论文部分内容阅读
本文涉及统计系统辨识,其目的是利用水质参数的非平稳时间序列以及水力学参数的时间序列建立潮汐河流的水质动态模型。文章中推导了变系数的差分模型,并将变系数分解成时变和时不变两部分,以导出时不变的待辨识参数。然后通过对噪声性质的讨论,指出可以采用时间序列的分析方法,从而建立潮汐河流水质的动态模型,并应用Allen的PSS准则确定非线性的待估参数值。本文还提出了通过预报来修正非线性参数的一种方法。最后,通过实例计算,证实了本文方法是可行的。
This paper deals with the identification of statistical systems. The purpose of this paper is to establish the dynamic model of water quality in tidal rivers by using the non-stationary time series of water quality parameters and the time series of hydraulic parameters. In this paper, the differential coefficient variation model is deduced, and the variable coefficient is decomposed into time-varying and time-invariant in order to derive the unchanged parameters to be identified. Then, by discussing the noise nature, it is pointed out that the time series analysis method can be used to establish the dynamic model of tidal river water quality, and Allen’s PSS criterion can be used to determine the nonlinear estimated value of the parameter to be estimated. In this paper, a method of correcting non-linear parameters by forecasting is also proposed. Finally, through the example calculation, it is proved that this method is feasible.