Holistic approach to diagnostics of engineering materials

• Autorzy: Kasperkiewicz J. , Alterman D.
• Konferencja: Neural Networks and Soft Computing/International Symposium (30.06-02.07.2005 ; Cracow, Poland)
• Języki publikacji: EN

Abstrakty

EN

A concept is presented of a system for automatic processing of the civil engineering data. It may concern designing, optimisation or diagnostics of constructional materials. The main point of interest was concrete and various concrete like composite materials. The applied methods are a combination of various soft computing techniques, like artificial neural networks, machine learning and certain techniques originating in statistics. The system is aimed at taking advantage of varied information available in publications, reports, monographs and direct experimental results, perhaps including even the grey information resources. After preparation of a database collected from laboratory or in-situ observations concerning the behaviour of various concrete materials, and gathered during the two last decades, a number of experiments were performed on the system dedicated mainly to prediction of compressive strength and frost resistance of concrete. The proposed approach allows more efficient control of information in problems of concrete technology.

Słowa kluczowe

EN

engineering materials; artificial neural networks; computing techniques; experimental analysis

PL

materiał techniczny; sztuczne sieci neuronowe; technika komputerowa; analiza eksperymentalna

• Wydawca: Instytut Podstawowych Problemów Techniki PAN
• Czasopismo: Computer Assisted Mechanics and Engineering Sciences
• Rocznik: 2007
• Tom: Vol. 14, No. 2
• Strony: 197--207
• Opis fizyczny: Bibliogr. 17 poz., rys., tab.

Twórcy

autor

Kasperkiewicz J.

autor

Alterman D.

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

Bibliografia

• [1] aiNet - ANNs; a trial yersion, (2.29 MB); at: http://www.ainet-sp.si/NN/En/nn.htm
• [2] AQ21 — Machinę Learaing programs, to be asked for at http://www.mli.gmu.edu/mdirections.html
• [3| D. Alterman. Evaluation of Concrete Materials by Automatic Reasoning (in Polish), doctoral disserlation, manuscriprt, 180 pp. IFTR PAS, Warszawa, 2005.
• [4] A.M. Brandt., ed. Optimization methods for material design of cement-based composites, 314 pp. E&FN SPON, London, L998
• [5] AM Brandt, J Kasperkiewicz, eds. Diagnosta of Concretes and High Performance Concrete by Structural Analysis fin Polish, 218 pp). IFTRPAS-NATO Sci. Alf. Div., Warszawa, 2003.
• [6] S. Dennis, D. McAuley. Connectionist models of cognition. The Brain Wave Connectionist Simulator, at: http://www.itee.uq.edu.au/~cogs2010/cmc/
• [7| GradeStat- grade data analysis package; a free application, (1.26 MB), at http://www.ipipan.waw.pl/~gradestat/
• [8] J. Kasperkiewicz. Application of artificial neural networks in desiPolish). Cement-Wapno-Beton, 1/63. 224-228, 1996.
• [9] J. Kasperkiewicz. D. Alterman. On effectiveness of pre-processing by clustering in prediction of CE. Technological data with ANNs. Proc. of the International Conference: New Trends in Intelligt Informaion Processing and Web Mining, Zakopane. June 2-5, 2003. Springer-Verlag, pp. 261-266.
• [10] J. Kasperkiewicz. J Kac/. A Dubrawski. HPC strength prediction using artificial neural network . Journal of Computing in Civil Engineering. 9: 279-284, 1995.
• [11] T. Kowalczyk, E. Pleszczyńska, F Ruland, eds. Grade models and methods for data analysis, With applications for the analysts of data populations, 177 pp. Springer-Verlag, 2004
• [12] C.B. Oland, C.F. Ferraris. Guide to Recommended Format for Concrete in Materials Property Database, Reported by AC1 Cbmmittee 126, AC1 126.3R-99, September 199
• [13| ROSETTA — a Rough Set Toolkit for Analysis of Data; available for non-commercial use, (1.78 MB); at http://rosetta.lcb.uu.se/general/download/
• [14] Sec5/C5.0-dcmonstration — 10 days evaluation version for Windows XP (608 kB http://www.rulequest.com/download.html
• [15] SPSS for Windows —a 14 days evaluation version, (130 MB); at: http://www.spss.com/
• [16] Statistics and Neural Network Toolboxes of MATLAB; possibility to ask for a 30 days trial software; http://www.mathworks.com/web_downloads/
• [17] WEKA — the package of Data Mining Software, (about LO MB); available on the web at http://www.cs.waikato.ac.nz/~ml/weka/