原油蒸馏曲线单调递增指数函数样条插值方法研究

MONOTONICALLY INCREASING EXPONENTIAL FUNCTION SPLINE INTERPOLATION METHOD FOR DISTILLATION CURVE OF CRUDE OIL

针对以虚拟组分法表征原油及其馏分油复杂组成时,常因蒸馏数据不足而导致蒸馏曲线不连续、不光滑,结果可靠性差,而传统二次、三次样条插值方法存在难以保证蒸馏曲线单调递增的问题,设计了一种包含3个参数的指数函数插值方法,从理论上保证了蒸馏曲线单调递增。进而,对52种原油的实沸点蒸馏数据进行插值验证,结果表明:指数函数插值法能够保证插值后的原油蒸馏曲线单调递增;在52种原油的插值结果中,指数函数插值与校验值拟合决定系数(R^(2))大于0.99的有37种,占比71.2%,三次样条插值结果R^(2)大于0.99的仅有21种,占比40.4%;而指数函数插值结果的准确度高于三次样条插值结果的有50种,说明指数函数插值方法效果明显优于三次样条插值方法。因此,基于指数函数插值方法,采用虚拟组分法模拟计算原油加工过程的精确度明显提高。

When the virtual component method is used to characterize the complex chemical composition of crude oil and its fractions,the distillation curve is often discontinuous and fluctuating,and the reliability of the results is poor because of insufficient distillation data.The traditional quadratic and cubic polynomial spline interpolation functions are commonly used to keep the distillation curve continuous and smooth,but those interpolation results sometimes are not accord with the monotonic increasing characteristics of the distillation curve.An exponential spline interpolation with three parameters was designed to guarantee the monotone increasing of distillation curve in theory.Furthermore,the real boiling point distillation data of 52 kinds of crude oils were interpolated and verified.The results showed that the method of exponential spline interpolation could guarantee the monotone increasing of the distillation curve after interpolation.Among the 52 kinds of interpolation results,there were 37 kinds whose fitting determination coefficient(R^(2))of exponential spline interpolation was greater than 0.99,accounting for 71.2%,and only 21 kinds whose R^(2)of cubic spline interpolation was greater than 0.99,accounting for 40.4%.There were 50 kinds whose accuracy of exponential spline interpolation was higher than that of cubic spline interpolation,which showed that exponential spline interpolation was better than cubic spline interpolation.Therefore,based on the exponential spline interpolation method,the accuracy of the virtual component method could be obviously improved.