基于改进布谷鸟搜索算法的压气机特性曲线预测  

Compressor characteristic curve prediction based on improved cuckoo search algorithm

作　　者：王巍[1] 李哲 刘祎阳 姜孝谟 刘朋 李士龙 WANG Wei;LI Zhe;LIU Yiyang;JIANG Xiaomo;LIU Peng;LI Shilong(School of Energy and Power Engineering,Dalian University of Technology,Dalian 116024,China;School of Mechanics and Aeronautics,Dalian University of Technology,Dalian 116024,China;China United Heavy Gas Turbine Technology Co.,Ltd,Beijing 100016,China)

机构地区：[1]大连理工大学能源与动力学院,辽宁大连116024 [2]大连理工大学力学与航空航天学院,辽宁大连116024 [3]中国联合重型燃气轮机技术有限公司,北京100016

出　　处：《推进技术》2025年第1期219-227,共9页Journal of Propulsion Technology

基　　金：国家基础研究(J2019-I-0012-0012);中央高校科技领军人才团队基金(DUT22LAB502)。

摘　　要：为了提高压气机特性曲线的预测精度和边界工况点的泛化能力,本文提出了一种改进布谷鸟搜索算法优化BP(ICS-BP)的模型,应用于某轴流压气机流量-压比特性预测方法研究,并对比分析了采用传统BP、遗传算法优化BP(GA-BP)、布谷鸟搜索算法优化BP(CS-BP)、径向基函数神经网络(RBF)、极限学习机(ELM)、自优化支持向量机(MSVM)和ICS-BP模型的预测结果。分析显示,ICS-BP模型整体预测结果的相对误差最小,普遍在±1%以内,评价指标展现出最高的精度和鲁棒性,预测结果具有最佳的泛化能力,且优化后的模型解决BP易陷入局部最优的问题;ELM和RBF模型运行速度较快的情况下依然具有良好的整体预测精度,但对于边界工况点预测效果欠佳,适用于对时间成本要求高的场景。针对7F重型燃气轮机和NASA74A型号压气机特性曲线,通过ICS-BP模型预测的压比特性精度较高,整体预测结果的平均绝对百分误差分别为1.129%和0.590%,进一步验证了其在特性预测方面的优势。This study introduces a model for optimizing backpropagation with improved cuckoo search algorithm(ICS-BP),aimed at augmenting the accuracy and generalization capability of predicting compressor characteristic curves under boundary operating conditions.Focusing on the flow-pressure ratio predictions for an axial flow compressor,this paper evaluates and contrasts the performance of the proposed ICS-BP model against traditional BP,BP optimized by genetic algorithm(GA-BP),cuckoo search optimized BP(CS-BP),radial basis function networks(RBF),extreme learning machines(ELM),and self-optimized support vector machines(MSVM).The comparative analysis reveals that the ICS-BP model achieves the lowest relative prediction error,consistently under±1%,showcasing superior precision and robustness,along with the best generalization across various conditions.This optimized model effectively addresses the common pitfalls of BP algorithms.While ELM and RBF models maintain commendable accuracy at high operational speeds,their performance deteriorates at the boundary operating points along the speed line,making them more suited for time-sensitive applications.Specifically,for the 7F heavy-duty gas turbine and NASA74A compressor characteristic curve,the ICS-BP model’s predictions of flow-pressure ratio characteristics exhibit high fidelity,and the average absolute percentage error of the overall prediction results is 1.129%and 0.590%,respectively,thereby affirming its superiority in characteristic curve prediction.

关 键 词：压气机特性 曲线预测 改进布谷鸟搜索算法 神经网络 泛化能力 

分 类 号：V231.1[航空宇航科学与技术—航空宇航推进理论与工程] TK472[动力工程及工程热物理—动力机械及工程]