Automatic classification of the 13CrMo4-5 steel worked in creep conditions

• Autorzy: Dobrzański J. , Sroka M.
• Języki publikacji: EN

Abstrakty

EN

Purpose: In material engineering the images obtained by various methods are the source of different information about materials. The artificial intelligence tools can be employed for automatic method for analysis of scanning electron microscope metallographic images of elements after long time operating in creep services. Design/methodology/approach: The methodology allows to work out a system of automatic classification of internal damages in 13CrMo4-5 steel working in creep conditions on the base of computational images analysis by the use of artificial neural networks. Input vectors of artificial neural networks were optimized by the use of genetic algorithms. Findings: The methodology of digital image analysis allowing identification of geometrical coefficients characterizing damages in the materials after long-time operating in creep conditions and methodology of classification of these damages by the use of artificial neural network were evaluated. Practical implications: The presented method can be use as a practical application for classification of creep-damages of elements power industry installations components operating in creep conditions. Originality/value: Applying of images analysis and neural networks to identification and classification of internal damages of 13CrMo4-5 steel working in creep conditions could shorten the time of classification and eliminate of many subjective errors made by humans.

Słowa kluczowe

EN

creep; neural networks; steels; image analysis

PL

pełzanie; sieć neuronowa; stal; analiza obrazu

• Wydawca: International OCSCO World Press
• Czasopismo: Journal of Achievements in Materials and Manufacturing Engineering
• Rocznik: 2008
• Tom: Vol. 29, nr 2
• Strony: 147--150
• Opis fizyczny: Bibliogr. 16 poz., wykr.

Twórcy

autor

Dobrzański J.

autor

Sroka M.

• Institute for Ferrous Metallurgy, ul. K. Miarki 12/14, 44-100 Gliwice, Poland,

Bibliografia

• [1] L. A. Dobrzański, M. Sroka, J. Dobrzański, Application of neural networks to classification of internal damages in steels working in creep service, Journal of Achievements in Materials and Manufacturing Engineering 20 (2006) 303-306.
• [2] J. Dobrzański, Internal damage processes in low alloy chromium-molybdenum steels during high-temperature creep service, Journal of Materials Processing Technology 157-158 (2004) 197-303.
• [3] J. Dobrzański, A. Zieliński, M. Sroka, Structure, properties and method of the state evaluation of low-alloyed steel T23 (HCM2S) worked in creep conditions, Proceedings of the 11thInternational Scientific Conference Contemporary "Achievents in Mechanics, Manufacturing and Materials Science" CAM3S'2005, Gliwice-Zakopane, 2005, (CD-ROM).
• [4] J. Dobrzański, M. Sroka, A. Zieliński, Methodology of classification of internal damage the steels during creep service, Journal of Achievements in Materials and Manufacturing Engineering 18 (2006) 263-266.
• [5] M. Sroka, Methodology of computer forecasting of residual life of elements in creep service, PhD Thesis, Gliwice (2006) (unpublished) (in Polish).
• [6] L. A. Dobrzański, M. Krupinski, J.H. Sokolowski, Computer aided classification of flaws occurred during casting of aluminum, Journal of Materials Processing Technology 167 (2005) 456-462.
• [7] L. Miaoquan, Ch. Dunjun, X. Aiming, Li. Long, An adaptive prediction model of grain size for the forging of Ti-6Al-4V alloy based on fuzzy neural networks, Journal of Materials Processing Technology 123 (2002) 377-381.
• [8] L. A. Dobrzański, M. Kowalski, J. Madejski: Methodology of the mechanical properties prediction for the metallurgical products from the engineering steels using the artificial intelligence methods, Journal of Materials Processing Technology 164-165 (2005) 1500-1509.
• [9] Polish standard, PN-EN 10028-2:2005 Flat products made of steels for pressure purposes - Part 2: Non-alloy and alloy steels with specified elevated temperature properties
• [10] H. Zheng, L. X. Kong, S. Nahavand, Automatic inspection of metallic surface defects using genetic algorithms, Journal of Materials Processing Technology 125-126 (2002) 427-433.
• [11] J. Dobrzański, M. Sroka, Computer aided classification of internal damages the chromium-molybdenum steels after creep service, Journal of Achievements in Materials and Manufacturing Engineering 24/2 (2007) 143-146.
• [12] D. Renowicz, A. Hernas, M. Cieśla, K. Mutwil, Degradation of the cast steel parts working in power plant pipelines, Journal of Achievements in Materials and Manufacturing Engineering 18 (2006) 219-222.
• [13] R. Tadeusiewicz, P. Korohoda, Computer assisted image analysis and processing, Development in telecommunication Press, Cracow 1997 (in Polish).
• [14] L. Wojnar, K. J. Kurzydłowski, J. Szala, Practice of image analysis, PTS, Cracow, 2002 (in Polish).
• [15] L. A. Dobrzański, S. Malara, J. Trzaska, Project of neural network for steel grade selection with the assumed CCT diagram, Journal of Achievements in Materials and Manufacturing Engineering 27 (2008) 155-158.
• [16] L. A. Dobrzanski, M. Kremzer, J. Trzaska, A. Wlodarczyk-Fligier, Neural network application in simulations of composites Al-Al2O3 tribological properties, Archives of Materials Science and Engineering 30/1 (2008) 37-40.