基于多尺度核函数的铆接件腐蚀疲劳预测
目前腐蚀疲劳破坏预测方法精度不高。提出基于小波多分辨分析法（MRA）,在再生核希尔伯特空间构建一种多尺度核函数的最小二乘支持向量机（multi-scale kernel LSSVM,MSK_LSSVM）预测算法。根据Mercer平移不变核定理,构造了多尺度复Gaussian小波核函数。由于多尺度核函数能够通过平移生成L2（R2）子空间的一组完备基,因此MSK_LSSVM可以任意逼近目标函数,更具灵活性。经仿真实验验证,与BP神经网络方法、标准支持向量机、灰色系统预测模型方法对比,机械结构中铆接件腐蚀变化的趋势通过MSK_LSSVM预测,准确率高、时间短。...
Saved in:
| Published in | 计算机应用研究 Vol. 32; no. 4; pp. 1074 - 1077 |
|---|---|
| Main Author | |
| Format | Journal Article |
| Language | Chinese |
| Published |
西南科技大学制造科学与工程学院,四川绵阳,621010%西南科技大学制造过程测试技术教育部重点实验室,四川绵阳,621010
2015
|
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Summary: | 目前腐蚀疲劳破坏预测方法精度不高。提出基于小波多分辨分析法（MRA）,在再生核希尔伯特空间构建一种多尺度核函数的最小二乘支持向量机（multi-scale kernel LSSVM,MSK_LSSVM）预测算法。根据Mercer平移不变核定理,构造了多尺度复Gaussian小波核函数。由于多尺度核函数能够通过平移生成L2（R2）子空间的一组完备基,因此MSK_LSSVM可以任意逼近目标函数,更具灵活性。经仿真实验验证,与BP神经网络方法、标准支持向量机、灰色系统预测模型方法对比,机械结构中铆接件腐蚀变化的趋势通过MSK_LSSVM预测,准确率高、时间短。 |
|---|---|
| Bibliography: | 51-1196/TP WANG Jing, CAI Yong, JIANG Gang （ a. School of Manufacturing Science ＆ Engineering, b. Key Laboratory of Testing Technology for Manufacturing Process Ministry of Education, Southwest University of Science ＆ Technology, Mianyang Sichuan 621010, China ） multi-resolution analysis method; multi-scale kernel; complex Gaussian wavelet; least squares support vector machine（LSSVM） Currently,the corrosion fatigue damage prediction method accuracy was low. This thesis proposed a method based on wavelet multi-resolution analysis（ MRA）,in the reproducing kernel Hilbert space to construct a multi-scale kernel least squares support vector machine prediction algorithm. According to Mercer translation invariant kernel function theorem,it constructed a multi-scale complex Gaussian wavelet kernel function. For multi-scale kernel function could generate a complete basis set of L2（ R2） subspace by panning. The MSK-LSSVM could approximate the objective function arbitrarily and it was more flexible. Through experimental ve |
| ISSN: | 1001-3695 |
| DOI: | 10.3969/j.issn.1001-3695.2015.04.027 |