EVALUATION OF MATERIAL PROPERTIES OF STRUCTURAL STEELS USING ARTIFICIAL INTELIGENCE NEURAL NETWORK METHOD

1 KANDER Ladislav
Co-authors:
2 POLCAR Petr 1 DORAZIL Ondřej 1 STEJSKALOVÁ Šárka 1 ČÍŽEK Petr
Institutions:
1 MATERIAL AND METALLURGICAL RESEARCH Ltd., Pohraniční 693/31, Ostrava - Vítkovice, Czech Republic, EU, ladislav.kander@mmvyzkum.cz
2 Research and Testing Insitute Plzeň, Tylova 1581/46, 301 00, Plzeň, Czech Republic; polcar@vzuplzen.cz
Conference:
28th International Conference on Metallurgy and Materials, Hotel Voronez I, Brno, Czech Republic, EU, May 22nd - 24th 2019
Proceedings:
Proceedings 28th International Conference on Metallurgy and Materials
Pages:
703-708
ISBN:
978-80-87294-92-5
ISSN:
2694-9296
Published:
4th November 2019
Proceedings of the conference were published in Web of Science and Scopus.
Metrics:
42 views / 12 downloads
Abstract

This work summarizes results and progress in new method development for identification of material properties of steel. This work deals with application of the small punch test for evaluation of material degradation of power station in the Czech Republic within the project TE01020068 “Centre of research and experimental development of reliable energy production, work package 8: Research and development of new testing methods for evaluation of material properties”. The main effort is here an improvement of empirical correlation of selected steel materials used in power industry for the manufacturing of critical components (rotors, steam-pipes, etc.). The effort here is on the utilization of the finite element method (FEM) and the neural network (NN) for evaluation of mechanical properties (Young modulus of elasticity, yield stress, tensile strength) of the selected material, based on SPT results only. Paper contains results of experimental work carried out over past 7 years. After modification of actual neural network and increasing of the number of results interesting results of mechanical properties prediction have been obtained. Increasing data of points in common up to 300, leads to significantly lower deviation that varies about 3-5 %.

Keywords: Small Punch Test, Neural Network, Power Plant Steel, Mechanical properties methods
Scroll to Top