摘要
为实现对基坑变形的高精度预测,提高预测结果的稳定性,采用支持向量机、BP神经网络及GM(1,1)作为基础预测模型,并建立了对应各模型参数优化的一阶递进预测模型。以一阶递进预测结果为基础,构建了多种定权与非定权的二阶组合预测模型;以马尔可夫链理论为基础,建立了三阶递进的误差修正模型,实现了对基坑变形的多阶段递进式预测。结果表明:通过各阶段的递进预测,预测精度及稳定性都有了很大的提高,验证了递进预测思路的有效性和可行性。通过对基坑变形的递进式预测研究,以期为基坑的变形提供一种新的思路。
The aim of this research is to improve the precision of pit deformation prediction and of prediction results. Support vector machine, BP neural netw^ork and GM （1,1） are used model , and the corresponding first-order prediction models with parameters optimized are sis ,the second-order combinatorial forecasting model of multiple fixed weight and non-fixed In subsequence , on the basis of the Markov chain theory , the error correction and the progressive prediction of foundation pit deformation is realized. Results demonstrate that the prediction ac-curacy and stability are greatly improved by the progressive prediction of multiple and feasibility of the proposed method in this paper. The result is expected to provide a new^ idea for the predictionof foundation pit deformation.
出处
《长江科学院院报》
CSCD
北大核心
2017年第8期47-51,共5页
Journal of Changjiang River Scientific Research Institute
关键词
基坑
递进预测模型
支持向量机
BP神经网络
GM(1
1)模型
组合预测
误差修正
foundation pit
progressive prediction model
support vector machines
BPneural network
GM （ 1, 1）
combinatorial forecasting
error correction
