To address the challenges of high computational cost and long simulation cycles inherent in traditional numerical simulation methods for analyzing labyrinth seal leakage characteristics. A two-stage artificial neural network-based method was proposed for predicting leakage in labyrinth seals. Using MLP (multilayer perceptron) as the core, a main network prediction model was constructed to achieve preliminary regression prediction of labyrinth seal leakage. To further improve accuracy, a second-stage residual prediction network was introduced to correct the prediction errors of the main network. Leakage data under different labyrinth seal structural parameters were obtained through computational fluid dynamics methods, and these data were used as samples to complete both stages of training and testing. The results Show as follows. The main network prediction model achieved a coefficient of determination R2 of 0.985 5 on the test set, demonstrating excellent predictive performance. The overall performance of the prediction model was improved after incorporating the error compensation network, reducing the root mean square error and mean absolute error of the main network by 30.56% and 31.98%, respectively, and increasing R2 to 0.992 6. The proposed method maintains high prediction accuracy even with only 800 samples, effectively mitigating the fluctuation in errors that typically occurs with MLP as sample size increases. This study provides a reliable and efficient predictive tool for the rapid design and performance optimization of labyrinth seal structures.
WuSenlin, ZhaoZheng, WangWenqi, et al. Experimental investigation of the influence of seal cavity leakage on a compressor performance[J]. Journal of Aerospace Power, 2025, 40(6): 318-324.
RenGuozhe, LuDezheng, SunDan, et al. Effects of structural parameters on flow characteristics and optimal number of sealing teeth of labyrinth seals[J]. Journal of Propulsion Technology, 2025, 46(2): 293-305.
LiWenkai, ZhangBo, JiHonghu, et al. Effect of fin geometrical parameters on leakage of straight-through labyrinth seals[J]. Lubrication Engineering, 2015, 40(2): 28-33.
DuFaqing, JiHonghu, ShuaiHaishan, et al. Orthogonal experiment of effect of fin geometrical parameters on leakage of straight-through labyrinth seals[J]. Journal of Aerospace Power, 2013, 28(4): 825-831.
KongXiaozhi, LiuGaowem, LeiZhao, et al. Experimental investigation for effects of tooth shapes on compressor inter-stage seal[J]. Journal of Propulsion Technology, 2018, 39(9): 2085-2093.
XiangXin, YanXin, LiZhigang, et al. Experimental measurement and numerical investigation on the leakage flow characteristic of labyrinth honeycomb seal[J]. Journal of Xi’an Jiaotong University, 2022, 11(56): 72-82.
ZhangWeiwei, ZhuLinyang, LiuYilang, et al. Progresses in the application of machine learning in turbulence modeling[J]. Acta Aerodynamica Sinica, 2019, 37(3): 444-454.
WeiDong, MaChuan, MaJianmin. XGBoost-neural networks for secondary return water temperature prediction in thermal stations[J]. Science Technology and Engineering, 2025, 25(17): 7226-7237.
ZhangQiang, LiChun, MiaoWeipao, et al. Prediction of flow field parameters for aerodynamic flap of airfoil based on deep learning[J]. Journal of Engineering for Thermal Energy and Power, 2024, 39(2): 162-168.
DuZhou, XuQuanyong, SongZhenshou, et al. Prediction of aerodynamic characteristics of compressor blade profile based on deep learning[J]. Journal of Aerospace Power, 2023, 38(9): 2251-2260.
ZhangHongbin, WangYun, SunLongxiang. Dynamic recognition model of driver’s propensity based on factor analysis and artificial neural network[J]. Science Technology and Engineering, 2021, 21(9): 3829-3833.
WangXuanzheng, XuZhipeng, LiXiaoqiu, et al. Industrial control protocol recognition based on edge distributed deep learning[J]. Science Technology and Engineering, 2025, 25(18): 7678-7685.
[31]
YangJ, HuangY P, WangD L, et al. Fast prediction of compressor flow field in nuclear power system based on proper orthogonal decomposition and deep learning[J]. Frontiers in Energy Research, 2023, 11.DOI: 10.3389/fenrg.2023.1163043.
[32]
HippleS M, Bonilla-AlvaradoH, PezziniP, et al. Using machine learning tools to predict compressor stall[J]. Journal of Energy Resources Technology, 2020, 142(7). DOI: 10.1115/1.4046458.
[33]
WaschkaW, WittigS, KimS. Influence of high rotational speeds on the heat transfer and discharge coefficients in labyrinth seals[J]. Journal of Turbomachinery, 1990, 114(2): 462-468.
[34]
KuvshinovA, GunnemannS. Robustness verification of ReLU networks via quadratic programming[J]. Machine Learning, 2022, 111(7): 2407-2433.
[35]
HomamN S, MagnusH, HerwartH, et al. A novel approach based on artificial neural network for calibration of multi-hole pressure probes[J]. Flow Measurement and Instrumentation, 2020, 73.DOI: 10.1016/j.flowmeasinst.2020.101739.
LiaoPeng, YaoLeijiang, BaiGuodong, et al. Prediction of hybrid airfoil leading edge pressure distribution based on deep learning[J]. Journal of Aerospace Power, 2019, 34(8): 1751-1758.