Evaluating concrete materials by application of automatic reasoning

• Autorzy: Alterman D. , Kasperkiewicz J.
• Języki publikacji: EN

Abstrakty

EN

There were two aims of the research. One was to enable more or less automatic confirmation of the known associations - either quantitative or qualitative - between technological data and selected properties of concrete materials. Even more important is the second aim - demonstration of expected possibility of automatic identification of new such relation-ships, not yet recognized by civil engineers. The relationships are to be obtained by methods of Artificial lntelligence, (Al), and are to be based on actual results from experiments on concrete materials. The reason of applying the Al tools is that in Civil Engi-neering the real data are typically non perfect, complex, fuzzy, often with missing details, which means that their analysis in a traditional way, by building empirical models, is hardly possible or at least can not be done quickly. The main idea of the proposed approach was to combine application of different Al methods in a one system, aimed at es-timation, prediction, design and/or optimization of composite materials. The paradigm of the approach is that the unknown rules concerning the properties of concrete are hidden in experimental results and can be obtained from the analysis of examples. Different Al techniques like artificial neural networks, machine learning and certain techniques related to statistics were applied. The data for the analysis originated from direct observations and from reports and publications on concrete technology. Among others it has been demonstrated that by combining different Al methods it is possible to improve the quality of the data, (e.g. when encountering outliers and missing values or in clustering problems), so that the whole data processing system will be giving better prediction, (when applying ANNs), or the newly discovered rules will be more effective, (e.g. with descriptions more complete and - at the same time - possibly more consistent, in case of ML algorithms).

Słowa kluczowe

EN

concrete materials; estimation; prediction; design and optimization of the properties of composite materials; Artificial lntelligence; Artificial Neural Networks; machine learning (ML); concrete databases processing; automatic rule generation

• Wydawca: Polska Akademia Nauk, Wydział IV Nauk Technicznych
• Czasopismo: Bulletin of the Polish Academy of Sciences. Technical Sciences
• Rocznik: 2006
• Tom: Vol. 54, nr 4
• Strony: 353--361
• Opis fizyczny: Bibliogr. 16 poz., rys., tab.

Twórcy

autor

Alterman D.

autor

Kasperkiewicz J.

• Institute of Fundamental Technological Research, Polish Academy of Sciences, 21 Świętokrzyska St., 00-049 Warsaw, Poland,

Bibliografia

• [1] D. Alterman, Evaluation of Concrete Materials by Automatic Reasoning, Doctoral Dissertation, IFTR PAS, Warszawa, 2005, (in Polish).
• [2] C.B. Oland and C.F. Ferraris, Guide to Recommended Format for Concrete in Materials Property Database, ACI Committee, 1999.
• [3] R.S. Michalski and K.A. Kaufman, The AQ19 System for Machine Learning and Patterndiscovery: a General Description and User’s Guide, George Mason University, 2001.
• [4] A.M. Brandt and J. Kasperkiewicz, Diagnosis of Concretes and High Performance Concrete by Structural Analysis, IFTR PAS, Warszawa, 2003, (in Polish).
• [5] SPSS for Windows, http://www.spss.com/.
• [6] aiNet – ANNs; a trial version, http://www.ainet-sp.si/NN/En/nn.htm
• [7] AQ19 – Machine Learning Programs, http://www.mli.gmu.edu/mdirections.html
• [8] See5/C5.0 – Demonstration, http://www.rulequest.com/download.html
• [9] Gradestat – Grade Correspondence Analysis Package, http://www.ipipan.waw.pl/ gradestat/
• [10] ROSETTA – a Rough Set Toolkit for Analysis of Data, http://rosetta.lcb.uu.se/general/download
• [11] Statistics and Neural Network Toolboxes of MATLAB, http://www.mathworks.com/web_downloads
• [12] Stuttgart Neural Network Simulator, http://www-ra.informatik.uni-tuebingen.de/SNNS
• [13] IAC – Interactive Activation and Competition, http://www2.psy.uq.edu.au/ brainwav/Manual/IAC.html
• [14] J. Kasperkiewicz, J. Racz, and A. Dubrawski, “HPC strength prediction using artificial neural network”, Journal of Computing in Civil Engineering 9 (4), 279–284 (1995).
• [15] T. Kowalczyk, E. Pleszczy´nska, and F. Ruland, Grade Models and Methods for Data Analysis with Applications for the Analysis of Data Populations, Springer-Verlag, Berlin, 2004.
• [16] J. Kasperkiewicz and D. Alterman, “On effectiveness of preprocessing by clustering in prediction of CE technological data with ANNS”, Int. Conf.: New Trends in Intelligent Information Processing and Web Mining, 261–266 (2003).