Konrad Świrski

Modeling Constructional Parameters of a Solid Oxide Fuel Cell by Using an Artificial Neural Network

An Artificial Neural Network (ANN) can predict an objects behavior with no algorithmic solution merely by utilizing available experimental data. The error backpropagation algorithm was used for an ANN training procedure. There are SOFC features mainly architectural in nature that cannot be expressed in numerical form or where numerical expression is difficult to obtain, i.e. electrolyte type, anode type, cathode type etc. In those situations a hybrid model (H-ANN) which contains the ANN model and mathematical expressions can be applied. The H-ANN is able to predict cell voltage with knowledge of minimum physical factors.

Information Platform TEWI

Information Platform TEWI (Technology, Education and Research, Knowledge, Innovation) is an interregional research network, which aims at integrating Polish scientific community using Product Lifecycle Management software. It is being created by three universities: Technical University of Lodz, Warsaw University of Technology and Bialystok University of Technology. The platform TEWI will allow to take advantage of new information technologies and state of the art solutions in research and industry. It will facilitate cooperation between the universities and industry by utilizing compatible software. The Product Lifecycle Management software will make knowledge management easier and more available for scientists. Moreover, the new software will improve the skills of scientific community and make the technology transfer to the industry more fluent. As a result this should make the Polish industry more competitive.

Towards Modern Collaborative Knowledge Sharing Systems

Read more and get great! Thats what the book enPDFd towards modern collaborative knowledge sharing systems will give for every reader to read this book. This is an on-line book provided in this website. Even this book becomes a choice of someone to read, many in the world also loves it so much. As what we talk, when you read more every page of this towards modern collaborative knowledge sharing systems, what you will obtain is something great.

Advanced Methods in Mathematical Modeling

The chapter presents fundamentals of mathematical modeling with special focus on “black box” models. Bio-inspired empirical models—various types of neural networks, hybrid systems with fuzzy logic, fuzzy neural networks and artificial immune systems are commonly used when there is insufficient phenomenological knowledge about objects and processes or when rapid computation is required for solutions. A multilayer perceptron structure (MLP) is used for SOFC fuel cell modeling and the presented Model Predictive Control or immune system optimization may be used in future for fuel cell operation control and optimization.