English
Język Polski
Implicit neural state functions in hybrid reliability analysis of plane frame
DOI:
https://doi.org/10.24425/ace.2023.147647Abstract
The objective of the article involves presenting innovative approach to the assessment of structural reliability analysis. The primary research method was the First Order Reliability Method (FORM). The Hasofer-Lind reliability index in conjunction with transformation method in the FORM was adopted as the reliability measure. The implicit limit state functions were used in the analysis. The formulation of the random variables functions were created in the Matlab software by means of neural networks (NNs). The reliability analysis was conducted in Comrel module of Strurel computing environment. In the proposed approach, Hybrid FORM method (HF) used the concept in which NNs replaced the polynomial limit state functions obtained from FEM (Finite Elements Method) for chosen limit parameters of structure work. The module Comrel referenced Matlab files containing limit state functions. In the reliability analysis of structure, uncertain and uncorrelated parameters, such us base wind speed, characteristic snow load, elasticity modulus for steel and yield point steel are represented by random variables. The criterion of structural failure was expressed by four limit state functions - two related to the ultimate limit state and two related to the serviceability limit state. Using module Comrel values of the reliability index with the FORM method were determined. Additionally, the sensitivity of the reliability index to random variables and graph of partial safety factors were described. Replacing the FEM program by NNs significantly reduces the time needed to solve the task. Moreover, it enables the parallel formulation of many limit functions without extending the computation time.References
[1] EN 1990: 2002 Eurocode - Basis of structural design. 2002.
[2] S. Reh, J. D. Beley, S. Mukherjee, and E. H. Khor, “Probabilistic finite element analysis using ANSYS”, Structural Safety, vol. 28, no. 1-2, pp. 17-43, 2006, doi: 10.1016/j.strusafe.2005.03.010.
[3] I. Papaioannou, A. Düster, E. Rank, C. Katz, and H. Heidkamp, “Integration of reliability methods into a commercial finite element software package”, in Proceedings of the 10th International Conference on Structural Safety and Reliability (ICOSSAR 2009). 2009.
[4] http://www.strurel.de. [Online]. [Accessed: 13 Jun. 2022].
[5] J. Deng, D. Gu, X. Li, and Z. Qi Yue, “Structural reliability analysis for implicit performance functions using neural networks”, Structural Safety, vol. 27, no. 1, pp. 25-48, 2005, doi: 10.1016/j.strusafe.2004.03.004.
[6] A. Dudzik and B. Potrzeszcz-Sut, “The structural reliability analysis using explicit neural state functions”, MATEC Web of Conferences,, vol. 262, 2018, doi: 10.1051/matecconf/201926210002.
[7] A. Hasofer and N. Lind, “Exact and invariant second-moment code format”, Journal of the Engineering Mechanics Division, ASCE, vol. 100, no. 1, pp. 111-121, 1974.
[8] R. Rackwitz and B. Fiessler, “Structural reliability under combined random load sequences”, Computers & Structure, vol. 9, no 5, pp. 489-494, 1978.
[9] T. Abdo and R. Rackwitz, “Reliability of uncertain structural system”, in Proceedings Finite Elements in Engineering Applications. Stuttgart: INTES GmbH, 1990, pp. 161-76.
[10] K. Schittkowski, User’s guide for the nonlinear programming code NLPQL. Handbook to optimization program package NLPQL. Germany: University of Stuttgart - Institute for Informatics, 1985.
[11] K. Schittkowski, C. Zillober, and R. Zotemantel, “Numerical comparison of nonlinear programming algorithms for structural optimization”, Structural and Multidisciplinary Optimization, vol. 7, no. 1-2, pp. 1-19, 1994.
[12] U. Radoń, W. Szaniec, and P. Zabojszcza, “Probabilistic approach to limit states of a steel dome”, Materials, vol. 14, no. 19, art. no. 5528, pp. 1-20, 2021, doi: 10.3390/ma14195528.
[13] A. Dudzik and U. Radoń, “The evaluation of algorithms for determination of the reliability index”, Archives of Civil Engineering, vol. 61, no. 3, pp. 133-147, 2015, doi: 10.1515/ace-2015-0030.
