| 一维热传导方程热源反问题基于最小二乘法的正则化方法 |
| |
| 引用本文： | 吴自库,李福乐,DO Young Kwak.一维热传导方程热源反问题基于最小二乘法的正则化方法[J].计算物理,2016,33(1):49-56. |
| |
| 作者姓名： | 吴自库 李福乐 DO Young Kwak |
| |
| 作者单位： | 1. 青岛农业大学理学与信息科学学院, 青岛;2. 韩国科技学院数学系, 韩国 大田 |
| |
| 基金项目： | 山东省高等学校优秀中青年骨干教师国际合作培养计划，国家自然科学基金，山东省自然科学基金 |
| |
| 摘 要： | 研究一维热传导方程热源反问题.给出基于最小二乘支持向量机（LS-SVM）求解的半解析表达式，此外还给出一种参数调节方法以及算法稳定性的证明.数值实验表明该方法具有较高的数值精度和稳定性.
|
| 关 键 词： | 最小二乘支持向量机 一维热传导方程 源项反问题 二次规划 |
| 收稿时间： | 2014-12-29 |
| 修稿时间： | 2015-04-21 |
Least Squares Regularized Method for One-Dimensional Source Inverse Heat Conduction Problem |
| |
| WU Ziku,LI Fule,DO Young Kwak.Least Squares Regularized Method for One-Dimensional Source Inverse Heat Conduction Problem[J].Chinese Journal of Computational Physics,2016,33(1):49-56. |
| |
| Authors: | WU Ziku LI Fule DO Young Kwak |
| |
| Institution: | 1. Science and Information College, Qingdao Agricultural University, Qingdao, China;2. Department of Mathematical Sciences, Korea Advanced Institute of Science and Technology, Daejeon, Korea |
| |
| Abstract: | We deal with one-dimensional source inverse heat conduction equation. An approach based on least squares support vector machines (LS-SVM) is proposed for semi-analytic approximate solutions. Furthermore, a parameters tuning formulism is shown and stability of the method is presented. The method yields high accuracy and stability solutions in practical examples. |
| |
| Keywords: | least squares support vector machines one-dimensional heat conduction equation source inverse problem quadratic programming |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《计算物理》浏览原始摘要信息 |
| 点击此处可从《计算物理》下载免费的PDF全文 |
