CAJ | 학술논문

支持向量机(SVM)是在统计学习理论基础上发展起来的一种新的模式识别方法,SVM的基本思想是通过非线性变换将输入空间变换到一个高维空间,然后在这个新的空间中求取最优分类超平面。它在解决小样本、非线性及高维模式识别问题中表现出许多特有的优势,并能够推广应用到函数拟合等其他机器学习问题中。本文着重介绍选取 SVM及其如何成功诊断处理钢厂轧机 X射线测厚仪 CS值电压自动漂移等故障的实例,实践理论与应用并重。
지지향량궤(SVM)시재통계학습이론기출상발전기래적일충신적모식식별방법,SVM적기본사상시통과비선성변환장수입공간변환도일개고유공간,연후재저개신적공간중구취최우분류초평면。타재해결소양본、비선성급고유모식식별문제중표현출허다특유적우세,병능구추엄응용도함수의합등기타궤기학습문제중。본문착중개소선취 SVM급기여하성공진단처리강엄알궤 X사선측후의 CS치전압자동표이등고장적실례,실천이론여응용병중。
Support vector machines (SVM )is a new pattern recognition method developed on the basis of statistical learning theory,the basic idea of SVM is to input data into a high dimensional space by a nonlinear transformation,then the optimal separating hyper plane in this new space.It has many advantages in solving small sample,nonlinear and high dimen-sional pattern recognition problem,and can be applied to the function fitting to other machine learning problems.This paper focuses on the selection of SVM and how to successfully diagnosis example related processing steel mill X ray thickness gauge CS value automatic voltage drift failure,theory of practice and application.