摘要
围岩的破坏受到多种因素的影响,并且各破坏模式之间没有明显的界限,因此其破坏模式的识别是一种模糊、非线性、小样本、高维数的模式识别问题。支持向量机(SVM)是最近发展起来的一种新机器学习技术,已在模式识别领域有很多成功地应用。基于支持向量机的思想,提出了围岩破坏模式识别的支持向量机方法,很好地表达了围岩破坏模式与其影响因素之间的复杂非线性关系。具体算例表明,该方法是可行的,具有一定的准确性。
The collapse of surrounding rock mass is affected by many factors, and the relationship between different collapse types has no distinct boundary, so the problem of recognition of collapse type is fuzzy, nonlinear, small samples and high dimensions. Support vector machine is a new machine learning technology, and there are a lot of successful application in the field of pattern recognition. This paper presents a new method based on support vector machine, and the complicated nonlinear relationship between type of collapse and its affected actors is presented well. The application of true example shows this method is feasible and precise.
出处
《岩土力学》
EI
CAS
CSCD
北大核心
2005年第2期235-238,共4页
Rock and Soil Mechanics
基金
绍兴市科技局科技计划项目(No.2004146)
院重点学科经费资助。
关键词
围岩
破坏模式
支持向量机
Finite automata
Learning algorithms
Pattern recognition
Pattern recognition systems
Rock mechanics
Rock pressure
