Kadlec, P., Grbic, R. and Gabrys, B., 2011. Review of adaptation mechanisms for data-driven soft sensors. Computers and Chemical Engineering, 35 (1), pp. 1-24.
This is the latest version of this eprint.
Full text not available from this repository.
We review and discuss the most signicant algorithms for adaptive data-driven soft sensing. Interestingly, one of the earliest algorithms, namely the Recursive Partial Least Squares method, remains one of the most popular methods until today. Nonetheless, a certain tendency towards kernel-based methods can be observed in the last years. In order to be able to provide a comprehensive overview of the meth- ods, we have grounded the adaptive soft sensing methods in the machine learning theory for adaptive learning systems. In particular, we use the concept drift theory to classify different adaptive soft sensing algorithms into three ifferent categories. We also provide a comprehensive list of publications where adaptive soft sensors were proposed and discuss the main characteristics of the algorithms. Last but not least, we present a list of publicly available data sets.
|Uncontrolled Keywords:||Data-driven soft sensing; Process industry; Adaptation; Incremental learning; Online prediction; Process monitoring; Soft sensor case studies; Review|
|Subjects:||Generalities > Computer Science and Informatics > Artificial Intelligence|
Generalities > Computer Science and Informatics
|Group:||School of Design, Engineering & Computing > Smart Technology Research Centre|
|Deposited By:||Professor Bogdan Gabrys|
|Deposited On:||06 Jun 2011 09:43|
|Last Modified:||07 Mar 2013 15:45|
Available Versions of this Item
|Repository Staff Only -|
|BU Staff Only -|
|Help Guide -||Editing Your Items in BURO|