基于环形拓扑自适应差分进化算法优化神经网络的压气机流量特性预测

姜瑞政; 张均东; 冯金红; 沈浩生; 王川

doi:10.16411/j.cnki.issn1006-7736.2021.01.012

大连海事大学学报 >

2021 , Vol. 47 >Issue 1: 101 - 110

DOI: https://doi.org/10.16411/j.cnki.issn1006-7736.2021.01.012

船舶与海洋工程

基于环形拓扑自适应差分进化算法优化神经网络的压气机流量特性预测

姜瑞政 ,
张均东 ,
冯金红 ,
沈浩生 ,
王川

展开

（大连海事大学轮机工程学院, 辽宁大连 116026）

张均东（1967 — ），男，博士，教授，博士生导师.

收稿日期: 2020-12-30

修回日期: 2021-02-21

网络出版日期: 2021-02-21

基金资助

国家自然科学基金青年基金项目（51709027）.

收起

Prediction of compressor flow characteristics based on neural network optimized by ring topology adaptive differential evolution algorithm

JIANG Rui-zheng ,
ZHANG Jun-dong ,
FENG Jin-hong ,
SHEN Hao-sheng ,
WANG Chuan

Expand

（Marine Engineering College, Dalian Maritime University, Dalian 116026,China）

Received date: 2020-12-30

Revised date: 2021-02-21

Online published: 2021-02-21

Fold

摘要

为提升轮机模拟器中柴油机非额定工况下的仿真精度，提出一种基于有限数据的混合方法来预测多工况下的压气机流量特性.该方法采用一种基于环形拓扑差分进化算法来优化三层前馈神经网络参数，利用有限的给定工况下的流量特性数据，预测压气机流量特性曲线.采用神经网络来拟合压气机流量特性的非线性映射关系，利用差分进化算法优化调整神经网络的连接权重、连接偏置、连接开关等难以调整的重要参数.仿真结果表明，基于有限数据的方法可较好地拟合船舶压气机流量特性，采用环形拓扑的自适应差分进化算法优化调整神经网络的重要参数具有一定的有效性.本文提出的混合方法具有更好的泛化能力和搜索精度，可作为处理类似预测问题的有效手段.

关键词： 压气机; 流量特性; 神经网络; 差分进化算法

本文引用格式

姜瑞政 , 张均东 , 冯金红 , 沈浩生 , 王川 . 基于环形拓扑自适应差分进化算法优化神经网络的压气机流量特性预测[J]. 大连海事大学学报, 2021 , 47(1) : 101 -110 . DOI: 10.16411/j.cnki.issn1006-7736.2021.01.012

Abstract

In order to improve the simulation accuracy of diesel engine in marine engine room simulator under non rated conditions, a hybrid method based on limited data was proposed to predict the compressor flow characteristics under multiple conditions. In this method, a ring topology differential evolution (DE) algorithm was used to optimize the parameters of the three-layer feedforward neural network (FNN), and the flow characteristic curve of the compressor was predicted by using the limited flow characteristic data under given conditions. A FNN was used to fit the nonlinear mapping of compressor flow characteristics, and the DE algorithm was used to adjust the important parameters, such as connection weight, connection bias and connection switch. The simulation results show that the method based on limited data can better fit the flow characteristics of marine compressor, and the adaptive differential evolution algorithm with ring topology is effective to optimize and adjust the important parameters of neural network. The hybrid method proposed in this paper has better generalization ability and search accuracy, which can be used as an effective means to deal with similar prediction problems.

Key words： compressor; flow characteristics; neural network; differential evolution algorithm

参考文献

[1]KIM T S and HWANG S H.Part load performance analysis of recuperated gas turbines considering engine configuration and operation strategy[J].Energy, 2006, 31(2-3):260-277 [2]BORGHETTI A, MIGLIAVACCA G, NUCCI C A and SPELTA S.Black-start-up simulation of a repowered thermoelectric unit[J].Control Engineering Practice, 2001, 9(7):791-803 [3]黄林, 程刚, 许伟范仕龙.基于双通道α键合图的压气机建模与仿真研究[J].海军工程大学学报, 2018, 30(01):46-52 [4]BAHRAMI S, GHAFFARI A, SADATI S H and THERN M.Identifying a simplified model for heavy duty gas turbine[J].Journal of Mechanical Science and Technology, 2014, 28(6):2399-2408 [5] ASGARI H, VENTURINI M, CHEN X and SAINUDIIN R.Modeling and Simulation of the Transient Behavior of an Industrial Power Plant Gas Turbine [J]. Journal of Engineering for Gas Turbines and Power-Transactions of the Asme, 2014, 136 (6):[J].Journal of Engineering for Gas Turbines and Power-Transactions of the Asme, 2014, 136(6):061601-1-061601-10 [6]李景轩, 周登极, 肖旺张会生.燃气轮机机理-数据混合建模方法研究[J].热能动力工程, 2019, 34(12):33-39 [7]黄伟, 常俊孙智滨.基于-神经网络的压气机特性曲线预测[J].重庆理工大学学报自然科学, 2019, 33(02):67-74 [8] 周奎.神经网络在燃气轮机建模仿真和性能监测中的应用 [D]. 清华大学, 2017. [9] JIANG R, ZHANG J, TANG Y, WANG C and FENG J.A Collective Intelligence Based Differential Evolution Algorithm for Optimizing the Structure and Parameters of a Neural Network [J]. Ieee Access, 2020, 8 69601-69614.[J].IEEE ACCESS, 2020, 8:69601-69614 [10]DAS S and SUGANTHAN P N.Differential Evolution: A Survey of the State-of-the-Art[J].Ieee Transactions on Evolutionary Computation, 2011, 15(1):4-31 [11]BREST J, GREINER S, BOSKOVIC B, MERNIK M and ZUMER V.Self-adapting control parameters in differential evolution: A comparative study on numerical benchmark problems[J].Ieee Transactions on Evolutionary Computation, 2006, 10(6):646-657 [12]STORN R and PRICE K.Differential evolution - A simple and efficient heuristic for global optimization over continuous spaces[J].Journal of Global Optimization, 1997, 11(4):341-359 [13]TSAI J T, CHOU J H and LIU T K.Tuning the structure and parameters of a neural network by using hybrid Taguchi-genetic algorithm[J].Ieee Transactions on Neural Networks, 2006, 17(1):69-80

Options

文章导航

模态框（Modal）标题

摘要

本文引用格式

Abstract

参考文献