Structural reliability analysis of elastic-plastic structures using neural networks and Monte Carlo simulation. (English) Zbl 0893.73079
Summary: This paper examines the application of neural networks (NN) to the reliability analysis of complex structural systems in connection with Monte Carlo simulation (MCS). The failure of the system is associated with the plastic collapse. The use of NN was motivated by the approximate concepts inherent in reliability analysis and the time consuming repeated analyses required for MCS. A back propagation algorithm is implemented for training the NN utilizing available information generated from selected elastoplastic analyses. The trained NN is then used to compute the critical load factor due to different sets of basic random variables leading to close prediction of the probability of failure. The use of MCS with importance sampling further improves the prediction of the probability of failure with neural networks.
MSC:
| 74S30 | Other numerical methods in solid mechanics (MSC2010) |
| 74R99 | Fracture and damage |
| 65C05 | Monte Carlo methods |
| 62N05 | Reliability and life testing |
Keywords:
plastic collapse; back propagation algorithm; critical load factor; basic random variables; importance samplingReferences:
| [1] | Shinozuka, M., Basic analysis of structural safety, J. Struct. Engrg. ASCE, 109, 721-739 (1983) |
| [2] | Madsen, H. O.; Krenk, S.; Lind, N. C., Methods of Structural Safety (1986), Prentice-Hall: Prentice-Hall Englewood Cliffs, NJ |
| [3] | Thoft-Chrinstensen, P., Reliability and optimisation of structural systems ’88, (Proceedings of the 2nd IFIP WG7.5. Proceedings of the 2nd IFIP WG7.5, London (1988), Springer-Verlag) |
| [4] | Deodatis, G.; Shinozuka, M., Weighted integral method II: Response variability and reliability, J. Engrg. Mech. ASCE, 117, 1865-1877 (1991) |
| [5] | Spanos, P. D.; Brebbia, C. A., Computational stochastic mechanics (1991), Computational Mechanics Publications · Zbl 0786.73004 |
| [6] | Kam, T. Y.; Corotis, R. B.; Rossow, E. C., Reliability of non-linear framed structures, J. Struct. Engrg. ASCE, 109, 1585-1601 (1983) |
| [7] | Fujimoto, Y.; Iwata, M.; Zheng, Y., (Spanos, P. D.; Brebbia, C. A., Fitting-adaptive importance sampling reliability analysis, computational stochastic mechanics (1991), Computational Mechanics Publications), 15-26 |
| [8] | Pulido, J. E.; Jacobs, T. L.; De Lima, E. C.Prates, Structural reliability using Monte-Carlo simulation with variance reduction techniques on elastic-plastic structures, Comput. Struct., 43, 419-430 (1992) |
| [9] | Berke, L.; Hajela, P., Applications of artificial neural nets in structural mechanics, NASA 331-348 TM-102420 (1990) |
| [10] | Berke, L.; Patnaik, S. N.; Murthy, P. L.N., Optimum design of aerospace structural components using neural networks, Comput. Struct., 48, 1001-1010 (1993) · Zbl 0800.73267 |
| [11] | Fu, B.; Hajela, P., Minimising distortion in truss structures—A Hopfleld network solution, Comput. Syst. Engrg., 4, 69-74 (1993) |
| [12] | Melosh, R. J.; Berke, L.; Marcal, P. V., Knowledge-based consultant for selecting a structural analysis strategy, (NASA Conference Publication 2059 (1987)) |
| [13] | Theocaris, P. S.; Panagiotopoulos, P. D., Neural networks for computing in fracture mechanics. Methods and prospects of applications, Comput. Methods Appl. Mech. Engrg., 106, 213-228 (1993) · Zbl 0782.73077 |
| [14] | Khan, A. I.; Topping, B. H.V.; Bahreininejad, A., Parallel training of neural networks for finite element mesh generation, (Topping, B. H.V.; Khan, A. I., Neural Networks and Combinatorial Optimisation in Civil and Structural Engineering (1993), Civil-Comp Press), 81-94 · Zbl 0899.73521 |
| [15] | Rummelhart, D. E.; McClelland, J. L., Parallel Distributed Processing, (Foundations, Vol. 1 (1986), The MIT Press: The MIT Press Cambridge) |
| [16] | Papadrakakis, M.; Karamanos, S. A., A simple and efficient solution method for the limit elastoplastic analysis of plane frames, J. Comput. Mech., 8, 235-248 (1991) · Zbl 0850.73367 |
| [17] | Papadrakakis, M.; Papadopoulos, V., A computationally efficient Method for the limit elastoplastic analysis of space frames, Comput. Mech. J., 16, 2, 132-141 (1995) · Zbl 0839.73071 |
| [18] | Rubinstein, R. Y., Simulation and the Monte Carlo Method (1981), John Wiley & Sons · Zbl 0529.68076 |
| [19] | Melchers, R. E., Structural reliability: Analysis and Prediction (1987), Ellis Horwood, John Wiley and Sons: Ellis Horwood, John Wiley and Sons Chishester |
| [20] | Bucher, C. G., Adaptive Sampling—An iterative fast Monte Carlo procedure, Structural Safety, 5, 119-126 (1988) |
| [21] | Karamchandani, A.; Cornell, C. A., Adaptive hybrid conditionals expectation approaches for reliability estimation, Structural Safety, 11, 59-74 (1991) |
| [22] | Schueller, G. I.; Ang, A. H-S., Advances in structural reliability, J. Nucl. Engrg., 39, 55-66 (1991) |
| [23] | Orbinson, J. G.; McGuire, W.; Abel, J. F., Yield surface applications in non-linear steel frames analysis, Comput. Methods Appl. Mech. Engrg., 33, 557-573 (1982) · Zbl 0478.73057 |
| [24] | Ueda, Y.; Yao, T., The plastic node method: A new method of plastic analysis, Comput. Methods Appl. Mech. Engrg., 34, 1089-1104 (1982) · Zbl 0497.73037 |
| [25] | Bitoulas, N.; Papadrakakis, M., An optimised computer implementation of the incomplete Cholesky factorisation, Comput. Syst. Engrg., 5, 3, 265-274 (1994) |
| [26] | Pao, Y. H., Adaptive Pattern Recognition and Neural Networks (1989), Addison-Wesley Publishing Co · Zbl 0748.68061 |
| [27] | Hirose, Y.; Yamashita, K.; Hijiya, S., Back-propagation algorithm which varies the number of hidden units, Neural Networks, 4, 61-66 (1991) |
| [28] | Baffes, P. T., (Nets user’s guide (1989), NASA, Lyndon B. Johnson Space Centre), version 2.01 |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
