嵌岩桩单桩竖向承载力智能化评价预测  

The Study of System for Evaluating the Vertical Beadng Capacity of the pile

作　　者：蒋洪胜[1] 安雪蕾[1] 马全安 范涛[2] 万立华[2] 

机构地区：[1]山东建筑大学土木工程学院,山东济南250101 [2]济南市建筑工程质量监督站,山东济南250013

出　　处：《中国包装科技博览（混凝土技术）》2012年第4期54-56,共3页China Science and Technology Review

摘　　要：利用遗传算法的全局搜索能力和BP神经网络的高次非线性能力，用遗传算法优化BP神经网络，建立预测嵌岩桩竖向承载力的遗传-BP神经网络模型，用济南地区的现场试桩数据对模型进行训练和检测，证明该模型预测精度高，能更加真实的反映单桩竖向承载力的机理。Based on the back propagation neural networks improved by genetic algorithm, a new prediction model is founded for prediction of the vertical bearing capacity of rock-socked piles. The model is trained with in static loading pile testing data in Jinan region. It is shown that the predicted value of vertical bearing capacity of single pile has a good agreement with the site tested value, can be more a reflection of reality the mechanism of vertical beating capacity of the single pile.

关 键 词：嵌岩桩 静载荷试验 遗传算法 BP神经网络 单桩竖向承载力 

分 类 号：TU473.11[建筑科学—结构工程]