In this paper a hybrid process of modeling and optimization, which integrates a support vector machine （SVM） and genetic algorithm （GA）, was introduced to reduce the high time cost in structural optimization of sh...In this paper a hybrid process of modeling and optimization, which integrates a support vector machine （SVM） and genetic algorithm （GA）, was introduced to reduce the high time cost in structural optimization of ships. SVM, which is rooted in statistical learning theory and an approximate implementation of the method of structural risk minimization, can provide a good generalization performance in metamodeling the input-output relationship of real problems and consequently cuts down on high time cost in the analysis of real problems, such as FEM analysis. The GA, as a powerful optimization technique, possesses remarkable advantages for the problems that can hardly be optimized with common gradient-based optimization methods, which makes it suitable for optimizing models built by SVM. Based on the SVM-GA strategy, optimization of structural scantlings in the midship of a very large crude carrier （VLCC） ship was carried out according to the direct strength assessment method in common structural rules （CSR）, which eventually demonstrates the high efficiency of SVM-GA in optimizing the ship structural scantlings under heavy computational complexity. The time cost of this optimization with SVM-GA has been sharply reduced, many more loops have been processed within a small amount of time and the design has been improved remarkably.展开更多
超声波检测法是高压开关柜局部放电检测的一种有效方法,但目前基于超声波信号检测原理开发的局部放电检测产品主要有信号幅值检测、将信号降频至音频从而监听检测,具有检测结果不够准确、对检测人员要求较高等缺点。该研究提出了一种基...超声波检测法是高压开关柜局部放电检测的一种有效方法,但目前基于超声波信号检测原理开发的局部放电检测产品主要有信号幅值检测、将信号降频至音频从而监听检测,具有检测结果不够准确、对检测人员要求较高等缺点。该研究提出了一种基于偏最小二乘(partial least squares,PLS)特征降维和支撑向量机(support vector machine,SVM)的开关柜局部放电检测方法,首先计算超声音频信号的声学特征,并采用PLS进行降维处理,然后采用SVM分类器来区分局放和非局放音频信号。实验结果表明,所提方法比传统阈值方法具有更高的识别准确率,并且降低了对检测人员的要求,具有更好的普适性。展开更多
文中搭建了真空断路器试验平台,实现了主轴卡涩等四类机械故障状态。通过将正常及故障状态下的实测振动信号进行经验模态分解,得到所需要的内禀模态函数(intrinsic made function,IMF),利用能量法求出包含主要故障特征信息的各内禀模态...文中搭建了真空断路器试验平台,实现了主轴卡涩等四类机械故障状态。通过将正常及故障状态下的实测振动信号进行经验模态分解,得到所需要的内禀模态函数(intrinsic made function,IMF),利用能量法求出包含主要故障特征信息的各内禀模态函数分量的能量总量。利用IMF分量能量总量作为特征向量,并以此作为支持向量机输入,分析对比了不同分类策略、核函数的分类时间和分类准确率,经实验分析选用"一对其他"分类策略并且核函数为径向基函数的分类效果最优,为研制完善的断路器故障诊断系统提供理论依据及实际的数据基础。展开更多
提出一种基于改进最大相关最小冗余判据(maximal relevance and minimal redundancy,mRMR)的暂态稳定评估特征选择方法。首先对标准mRMR方法进行改进,在最大相关、最小冗余判据中引入一个权重因子以细化对特征相关性和冗余性的度量。然...提出一种基于改进最大相关最小冗余判据(maximal relevance and minimal redundancy,mRMR)的暂态稳定评估特征选择方法。首先对标准mRMR方法进行改进,在最大相关、最小冗余判据中引入一个权重因子以细化对特征相关性和冗余性的度量。然后,考虑相量测量单元可以提供的故障后实测信息,构造由系统特征构成的原始特征集,将改进的mRMR应用于特征选择。通过增量搜索算法得到一组嵌套的候选特征子集,并使用支持向量机分类器验证各候选特征子集的分类性能,选择得到具有最大分类正确率的特征子集。基于新英格兰39节点系统和IEEE 50机测试系统的算例结果验证了所提特征选择方法的有效性。展开更多