[14] K.Kubicka and U. Radoń, “The impact of support type on the reliability of steel trusses subjected to the action of a fire”, Applied Sciences-Basel, vol. 10, no. 21, art. no. 7916, pp. 1-21, 2020, doi: 10.3390/app10217916.
[15] K. Kubicka and U. Radoń, “Proposal for the assessment of steel truss reliability under fire conditions”, Archives of Civil Engineering, vol. 61, no. 4, pp. 141-154, 2015, doi: 10.1515/ace-2015-0041.
[16] K. Kubicka and U. Radoń, “Influence of the buckling coefficient randomness on the reliability index value under fire conditions”, Archives of Civil Engineering, vol. 64, no. 3, pp. 173-179, 2018, doi: 10.2478/ace- 2018-0037.
[17] A. Dudzik and B. Potrzeszcz-Sut, “Hybrid approach to the first order reliability method in the reliability analysis of a spatial structure”, Applied Sciences-Basel, vol. 11, no. 2, art. no. 648, pp. 1-17, 2021, doi: 10.3390/app11020648.
[18] W. McCulloch and W. Pitts, “A logical calculus of the ideas immanent in nervous activity”, Bulletin of Mathematical Biophysics, vol. 5, pp. 115-133, 1943.
[19] J. H. Argyris, et al., “Finite element method for geometrically nonlinear problems”, in Computational methods in non-linear mechanics. Wrocław: Ossolineum, 1977.
[20] K. J. Bathe, Finite element procedure in engineering analysis. New York: Prentice Hall, 1982.
[21] P. G. Bergan, “Solution techniques for nonlinear finite element problems”, International Journal for Numerical Methods Engineering, no. 12, pp. 1677-1696, 1978.
[22] M. A. Crisfield, Non-linear finite element analysis of solids and structures, vol. 2: advanced topics. Chichester, UK: J. Wiley & Sons, 2000.
[23] Z. Waszczyszyn, “Artificial neural networks in civil engineering: another five years of research in Poland”, Computer Assisted Methods in Engineering and Science, vol. 18, no. 3, pp. 131-146, 2017.
[24] J. Garret, “Where and why artificial neural networks are applicable in civil engineering”, Journal of Computing in Civil Engineering, ASCE, vol. 8, no. 2, pp. 129-130, 1994.
[25] M. Linek and P. Nita, “Neural networks in diagnostics of concrete airfield pavements”, Roads and Bridges - Drogi i Mosty, vol. 21, no. 1, pp. 81-97, doi: 10.7409/rabdim.022.005.
[26] J. V. Kozubal, W. Puła, and M. Stach, “Pile in the unsaturated cracked substrate with reliability assessment based on neural networks”, KSCE Journal of Civil Engineering, vol. 23, pp. 3843-3853, 2019, doi: 10.1007/s12205-019-1537-5.
[27] M. Linek, “Neural model of projecting flexural strength of cement concrete intended for airfield pavements”, IOP Conference Series: Materials Science and Engineering, vol. 664, Proceedings of the 11th International Scientific Conference on Aeronautics, Automotive and Railway Engineering and Technologies, BulTrans-2019, pp. 1-8, 2019, doi: 10.1088/1757-899X/664/1/012013.
[28] A. I. Galushkin, Neural networks theory. Berlin, Heidelberg: Springer-Verlag,2007.
[29] J. Hertz, A. Krogh, and R. Palmer, Introduction to the theory of neural computation. Warszawa: WNT, 1995.
[30] D. Marquardt, “An algorithm for least squares estimation of non-linear parameters”, Journal of the Society for Industrial and Applied Mathematics, vol. 11, no. 2, pp. 431-441, 1963.
[31] M. Hudson Beale, M. Hagan, and H. Demuth, Deep Learning Toolbox™. User’s Guide. The MathWorks, Inc. See, 2022.
[32] MathWorks, MATLAB®Primer. The MathWorks. Inc, 1984.
[33] F. Pukelsheim, “The Three Sigma Rule”, The American Statistician, vol. 48, no. 2, pp. 88-91, 1994.
Downloads
Published
How to Cite
Issue
Section
