An Effective Damage Evaluation Method for Crane Girder Based on SVI and LSSVM

Abstract:

Health assessment of the girder is crucial to an overhead traveling crane. This paper presents an intelligent damage identification method for the girder based on stiffness variation index (SVI) and least squares support vector machine (LSSVM). In the method, the SVI indicators, which have high resolution to environmental noise, serve as the damage feature to detect damage locations. Moreover, the SVI indicators are input to the LSSVM classifier for identifying the actual damage level of the girder. A case study on girder damage identification demonstrates that the method could determine the actual conditions of the girder structure accurately.

• Periodical: Applied Mechanics and Materials (Volumes 602-605)
• Pages: 370-374
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.602-605.370
• Online since: August 2014
• Authors: Hong Bo Xu*, Jia Yu Li
• Keywords: Damage, Girder, Health Assessment, LSSVM, SVI

References

[1] A.K. Pandey, M. Biswas and M.M. Samman, Damage detection from changes in curvature mode shapes, J Sound Vib. 145(2) (1991)321-332.

DOI: 10.1016/0022-460x(91)90595-b

[2] Y. Yang, X.Y. Zhou, G.F. Jin, and H. Liu, Modified direct stiffness method for the damage detect- ion of continuous beam-type structures, Engineering mechanics. 27(7) (2010)82-91. (In Chinese).

[3] V.N. Vapnik, Statistical Learning Theory, John Wiley, New York, 1998, pp.169-183.

[4] D.A. Pierre, Optimization theory with applications, John Wiley & Sons Inc, New York, 1969. pp.211-233.