采用基于核函数的多元非线性回归分析方法,对Rolls-Royce公司的发动机基线方程进行了求解,建立了标准化过程中的核函数和性能参数的偏差值模型。把厂家系统计算出的偏差值作为目标值,其他相关参数的测量值作为输入,采用高斯牛顿迭代法对该多元非线性方程组进行回归分析,能够迅速收敛,准确地求解出模型未知系数,经整理可得出准确的基线方程。通过比较自主基线求解的偏差值与厂家系统求解的偏差值可知,采用上述基线挖掘方法得到的基线方程模型精度能够满足实际应用的要求。
The nonlinear multiple regression analysis based on kernel function was used to solve the baseline equation of Rolls-Royce's(RR's)engine.The standard kernel function was established and then the deviation model of performance parameters was established.The deviation calculated by factory system was used as target value,and other relevant parameters of the measured values as input,the unknown coefficient could quickly converge and be solved by Gauss-Newton iterative method in nonlinear multiple regression analysis,and the accurate baseline was obtained by ordering the equation.The accurate engine baseline function obtained by the proposed method could satisfy practical application requirements.