本文通过对某船用柴油机的匹配涡轮增压器进行研究，得到了压气机的特性曲线。分析了压气机转速、质量流量、压比和效率之间的关系。为了拟合回归和预测压气机特性曲线，使用了一些广泛使用的代理模型，包括Kriging模型、响应面法（RSM）、人工神经网络（ANN）、径向基函数（RBF）和支持向量机（SVM）。代理模型用于精确预测涡轮增压器在特定时间的运行参数。采用代理模型对不同速度组的曲线进行拟合，研究了压力比与效率的整体预测建模方法，并通过数据分析了不同训练样本量对拟合精度的影响; 通过遗传算法优化后的全转速下的代理模型的拟合精度提高，在样本数量较少时，其代理模型拟合结果的R2超过95%。
This study gets the matched turbocharger of a marine diesel engine to acquire the compressor characteristic curve. It was done to analyze the relationships between compressor speed, mass flow rate, pressure ratio, and efficiency. For fitting regression and predicting the compressor characteristic curve, a number of widely used surrogate models, including the Kriging model, Response Surface Methodology (RSM), Artificial Neural Networks (ANNs), Radial Basis Function (RBF) and Support vector machines (SVM), were used. The surrogate model is used to precisely anticipate the turbocharger's operational parameters at a specific time. The surrogate models are used to fit the curves of different speed groups, the result shows that the whole prediction modeling method of pressure ratio and efficiency is studied, and the influence of different training sample size on fitting accuracy is analyzed by data. After optimization by genetic algorithm, the fitting accuracy of the surrogate model at full speed is improved. When the samples size is small, the fitting result R2 of the surrogate model is more than 95%.
2025,47(3): 89-94 收稿日期：2024-4-30
DOI：10.3404/j.issn.1672-7649.2025.03.015
分类号：U664.5+1
基金项目：黑龙江省重点研发计划项目（2023ZX01A14）
作者简介：杨启融(1993-),男,博士研究生,研究方向为发动机涡轮增压原理、数字孪生系统构建
参考文献：
[1] HAN Z. Kriging surrogate model and its application to design optimization: A review of recent progress[J]. Acta Aeronauticaet Astronautica Sinica, 2016, 37(11): 3197?3225.
[2] FAISAL T R, ADOUNI M, DHAHER Y Y. Surrogate modeling of articular cartilage degradation to understand the synergistic role of MMP-1 and MMP-9: a case study[J]. Biomech Model Mechanobiol, 2023, 22(1): 43?56.
[3] YEPES B L, BRUN I A, ALCALá J, et al. CO(2)-Optimization of post-tensioned concrete slab-bridge decks using surrogate modeling[J]. Materials (Basel), 2022, 7, 15(14).
[4] BERTHELSON P R, GHASSEMI P, WOOD J W, et al. A finite element-guided mathematical surrogate modeling approach for assessing occupant injury trends across variations in simplified vehicular impact conditions[J]. Med Biol Eng Comput. 2021 May;59(5): 1065?1079.
[5] CONN A R, SCHEINBERG K, VICENTE L N. Introduction to derivative-free optimization | | 12[J]. Review of Surrogate Model Management. 2009, 229–240.
[6] GARZóN A, LANGEVELD J, KAPELAN Z, et al. Machine learning‐based surrogate modeling for urban water networks: review and future research directions[J]. Water Resources Research, 2022, 58(5): 1–26.
[7] WU T. Recent advances in surrogate modeling methods for uncertainty quantification and propagation[J]. Symmetry, 2022, 14: 1219.
[8] JIANG C, ZHANG D Q, LIU J, et al. Time-dependent reliability analysis through response surface method[J]. Journal of Mechanical Design, 2017, 139(4): 1547?1559.
[9] KUMAR A S, SINGH H P, MOHSIN M K. Response surface optimization approach to enhance the performance of diesel engine using ternary blends of biobutanol and biodiesel doped with ZnO nanoparticles[J]. Energy Conversion and Management, 2024, 300: 117899.
[10] DAI H, ZHANG H, WANG W. A support vector density-based importance sampling for reliability assessment[J]. Reliability Engineering and System Safety, 2012, 106(106): 86?93.
[11] SALMA J, ADEL K. Sensorless DTC-SVM applied to an induction motor controlled by a three-level inverter using SMSFO[J]. COMPEL - The international journal for computation and mathematics in electrical and electronic engineering, 2023, 42(6): 1349?1371.
[12] PAPADOPOULOS V, GIOVANIS D G, LAGAROS N D, et al. Accelerated subset simulation with neural networks for reliability analysis[J]. Computer Methods in Applied Mechanics and Engineering, 2012, 223?224: 70?80.
[13] SHENG G, YAN H Z, ZHI Q Z, et al. Multi-objective optimization of the combustion chamber geometry for a highland diesel engine fueled with diesel/n-butanol/PODEn by ANN-NSGA III[J]. Energy, 2023, 282: 128793.
[14] LEE S, KIM J H. An adaptive importance sampling method with a Kriging metamodel to calculate failure probability[J]. Journal of Mechanical Science & Technology, 2017, 31(12): 5769?5778.
[15] DR??EK P S. , Kubacki s?awomir, ?ó?tak jerzy. kriging-based framework applied to a multi-point, multi-objective engine air-intake duct aerodynamic optimization problem[J]. Aerospace, 2023, 10(3): 266?266.
[16] GAO S, LIU J. Adaptive fault‐tolerant robust control based on radial basis function neural network for a class of mechanical systems with input constraints[J]. International Journal of Robust and Nonlinear Control, 2022(7): 32.
[17] QIU W M, HUI H Z, ZHI B S, et al. Multiobjective optimization of stress-release boot of solid rocket motor under vertical storage based on RBF model[J]. International Journal of Aerospace Engineering, 2022(346?351): 1?8
[18] YING Y, SUN B, PENG S, et al. Study on the regression method of compressor map based on partial least squares regression modeling[J]. Proceedings of the ASME Turbo EXPO: Turbine Technical Conference and Exposition, 2014.
[19] BAYOMI N, ABDEL M R, REZK M. Centrifugal compressor map prediction and modification[J]. Journal of King Abdulaziz University Engineering Sciences, 2013, 24(24): 73?88.
[20] CHU F, WANG F, WANG X, et al. Performance modeling of centrifugal compressor using kernel partial least squares[J]. Applied Thermal Engineering, 2012, 44: 90?99.
[21] ZHAO Y, LI B W, ZHU F X, et al. Surrogate model optimization of compressor characteristics based on qpso algorithm[J]. Journal of Propulsion Technology, 2014, 35(11): 1537?1543.
[22] QUEIPO N V, HAFTKA R T, SHYY W, et al. Surrogate-based analysis and optimization[J]. Progress in Aerospace Sciences, 2005, 41(1): 1?28.
[23] YANG Q R, WANG H C, YANG C L, et al. Research on surrogate models and optimization algorithms of compressor characteristic based on digital twins[J/OL]. Journal of Engineering Research, 2024.
