Truncated-Newton training algorithm for neurocomputational viscoplastic model

Computer Methods in Applied Mechanics and Engineering

Volumn 192, Issue 19, 2003, Pages 2249-2267

  Al Haik, M S ^a   Garmestani, H ^b   Navon, I M ^a  

^a FLORIDA STATE UNIVERSITY   (United States)

^b Georgia Institute of Technology   (United States)

Author keywords

Neural networks; Optimization creep; Truncated Newton method; Viscoplasticity

Indexed keywords

ALGORITHMS; COMPOSITE MATERIALS; CREEP; NEURAL NETWORKS; OPTIMIZATION;

TRAINING ALGORITHMS;

VISCOPLASTICITY;

NEURAL NETWORK;

EID: 0038318994     PISSN: 00457825     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0045-7825(03)00261-5     Document Type: Article

References (56)

1. Al-Haik, M., & Garmestani, H. (2001). Durability study of a polymeric composite material for structural applications. J. Polym. Comp., 22(6), 779-792.
2. M. Al-Haik, Durability of a polymer matrix composite, a neural networks Approach, Ph.D. Thesis, Department of Mechanical Engineering, Florida Sate University, 2002
3. Al-Haik, M., Vaghar, M. R., Garmestani, H., & Shahawy, M. (2001). Viscoplastic analysis of structural polymer composites using stress relaxation and creep data. Compos. Part B--Engrg., 32 165-170.
4. Battiti, R. (1989). Accelerated backpropagation learning: Two optimization methods. Complex Syst., 3 331-342.
5. J. Corum, Durability of Polymer Matrix Composites for Automotive Structural Applications: A State of the Art Review, Technical Report ORNL-6869, Oak Ridge National Laboratory, 1995
6. Dembo, P. S., & Steihaug, T. (1983). Truncated Newton algorithms for large-scale unconstrained optimization. Math. Program., 26 190-212.
7. Dillard, D. A. (1991). Viscoelastic Behavior of Laminated Composite Materials. England: Elsevier Applied Science Publishers Ltd..
8. Fletcher, R. (1987). Practical methods of optimization. : John Wiley and Sons.
9. Fletcher, R., & Reeves, C. (1964). Function minimization by conjugate gradients. Computer J., 7 149-154.
10. Franke, L., & Meyer, H. J. (1992). Predicting the tensile strength and creep-rupture behavior of pultruded glass reinforced polymer rods. J. Mater. Sci., 27 4899-4908.
11. Furukawa, T., & Yagawa, G. (1998). Implicit constitutive modeling for viscoplasticity using neural networks. Int. J. Numer. Meth. Engrg., 195-219.
12. H. Garmestani, M.S. Al-Haik, S. Downey, Durability analysis of an autoclave structural polymer composite using stress relaxation and creep data, in: Proc. CANCOM'2001, Quebec, Canada, 2001, pp. 136-141
13. T.S. Gates, Matrix dominated stress/strain behavior in polymeric composites: effects of hold time, nonlinearity and rate dependency, in: E.T. Camponeschi, Jr. (Ed.), Composite Materials: Testing and Design, vol. 11, ASTM STP 1206, American Society for Testing and Material, 1993, pp. 177-189
14. T.S. Gates, Effects of elevated temperature on the viscoplastic modeling of graphite/polymeric composites, in: C.E. Harris, T.S. Gates (Eds.), High Temperature and Environmental Effects on Polymeric Composites, ASTM STP 1174, American Society for Testing and Material, 1991, pp. 201-221
15. Gates, T. S., & Sun, C. T. (1991). Elastic/viscoplastic constitutive model for fiber reinforced thermoplastic composites. AIAA, 29(3), 457-463.
16. T.S. Gates, J.L. Chen, C.T. Sun, Micromechanical characterization of nonlinear behavior of advanced polymer matrix composites, in: C.R. Saff, R.B. Deo (Eds.), Composite Materials: Testing and Design, vol. 12, ASTM STP 1274, American Society for Testing and Materials, 1995, pp. 295-319
17. Gill, P. E., & Murray, W. (1974). Newton-type methods for unconstrained and linearly constrained optimization. Math. Program., 28 311-350.
18. Ghaboussi, J., Garrett, J. H., & Wu, X. (1991). Knowledge-based modeling of materials behavior with neural networks. J. Engrg. Mech--ASCE, 117(1), 132-153.
19. Haplin, J. C. (1968). Introduction to Viscoelasticity. : Technomic Publishing Co..
20. Hart, E. W., & Solomon, H. D. (1973). Load relaxation studies of polycrystalline high purity aluminum. Acta. Metall. Mater., 21 295-307.
21. Haykin, S. (1999). Neural Networks: A Comprehensive Foundation. New Jersey: Prentice Hall.
22. Hornik, K. (1991). Approximation capabilities of multilayer feedforward networks. Neural Networks, 4 251-257.
23. Hornik, K., Stinchocombe, M., & White, H. (1989). Multilayer feedforward networks are universal approximators. Neural Networks, 2 359-366.
24. Johansson, E. M., Dowla, F. U., & Goodman, D. M. (1991). Backpropagation learning for multi-layer feedforward neural networks using the conjugate gradient method. Int. J. Neural Syst., 2 291-302.
25. Le Dimet, F. X., Navon, I. M., & Daescu, D. N. (2002). Second order information in data assimilation. Mon. Weather Rev., 130 629-648.
