Structure Fault Diagnosis of Tower Crane Based on Wavelet Packet Analysis and Support Vector Machines

Abstract:

First establish a dynamic model of tower crane in the load lifting process, the lifting load is solved under two work conditions.Then establish the FEM(finite element analysis) model of the tower crane under the normal and the damage condition. Get the dynamic displacement of the normal and the damage status under the lifting dynamic load. With wavelet packet decomposition and SVM(Support vector machines) multi-classification algorithm, a multi-fault classifier is constructed, and applied to the fault diagnosis of tower body. The results of the study show that the multi-fault classifier has such advantages as simple algorithm and excellent capability of fault classification, and it can not only diagnose the structural damage status, but also determine the positions of structural damage. This will be a new search on tower crane structural health diagnosis.

• Periodical: Applied Mechanics and Materials (Volumes 325-326)
• Pages: 294-298
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.325-326.294
• Online since: June 2013
• Authors: Sheng Chun Wang, Rong Sheng Shen, Shi Jun Song, Yan Tian
• Keywords: Structural Damage, Support Vector Machine (SVM), Tower Crane, Wavelet Packet

References

[1] Haijiang Jiang. Researches About the Dynamic Characteristics of the Portal. Wuhan University of technology, (2006).

[2] Yang YU, Zegnang Han. The Modeling Analysis for Tower Crane Based on Finite Element technology, 20(3)(2007) , pp.93-95.

[3] Rui Li. Based on the dynamic characteristics of the bridge damage identification research. Chang'an University, 5(2009).

[4] S.X. Jing, W.Hua, "Study on the Gear Fault Diagnosis Based on Wavelet support Vector Machine," Journal of Shandong University of Science and Technology, 27(2008) , p.31–36.