摘要
为合理、准确地预测单桩竖向极限承载力,借助模糊神经网络较强的学习能力和模糊逻辑推理功能,建立了基于模拟退火算法的单桩竖向极限承载力预测模型,对收集到的样本进行了训练预测,并与常规的减法聚类算法预测结果进行了对比。分析结果表明:基于模拟退火算法的模糊神经网络模型预测单桩竖向极限承载力是可行有效的,具有较大的工程实用价值。
To predict vertical ultimate bearing capacity of single pile reasonably,with the strong learning ability and fuzzy logic functions,the predicting model of vertical ultimate bearing capacity of single pile based on the simulated annealing algorithm was established.The training and predicting of collected sample were carried out,and predicting results of the method were compared with those of conventional subtractive clustering algorithm.Analysis result shows that the fuzzy neural network model based on the simulated annealing algorithm is effective and feasible in predicting the vertical ultimate bearing capacity of single pile,and it has greater practical value in engineering.
出处
《建筑科学与工程学报》
CAS
2010年第4期25-30,共6页
Journal of Architecture and Civil Engineering
基金
国家自然科学基金项目(40772174)
关键词
单桩竖向极限承载力
模拟退火算法
模糊神经网络
预测模型
vertical ultimate bearing capacity of single pile
simulated annealing algorithm
fuzzy neural network
predicting model
