基于基因表达式算法的某型发动机可调放气阀门基线建模

Baseline Modeling of Engine Variable Bleed Valve Based on Gene Expression Programming Algorithm

摘要: 本文针对航空发动机工作阀门的特性指标难以获取的问题，采用基因表达式编程算法(gene expres-sion programming, GEP)，利用飞机快速存储记录器(quick access recorder, QAR)数据对发动机的可调放气阀门(Variable bleed valve, VBV)工作基线进行挖掘分析。结果表明，基因表达式编程在处理阀门的非线性回归分析时，构建的模型非常接近运行规律，具有偏差小、精度高的特点，并且能得到具体、方便实用的函数关系，能够有效地提高发动机阀门监控和故障诊断的准确性。

Abstract: Aiming at the problem that it is difficult to obtain the characteristic index of engine operation valves, adopting gene expression programming algorithm (GEP), using the quick access recorder (QAR) data, this paper mines and analyzes the engine variable bleed valves (VBV) operation base-line. The results show that, during VBV nonlinear regression analysis, GEP has the advantages of little deviation and high precision. GEP can also get specific and convenient function relations, which can improve the accuracy of VBV monitoring and fault diagnosis effectively.