http://www.tu-ilmenau.de

Logo TU Ilmenau


Neuroinformatics and
Cognitive Robotics Lab

headerphoto Neuroinformatics and 
Cognitive Robotics Lab
Contact Person

Univ.-Prof. Dr.-Ing. Horst-Michael Groß

Head of department

Phone +49 3677 692858

Send email

INHALTE

SOFCOM

Overview

Title:Selfoptimizing combustion control for CO2 emission reduction in industrial coal-fired power plants
(SelbstOptimierende Feuerungsführung zur CO2-EmissionsMinderung in großindustriellen Kohlekraftwerken)
Duration:01.10.2006 - 31.10.2009
Funding:Vattenfall Europe AG
Project Partners:Vattenfall Research and Development AB, Vattenfall Europe Heat Hamburg, Powitec GmbH Essen
Project Manager:Prof. Dr. Horst-Michael Groß, Dr.-Ing. Klaus Debes
Staff:Dipl.-Inf. Erik Schaffernicht
Preceding Projects:VIP
CORSA

Description

Figure of the project's system

The scope of the SOFCOM project is to develop a selfoptimizing combustion control suitable for industrial coal-fired power plants. The primary goal is to increase the effectiveness of the combustion process to reduce the coal consumption and therefore minimize the production of greenhouse gases. The realization is focused on intelligent control of the underlying process. Selforganizing, hence selfoptimizing, techniques are used to handle the input of spatial-temporal video data, to produce an optimal control strategy, and to adapt to changes in the combustion process.

Publications

Papers available for download on the lab's publication page

Funkquist, J., Stephan, V., Schaffernicht, E., Rosner, C., Berg, M.
SOFCOM - Self-optimising strategy for control of the combustion process.
in: VGB PowerTech Journal, 8 (2011) 3, 48-54, 

Schaffernicht, E., Stephan, V., Gross, H.-M.
Adaptive Feature Transformation for Image Data from Non-stationary Processes.
in: Proc. Int. Conf. on Artificial Neural Networks (ICANN 2009), Cyprus, Part II, LNCS 5769, pp. 735-744, Springer 2009

Schaffernicht, E., Stephan, V., Debes, K., Gross, H.-M.
Machine Learning Techniques for Selforganizing Combustion Control.
in: Proc. 32nd Annual Conference on Artificial Intelligence (KI 2009), Paderborn, LNCS 5803, pp. 395-402, Springer 2009

Schaffernicht, E., Möller, Ch., Debes, K., Gross, H.-M.
Forward Feature Selection Using Residual Mutual Information.
in: Proc. 17th European Symposium On Artificial Neural Networks - Advances in Computational Intelligence and Learning (ESANN 2009), pp. 583-588, d-side publication 2009

Rosner, C., Röpell, H., Wintrich, F., Stephan, V. Schaffernicht, E.
Wirkungsgradverbesserung an steinkohlebefeuerten Dampferzeugern mittels lernfähiger, videogestützter Luftverteilungsoptimierung.
VGB Powertech 12, 2008

Schaffernicht, E., Stephan, V., Gross, H.-M.
An Efficient Search Strategy for Feature Selection Using Chow-Liu Trees.
in: Proc. Int. Conf. on Artificial Neural Networks (ICANN) 2007, Portugal, LNCS 4668, pp. 190-199, Springer Verlag 2007, 

Stephan, V., Wintrich, F., König, A., Debes, K.
Application of Action Dependant Heuristic Dynamic Programming to Control an Industrial Waste Incineration Plant.
in: Proc. 3rd Workshop on Self-Organization of AdaptiVE Behavior (SOAVE), 2004, Ilmenau, pp. 262-270, Fortschritt-Berichte VDI, Reihe 10, Nr. 743, VDI-Verlag 2004, 

Stephan, V., Saupe, M., Bischoff, M., Reindanz, H., Gross, H.-M.
Is Reinforcement-Learning Able to Solve Real-World Challenges?
in: Proc. Int. Conf. on Aritficial Neural Networks (ICANN/ICONIP 2003), Istanbul, pp. 346-349, Bogaziai University Library, ISBN 975-518-209-8, 

Stephan, V., Debes, K., Gross, H.-M.
Beschreibung von Verbrennungszuständen mittels farbbildbasierten Eigenflames.
in: Proc. 8. Workshop Farbbildverarbeitung 2002, pp. 119-126, ZBS Ilmenau, ISSN 1432-3346, 

Stephan, V., Debes, K., Gross, H.-M., Wintrich, F., Wintrich, H.
A New Control Scheme for Combustion Processes using Reinforcement Learning based on Neural Networks.
International Journal on Computational Intelligence and Applications, vol. 1 (2001) 2, pp. 121-136, Imperal College Press 2001, 

Stephan, V., Debes, K., Gross, H.-M., Wintrich, F., Wintrich, H.
Reinforcement Learning Based Control Scheme for a Visually-guided Combustion Process.
in: Proc. 15th European Meeting on Cybernetics and Systems Research (EMCSR 2000), Vienna, 2000, vol. 2, pp. 555-558, Austrian Society for Cybernetic Studies, 2000, 

Stephan, V., Debes, K., Gross, H.-M., Wintrich, F., Wintrich, H.
A Reinforcement Learning based Neural Multi-Agent-System for Control of a Combustion Process.
in: Proc. IEEE-INNS-ENNS Int. Joint Conference on Neural Networks (IJCNN 2000), Como (Italy), 2000, pp.VI 217-222, IEEE Computer Society Press 2000, 

Debes, K., Stephan, V., Gross, H.-M., Wintrich, H., Wintrich, F.
Farbbildbasierte Prozessführung in der Kohlenstaubfeuerung mittels Reinforcement-Lernverfahren.
in: Proc. SOAVE2000 - SelbstOrganisation von Adaptivem VErhalten, Ilmenau, Fortschritt-Berichte VDI, Reihe 10: Informatik/Kommunikationstechnik, Vol. 643, pp. 155-163, VDI-Verlag 2000, 

Gross, H.-M., Stephan, V., Krabbes, M.
A Neural Field Approach to Topological Reinforcement Learning in Continous Action Spaces.
in: Proc. 1998 IEEE World Congress on Computational Intelligence WCCI'98 and International Joint Conference on Neural Networks IJCNN'98, Anchorage, pp. 1992-1997, IEEE Computer Society Press 1998,