Kadlec, P. and Gabrys, B., 2010. Local learning-based adaptive soft sensor for catalyst activation prediction. AIChE Journal. (In Press)
Full text not available from this repository.
This work presents an algorithm for the development of adaptive soft sensors. The method is based on the local learning framework, where locally valid models are built and maintained. In this framework it is possible to model non-linear relationship between the input and output data by the means of a combination of linear models. The method provides the possibility to perform adaptation at two levels: (i) recursive adaptation of the local models; and (ii) the adaptation of the combination weights. The data set used for evaluation of the algorithm describes a polymerisation reactor where the target value is a simulated catalyst activity in the reactor. This data set is also used to evaluate the performance of the proposed algorithm. The results show that the traditional RPLS algorithm struggles to deliver accurate predictions. In contrast to this, by exploiting the two level adaptation scheme, the proposed algorithm delivers more accurate results.
|Subjects:||Generalities > Computer Science and Informatics > Artificial Intelligence|
Generalities > Computer Science and Informatics
Technology > Engineering > General Engineering
|Group:||School of Design, Engineering & Computing > Smart Technology Research Centre|
|Deposited By:||Professor Bogdan Gabrys|
|Deposited On:||02 Feb 2009 18:02|
|Last Modified:||07 Mar 2013 15:06|
Available Versions of this Item
- Local learning-based adaptive soft sensor for catalyst activation prediction. (deposited 02 Feb 2009 18:02) [Currently Displayed]
|Repository Staff Only -|
|BU Staff Only -|
|Help Guide -||Editing Your Items in BURO|