Prediction and Analysis of Transient Turbine Tip Clearance Using Long Short-Term Memory Neural Network

The transient turbine tip clearance (δ) throughout the engine process is crucial to modern high-performance aero engines. However, there is still a lack of efficient and accurate transient prediction models of tip clearances with active thermal control (ATC) system, especially for the tip clearances of the complex turbine structures with various parameters. This study develops a transient prediction model for the tradeoff between computational efficiency and accuracy, which includes an offline dataset generation process and an online δ prediction process. The offline dataset is first generated using an in-house finite element analysis code, which is validated against a transient tip clearance experiment, and data splicing and sensitivity analysis are applied to enrich the sample features and reduce the input parameters' dimensionality. Then, the long short-term memory neural network (LSTM) is employed to learn the transient tip clearances' timing information. The time consumption for the transient prediction model is significantly shorter than that for the tip clearance calculation method by three orders, and the maximum relative error is as low as 3.59%. In addition, the transient characteristics, including the overshoot value (σ) and the response time (t_s), are investigated with different jet Reynolds numbers (Re_c) and temperatures (T_fc) of ATC cooling flow. The t_s decreases with larger Re_c and smaller T_fc due to a more significant cooling effect. However, the σ increases with the increase of Re_c and T_fc due to the different sensitivity of cooling parameters. This study provides a reference for the transient tip clearance prediction and the adjustments in the cooling strategies.