-
Expert Syst. Appl. 01/2012; 39:806-815.
-
Data Mining Workshops (ICDMW), 2011 IEEE 11th International Conference on, Vancouver, BC, Canada, December 11, 2011; 01/2011
-
[show abstract]
[hide abstract]
ABSTRACT: Fuel feeding and inhomogeneity of fuel typically cause process fluctuations in the circulating fluidized bed (CFB) boilers.
If control systems fail to compensate the fluctuations, the whole plant will suffer from fluctuations that are reinforced
by the closed-loop controls. Accurate estimates of fuel consumption among other factors are needed for control systems operation.
In this paper we address a problem of online mass flow prediction. Particularly, we consider the problems of (1)constructing
the ground truth, (2)handling noise and abrupt concept drift, and (3)learning an accurate predictor. Last but not least we emphasize the
importance of having the domain knowledge concerning the considered case. We demonstrate the performance of OMPF using real
data sets collected from the experimental CFB boiler.
10/2009: pages 272-286;
-
[show abstract]
[hide abstract]
ABSTRACT: Fuel feeding and inhomogeneity of fuel typically cause process fluctuations in the circulating fluidized bed (CFB) process.
If control systems fail to compensate for the fluctuations, the whole plant will suffer from fluctuations that are reinforced
by the closed-loop controls. This phenomenon causes a reduction of efficiency and lifetime of process components. Therefore,
domain experts are interested in developing tools and techniques for getting better understanding of underlying processes
and their mutual dependencies in CFB boilers. In this paper we consider an application of data mining technology to the analysis
of time series data from a pilot CFB reactor. Namely, we present a rather simple and intuitive approach for online mass flow
prediction in CFB boilers. This approach is based on learning and switching regression models. Additionally, noise canceling,
and windowing mechanisms are used for improving the robustness of online prediction. We validate our approach with a set of
simulation experiments with real data collected from the pilot CFB boiler.
07/2009: pages 206-219;
-
[show abstract]
[hide abstract]
ABSTRACT: Fuel feeding and inhomogeneity of fuel typically cause fluc-tuations in the circulating fluidized bed (CFB) process. If control systems fail to compensate the fluctuations, the whole plant will suffer from dynamics that is reinforced by the closed-loop controls. This phenomenon causes reducing effi-ciency and the lifetime of process components. In this paper we address the problem of online mass flow prediction, which is a part of control. Particularly, we consider the prob-lem of learning an accurate predictor with explicit detec-tion of abrupt concept drift and noise handling mechanisms. We emphasize the importance of having domain knowledge concerning the considered case and constructing the ground truth for facilitating the quantitative evaluation of different approaches. We demonstrate the performance of change de-tection methods and show their effect on the accuracy of the online mass flow prediction with real datasets collected from the experimental laboratory-scale CFB boiler.
SIGKDD Explorations. 01/2009; 11:109-116.
-
Foundations of Intelligent Systems, 18th International Symposium, ISMIS 2009, Prague, Czech Republic, September 14-17, 2009. Proceedings; 01/2009
-
Proceedings of the Third International Workshop on Knowledge Discovery from Sensor Data, Paris, France, June 28, 2009; 01/2009
-
Discovery Science, 12th International Conference, DS 2009, Porto, Portugal, October 3-5, 2009; 01/2009
-
[show abstract]
[hide abstract]
ABSTRACT: Sales prediction is a complex task because of a large number of factors affecting the demand. We present a context aware sales prediction approach, which selects the base predictor depending on the structural properties of the historical sales. In the experimental part we show that there exist product subsets on which, using this strategy, it is possible to outperform naive methods. We also show the dependencies between product categorization accuracies and sales prediction accuracies. A case study of a food wholesaler indicates that moving average prediction can be outperformed by intelligent methods, if proper categorization is in place, which appears to be a difficult task.
ICDM Workshops 2009, IEEE International Conference on Data Mining Workshops, Miami, Florida, USA, 6 December 2009; 01/2009