26. Li, C. J., & Ray, A. (1995). Neural network representation of fatigue damage dynamics. Smart Mater. Struct., 4 126-133.
27. Liu, M. C., & Krempl, E. (1979). A uniaxial viscoplastic model based on total strain and overstress. J. Mech. Phys. Solids, 27 377-391.
28. Mukherjee, A., & Biswas, S. N. (1997). Artificial neural network in prediction of mechanical behavior of concrete at high temperature. Nucl. Engrg. Des., 178(4), 1-11.
29. Nash, S. G. (1984). Newton-type minimization via the Lanczos method. SIAM J. Numer. Anal., 21 770-788.
30. Nash, S. G. (1985). Preconditioning of truncated Newton methods. SIAM J. Sci. Stat. Comp., 6 599-616.
31. Nash, S. G., & Nocedal, J. (1991). A numerical study of the limited memory BFGS method and the truncated-Newton method for large scale optimization. SIAM J. Optimiz., 1 358-372.
32. Nash, S. G., & Sofer, A. (1989). Block truncated-Newton methods for parallel optimization. Math. Program., 45 529-546.
33. Nash, S. G., & Sofer, A. (1990). Assessing a search direction within a truncated Newton method. Oper. Res. Lett., 9 219-221.
34. Nash, S. G., & Sofer, A. (1996). Linear and Nonlinear Programming. : McGraw-Hill.
35. Navon, I. M., Zou, X., Berger, M., Phua, P. K., Schlick, T., & Le Dimet, F. X. (1992). Numerical experience with limited memory quasi-Newton and truncated Newton methods. In K. Phua (Ed.), Optimization Techniques and Applications, 33-48. : World Scientific Publishing Co..
36. Navon, I. M., Zou, X., Berger, M., Phua, P. K., Schlick, T., & Le Dimet, F. X. (1992). Testing for reliability and robustness of optimization codes for large scale optimization problems. In K. Phua (Ed.), Optimization Techniques and Applications, 445-480. : World Scientific Publishing Co..
37. Nocedal, J., & Wright, S. (1999). Numerical Optimization. : Springer-Verlag.
38. B.D. Parker, Second order backpropagation, in: IEEE First International Conference on Neural Networks, vol. 2, 1987, pp. 593-600
39. Pertez, D., & Weitsman, Y. (1966). Nonlinear viscoelastic characterization of FM-73 adhesive. J. Rheology, 26(3), 245-261.
40. Principe, J. C., Euliano, N. R., & Lefebvre, W. C. (2000). Neural and Adaptive Systems: Fundamentals through Simulations. New York: John Wiley and Sons Inc..
41. Robertson, D., & Mall, S. (1994). Micromechanical analysis for thermoviscoplastic behavior of unidirectional fibrous composites. Comp. Sci. Tech., 50 483-496.
42. Schalkoff, R. (1997). Artificial Neural Networks. New York: McGraw-Hill Inc..
43. Schapery, R. A. (1965). A method of viscoelastic stress analysis using elastic solutions. J. Franklin Inst., 279(74), 268-289.
44. Schapery, R. A. (1966). An engineering theory of nonlinear viscoelasticity with applications. Int. J. Solids. Struct., 2 407-425.
45. Schapery, R. A. (1968). Stress Analysis of Viscoelastic Composite Materials. : Technomic Publishing Co..
46. E. Shin, R. Morgan, Performance evaluation of glass fiber-epoxy composites for durable goods applications, in: Proceedings of the 10th Annual ASM/ESD Advanced Composites Conference, 1994, pp. 545-554
47. Schlick, T., & Fogelson, A. (1992). TNPACK: A truncated Newton minimization package for large-scale problems: I. algorithm and usage. ACM Trans. Math. Soft., 18 46-70.
48. Skinner, A., & Broughton, J. (1995). Neural networks in computational materials science: Training algorithms. Model. Simul. Mater. Sci. Engrg., 3 371-390.
49. Sun, C. T., & Chen, J. L. (1991). A micromechanical model for plastic behavior of fibrous composites. Comp. Sci. Tech., 40 115-129.
50. Sun, C. T., & Chang, I. (1992). Modeling of elastic-plastic behavior of IDF and continuous fiber reinforced AS-4/PEEK composites. Comp. Sci. Tech., 43 339-345.
51. Wang, Z., Navon, I. M., Zou, X., & Le Dimet, F. X. (1995). Truncated-Newton optimization algorithm in meteorology applications with analytic Hessian vector products. Comput. Optim. Appl., 4 241-262.
52. Wang, Z., Droegemeier, K. K., White, L., & Navon, I. M. (1997). Application of a new adjoint Newton algorithm to the 3-d ARPS storm scale model using simulated data. Mon. Weather Rev., 125 2460-2478.
53. P. Werbos, Backpropagation past and future, in: IEEE International Conference of Neural Networks, vol. 1, 1988, pp. 343-353
54. X. Wu, Neural network based material modeling, Ph.D. Thesis, Department of Civil Engineering, University of Illinois at Urbana-Champaign, 1991
55. Yeh, I. C. (1999). Modeling of strength of high-performance concrete using artificial neural networks. Cement Concrete Res., 28(12), 1797-1808.
56. Zou, X., Navon, I. M., Berger, M., Phua, P. K., Schlick, T., & Le Dimet, F. X. (1993). Numerical experience with limited memory quasi-Newton methods and truncated Newton methods. SIAM J. Optimiz., 3 582-608.