基于偏差值的航空发动机参数标准化修正模型

考虑到大气温度、大气湿度和燃烧热值等因素的影响,在第三相似理论的基础上提出了一种基于气路参数偏差值的标准化修正模型,以发动机生产厂家的历史数据为学习样本,建立了多元非线性超定方程组,采用高斯牛顿迭代法进行模型中未知参数的回归求解.使用该模型对测试集数据进行偏差值求解,并把结果与其他模型求解的偏差值进行对比,结果表明:修正后的标准化模型具有更高的精度,更接近于厂家系统的原始模型,具有较高的创新性和实用价值.

Corrected standardization model of aero-engine parameter based on deviation

Considering the effect of atmospheric temperature,atmospheric humidity and fuel heating value,a corrected standardization model was proposed relating gas path parameter deviation based on third similarity theory,the multivariate nonlinear overdetermined equations were established using the historical data as learning sample,and the unknown parameters were solved using Gauss-Newton iterative method.The deviation was solved using the corrected standardization model proposed,and the result was compared with deviation solved by other models.the conclusion is drawn that the correction model proposed is closer to the original factory model with higher accuracy,and it is more innovative and has practical value.