Neural network for structural stress concentration factors in reliability-based optimization

Abstract

Stress concentration damage is one of the most troublesome problems in practical engineering structures. In order to reduce damage, it is very important to determine stress concentration factors accurately. An artificial neural network (NN) technique has been used in this article to simulate the relationship between basic random variables and stress concentration factors, and the explicit expression of the stress concentration factors can be obtained directly. The expression of the stress concentration and the reliability theory have been combined to solve the structural reliability problems; then, the corresponding methods of reliability analysis and optimization design have been presented.

Keywords

stress concentration factors artificial neural network probabilistic perturbation method reliability-based optimization

Get full access to this article

View all access options for this article.

References

Walter

P. D.

Peterson's stress concentration factors, 2nd edition, 1997 (John Wiley and Sons, New York).

Pehan

Hellen

T. K.

Flasker

Glodez

Numerical methods for determining stress intensity factors vs crack depth in gear tooth roots. Int. J. Fatigue, 1997, 19 (10), 677–685.

Reifsnider

Case

Duthoit

The mechanics of composite strength evolution. Compos. Sci. Technol., 2000, 60 (12–13), 2539–2546.

Mollenhauer

Reifsnider

Measurements of interlaminar deformation along the cylindrical surface of a hole in laminated composite materials by Moire interferometry. Compos. Sci. Technol., 2000, 60 (12–13), 2375–2388.

Robinson

P. A.

Swift

K. G.

Raines

Graham

R. H.

Peckover

Gill

An expert system for the determination of stress concentration factors. Proc. Instn Mech. Engrs, Part G: J. Aerospace Engineering, 2001, 215 (G4), 219–228.

Arola

Williams

C. L.

Estimating the fatigue stress concentration factor of machined surfaces. Int. J. Fatigue, 2002, 24 (9), 923–930.

Nando

Gaetano

Carlos

Simultaneous considerations of length and boundary conditions on theoretical stress concentration factors. Int. J. Fatigue, 2003, 25, 353–355.

Fujimoto

Cao

F. Y.

Nisitani

Approximate formula for estimating stress concentration factors for V-notched cylindrical specimens. Adv. Fracture Damage Mech. Key Eng. Mat., 2003, 251 (2), 261–266.

Haykin

Neural networks, 2nd edition, 1999 (Prentice-Hall, Inc., New Jersey).

10.

Papadrakakis

Papadopoulos

Computationally efficient method for the limit elasto plastic analysis of space frames. Comput. Mech., 1995, 16 (2), 132–141.

11.

Chen

T. P.

Chen

Liu

R. W.

Approximation capability in C(R over-barⁿ) by multilayer feedforward networks and related problems. IEEE Trans. Neural Netw., 1995, 6 (1), 25–30.

12.

Zhang

Y. M.

Liu

Q. L.

Practical reliability-based analysis of coil tube-spring. Proc. Instn Mech. Engrs, Part C: J. Mechanical Engineering Science, 2002, 216 (C2), 179–182.

13.

Zhang

Y. M.

Liu

Q. L.

Reliability-based design of automobile components. Proc. Instn Mech. Engrs, Part D: J. Automobile Engineering, 2002, 216 (D6), 455–471.

14.

Zhang

Y. M.

Liu

Q. L.

Wen

B. C.

Quasi-failure analysis on resonant demolition of random structural systems. AIAAJ., 2002, 40 (3), 585–586.

15.

Zhang

Y. M.

Liu

Q. L.

Wen

B. C.

Practical reliability-based design of gear pairs. Mech. Mach. Theory, 2003, 38 (12), 1363–1370.

16.

Vetter

W. J.

Matrix Calculus operations and Taylor expansions. SIAM Rev., 1973, 15 (2), 352–369.

17.

Ang

A. H.S.

Tang

W. H.

Probability concepts in engineering planning and design, decision, risk, and reliability, 1984, vol. II (John Wiley and Sons, Inc., New York).

18.

Peterson

R. F.

Stress concentration factors, 1974 (Wiley-InterScience, New York).