed at establishing an accurate turbine loss prediction system based on machine learning, the feasibility, and superiority of this approach are confirmed.