STUDY ON THE PREDICTION MODEL OF THE SINGLE PILE VERTICAL BEARING CAPACITY BASED ON WAVELET PROBABILISTIC NEURAL NETWORK AND ITS USE
-
摘要: 分析小波概率神经网络(WPNN)与数据融合技术在预测单桩竖向承载力中的应用原理,建立基于小波概率神经网络和数据融合技术的预测模型。根据长期的工程实测资料,利用高层建筑物静载试验数据对模型进行检验,并选取典型的样本进行预测值的误差分析。结果表明,预测的结果与静载试验数据吻合较好,从而证实了WPNN预测方法具有较好的可靠性和工程应用价值。Abstract: It was analyzed that the applied principles of wavelet probabilistic neural network (WPNN) and data fusion technique in the prediction of single pile vertical bearing capacity, and a prediction model based on WPNN and data fusion technique was set up.This model was examined by the static load test data of tall buildings, and according to the measured data of long-term projects.The error analysis of the predicted values was also carried out by selecting typical specimens, the results showed that the predicted data agreed well with those of the static load test, which verified the better reliability and applied value of WPNN prediction method.
-
Key words:
- bearing capacity of piled foundation /
- wpnn /
- prediction of bearing capacity /
- prediction method /
- study
-
[2] 袁旭东.基于不完备信息土木工程结构损伤识别方法研究[D].大连: 大连理工大学,2005. 王建华.神经网络法预估水泥搅拌桩单桩沉降[J].土木工程学报,1996,29(1): 55-61. [3] 翁光远,王社良.悬壁板损伤数值模拟试验与WPNN 识别方法[J].西安工业大学学报,2009,29(3): 290-292. [4] 翁光远,王社良.基于BP 神经网络的损伤识别方法研究[J].华中科技大学学报: 城市科学版,2009,26(2): 16-18. [5] Yoshimnral S,Matsuda A,Yagawa A.New Regularization byTransformation for Neural Network Based Inverse Analyses and ItsApplication to Structure Identification[J].International Journal ofNumerical Methods in Engineering,1996,39(23): 3953-3968. [6] 翁光远.钢筋混凝土预制桩单桩竖向承载力分析[J].建筑技术,2009,40(7): 636-638. [7] 姚仰平,高永贵,韩昌.西安地区桩基静载荷试验资料汇编[M].西安: 陕西科学技术出版社,1999
点击查看大图
计量
- 文章访问数: 118
- HTML全文浏览量: 9
- PDF下载量: 105
- 被引次数: 0