摘要
对影响深层搅拌桩复合地基承载力的因素进行了分析 ,并对现行的设计方法存在的问题进行探讨 ,提出利用人工神经网络带有偏差单元的IRN(InternallyRecurrentNet)模型对复合地基承载力进行计算的新思路。通过实例验证 ,该模型可达到较好的效果 ,为今后深层搅拌桩承载力设计计算提供了可借鉴的方法。
The infecting factors of the bearing capacity of compound foundation to deep mixing pile are analyzed,and the existing questions of the current design method to mixing pile are discussed in the paper.A new athematics model of IRN artificial neural network with error unit is set up and applied to the calculation of the bearing capacity of compound foundation to deep mixing pile.It can be verified that the model is ideal with the actual examples.The new method can be referenced to the reasonable design of deep mixing pile in the future.
出处
《建筑技术开发》
2002年第1期17-20,共4页
Building Technology Development
关键词
人工神经网络
IRN模型
深层搅拌桩
复合地基
承载力
Artificial neural network
IRN model
Deep mixing pile
Bearing capacity of compound foundation
