Parameter Estimation with Improved Model Prediction for Over-Parametrized Nonlinear Systems

Parameter Estimation with Improved Model Prediction for Over-Parametrized Nonlinear Systems
复制标题

超参数化非线性系统的参数估计和改进的模型预测

DOI:
10.1016/j.compchemeng.2021.107601
复制
发表时间:
2021-11
期刊:
Computers & Chemical Engineering
影响因子:
--
通讯作者:
Lorenz T. Biegler
Lorenz T. Biegler
中科院分区:
其他
文献类型:
--
作者:
Weifeng Chen;Baojia Wang;Lorenz T. Biegler

文献摘要

参考文献

相似文献

参数估计是系统建模的关键步骤。在实践中,化学工程师开发的基本模型通常很复杂。可能存在对模型预测没有影响或影响很小的参数。此外,某些参数可能会对与其他参数相关的模型预测产生影响。在这种情况下,很难估计所有参数。解决这个问题的一般方法是选择一个参数子集来估计,并将其余参数固定为初始值。在这里,提出了一种简化的 Hessian 和基于统计标准的参数估计方法来改进模型预测。该方法考虑了初始参数值对模型预测的影响。在根据输出的均方误差(MSE)选择变换参数的最优子集的过程中,将灵敏度矩阵替换为简化的Hessian矩阵,这样可以节省MSE计算的计算成本。获得最优变换参数子集后,根据统计准则选择最优初始值。可以避免由于任意初始值而导致的模型预测与实际模型输出之间的较大差异。数值结果表明了所提出方法的有效性。
Parameter estimation is a crucial step in system modeling. In practice, the fundamental models developed by chemical engineers are often complex. There may be parameters that have no or little effect on the model prediction. Also, some parameters may have an impact on model prediction related to other parameters. In this case, it is difficult to estimate all the parameters. The general approach to address this issue is to select a subset of parameters to estimate, and fix the rest at the initial value. Here, a reduced Hessian and statistical criterion-based parameter estimation approach is proposed for improving model prediction. The proposed method considers the influence of the initial parameter values on model prediction. In the process of selecting the optimal subset of transformed parameters based on the mean square error (MSE) of output, the sensitivity matrix is replaced by the reduced Hessian matrix, which can save computational cost of MSE calculation. After obtaining the optimal transformed parameter subset, the optimal initial values are selected based on the statistical criterion. The large difference between the model prediction and the actual model output caused by the arbitrary initial values can be avoided. The numerical results show the effectiveness of the proposed approach.
DOI: 10.1186/1752-0509-3-113
发表时间: 2009-12-04
影响因子: --
作者:
Wu J;Sinfield JL;Buchanan-Wollaston V;Feng J
通讯作者: Feng J
DOI: 10.1109/9.21105
发表时间: 1989-02
影响因子: 6.8
作者:
S. Vajda;H. Rabitz
通讯作者: S. Vajda;H. Rabitz
DOI: 10.1021/ie202352f
发表时间: 2012-05-02
影响因子: 4.2
作者:
McLean, Kevin A. P.;Wu, Shaohua;McAuley, Kimberley B.
通讯作者: McAuley, Kimberley B.
DOI: 10.1137/0904025
发表时间: 1983-06
期刊: Siam Journal on Scientific and Statistical Computing
影响因子: --
作者:
P. Gill;W. Murray;M. Saunders;M. H. Wright
通讯作者: P. Gill;W. Murray;M. Saunders;M. H. Wright
DOI: 10.1021/ie800432s
发表时间: 2009-07
影响因子: 4.2
作者:
Y. Chu;J. Hahn
通讯作者: Y. Chu;J. Hahn