预测钢筋混凝土预制桩竖向极限承载力的ANN方法研究  

Using ANN to Predict The Ultimate Bearing Capacity of Precast Reinforced Concrete Piles

作　　者：张志军[1] 周泉[1] 丁德馨[1] 孟小敏 

机构地区：[1]南华大学核资源与安全工程学院,湖南衡阳421001 [2]石家庄石房房产测绘所,河北石家庄050000

出　　处：《南华大学学报（自然科学版）》2008年第1期5-8,共4页Journal of University of South China：Science and Technology

基　　金：湖南省教育厅资助项目(05C491)

摘　　要：传统的钢筋混凝土预制桩极限承载力预测方法,难以考虑单桩极限承载力影响因素的模糊性和相互作用关系.本文提出并建立了预测钢筋混凝土预制桩极限承载力的人工神经网络方法,收集了某地区的41例钢筋混凝土预制桩,利用其中37例的实测数据建立了预测单桩极限承载力的ANN模型,另外的4例检验了模型的预测性能.研究结果表明,所建立的ANN方法的预测精度能够满足工程应用要求.The traditional methods for predicting the ultimate bearing capacity of precast reinforced concrete piles can not consider the fuzziness and inter - influence of the factors influencing the ultimate bearing capacity. ANN was used to establish an ANN based approach for predicting the ultimate bearing capacity of precast reinforced concrete piles. 41 examples of precast reinforced concrete piles were accumulated from an area in China. 37 examples of them were used to build a new prediction model for the ultimate bearing capacity. The model was then used to predict the ultimate bearing capacity of the rest 4 examples. A comparison was conducted between the predicted results and the practical measurements. The comparison results show that the approach has enough accuracy to meet demands of engineering completly.

关 键 词：预制桩 承载力 人工神经网络 

分 类 号：TU413.62[建筑科学—岩土工程] TU457[建筑科学—土工工程]