摘要
在智能岩石力学的研究方法中,专家系统方法是基于专家和经验判断进行问题求解的非数值分析方法,因为领域知识获取的困难,限制了其发展;而神经网络方法是基于大样本的一种方法,其推广能力较差.为了克服专家系统知识获取的“瓶颈”问题和人工神经网络的推广能力差的问题,基于统计学习理论的支持向量机方法为岩土工程的智能化研究提供了新的途径.主要介绍了支持向量机方法及其在岩土工程领域的应用现状,并指出其理论存在的问题和未来的发展方向.
Support vector machine is a kind of novel machine with learning methods, and it is fitful for the problem that can't be solved with traditional mathematical model. It has become the hotspot of machine learning because of their excellent learning performance, and now there are a lot of study on application of SVM. In this paper, the method of SVM and its application in geotechnical engineering were introduced, and some limitations and future research direction were also discussed.
出处
《宁夏工程技术》
CAS
2005年第2期160-164,共5页
Ningxia Engineering Technology
关键词
统计学习理论
支持向量机
应用
岩土工程
反分析
statistical learning theory
support vector machines
application
geotechnical engineering
anti-analysis
