Prediction Method of Vertical Ultimate Bearing Capacity of Single Pile Based on Support Vector Machine

Autor: Yong Jian Liu, Shi Hua Liang, Jia Wu Wu, Na Fu
Rok vydání: 2010
Předmět:
Zdroj: Advanced Materials Research. :2278-2282
ISSN: 1662-8985
DOI: 10.4028/www.scientific.net/amr.168-170.2278
Popis: By comprehensively analyzing the main factors affecting vertical ultimate bearing capacity of single pile, a prediction model of Support Vector Machine (SVM), which discusses the nonlinear relationship between vertical ultimate bearing capacity of single pile and influencing factors and analyzes the parameters on the performance of the model through sample knowledge learning, is established in this paper. The research results indicate that, SVM model, which is compared with BP neural networks model, possesses simple structure, flexible adaptability, high precision and powerful generalization ability, and can accurately reflect the actual mechanical characteristics of pile, therefore, SVM is an effective method for predicting vertical ultimate bearing capacity of single pile.
Databáze: OpenAIRE