Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
713203 | IFAC-PapersOnLine | 2015 | 6 Pages |
Abstract
A Bayesian algorithm is developed for estimating parameters in nonlinear stochastic differential equation (SDE) models. The proposed algorithm uses prior information about parameters and builds on the approximate expectation maximization (AEM) algorithm (Karimi and McAuley, 2014a). A nonlinear continuous stirred tank reactor (CSTR) model is used to compare the effectiveness of the Bayesian algorithm to that of the AEM algorithm. For the CSTR example studied, the proposed method provides more accurate parameter estimates, especially for small data sets.
Related Topics
Physical Sciences and Engineering
Engineering
Computational Mechanics