Study and Application of Displacement Back Analysis Based on CACA-SVM

Abstract:

An new intelligent displacement back analysis, named as CACA-SVM, was proposed based on support vector machine (SVM) and Continuous Ant Colony Algorithm (CACA). On the one hand, CACA-SVM used SVM to build the nonlinear mapping relationship between them. On the other hand, CACA-SVM used the global optimization performance of CACA to search the optimal rock mechanics parameters in the global space. The nonlinear mapping relationship built by SVM can fit and forecast the measuring point displacements under different parameters with high accuracy, avoiding the complex numerical calculation. CACA can prevent object function from trapping in local optimum and improve precision of back analysis. Case study shows that the forecasting trend was in good agreement with the measured trend, which indicated that the model was suitable for solving the geotechnical engineering problem of nonlinearity and uncertainty and could well be applied to displacement back analysis.

• Periodical: Applied Mechanics and Materials (Volumes 353-356)
• Pages: 142-145
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.353-356.142
• Online since: August 2013
• Authors: Fei Xu*, Bin Li, Ke Wang
• Keywords: Continuous Ant Colony Algorithm, Displacement Back Analysis, Rock, Soil Mechanics Parameters, Support Vector Machine (SVM)

References

[1] A. Colorni, M. Dorigo, V. Maniezzo, in: Proceedings of the First European Conference on Artificial Life, edtied by Elsevier Publising, Paris (1991), in press.

[2] B.D. Yonas, V. Slavco: Journal of Computing in Civil Engineering, Vol. 7(2001), pp.208-216.

[3] H.B. Zhao, X.T. Feng: Chinese Journal of Rock Mechanics and Engineering, Vol. 22(2003), pp.1618-1622. (In Chinese).