在机器学习领域,核方法是解决非线性模式识别问题的一种有效手段.目前,用多核学习方法代替传统的单核学习已经成为一个新的研究热点,它在处理异构、不规则和分布不平坦的样本数据情况下,表现出了更好的灵活性、可解释性以及更优异的泛...在机器学习领域,核方法是解决非线性模式识别问题的一种有效手段.目前,用多核学习方法代替传统的单核学习已经成为一个新的研究热点,它在处理异构、不规则和分布不平坦的样本数据情况下,表现出了更好的灵活性、可解释性以及更优异的泛化性能.结合有监督学习中的多核学习方法,提出了基于Lp范数约束的多核半监督支持向量机(semi-supervised support vector machine,简称S3VM)的优化模型.该模型的待优化参数包括高维空间的决策函数fm和核组合权系数m.同时,该模型继承了单核半监督支持向量机的非凸非平滑特性.采用双层优化过程来优化这两组参数,并采用改进的拟牛顿法和基于成对标签交换的局部搜索算法分别解决模型关于fm的非平滑及非凸问题,以得到模型近似最优解.在多核框架中同时加入基本核和流形核,以充分利用数据的几何性质.实验结果验证了算法的有效性及较好的泛化性能.展开更多
基金Supported by the Project of Ministry of Education and Finance (No.200512)the Project of the State Key Laboratory of Ocean Engineering (GKZD010053-10)
文摘In this paper a hybrid process of modeling and optimization, which integrates a support vector machine （SVM） and genetic algorithm （GA）, was introduced to reduce the high time cost in structural optimization of ships. SVM, which is rooted in statistical learning theory and an approximate implementation of the method of structural risk minimization, can provide a good generalization performance in metamodeling the input-output relationship of real problems and consequently cuts down on high time cost in the analysis of real problems, such as FEM analysis. The GA, as a powerful optimization technique, possesses remarkable advantages for the problems that can hardly be optimized with common gradient-based optimization methods, which makes it suitable for optimizing models built by SVM. Based on the SVM-GA strategy, optimization of structural scantlings in the midship of a very large crude carrier （VLCC） ship was carried out according to the direct strength assessment method in common structural rules （CSR）, which eventually demonstrates the high efficiency of SVM-GA in optimizing the ship structural scantlings under heavy computational complexity. The time cost of this optimization with SVM-GA has been sharply reduced, many more loops have been processed within a small amount of time and the design has been improved remarkably.
文摘超声波检测法是高压开关柜局部放电检测的一种有效方法,但目前基于超声波信号检测原理开发的局部放电检测产品主要有信号幅值检测、将信号降频至音频从而监听检测,具有检测结果不够准确、对检测人员要求较高等缺点。该研究提出了一种基于偏最小二乘(partial least squares,PLS)特征降维和支撑向量机(support vector machine,SVM)的开关柜局部放电检测方法,首先计算超声音频信号的声学特征,并采用PLS进行降维处理,然后采用SVM分类器来区分局放和非局放音频信号。实验结果表明,所提方法比传统阈值方法具有更高的识别准确率,并且降低了对检测人员的要求,具有更好的普适性。
文摘文中搭建了真空断路器试验平台,实现了主轴卡涩等四类机械故障状态。通过将正常及故障状态下的实测振动信号进行经验模态分解,得到所需要的内禀模态函数(intrinsic made function,IMF),利用能量法求出包含主要故障特征信息的各内禀模态函数分量的能量总量。利用IMF分量能量总量作为特征向量,并以此作为支持向量机输入,分析对比了不同分类策略、核函数的分类时间和分类准确率,经实验分析选用"一对其他"分类策略并且核函数为径向基函数的分类效果最优,为研制完善的断路器故障诊断系统提供理论依据及实际的数据基础。
文摘在机器学习领域,核方法是解决非线性模式识别问题的一种有效手段.目前,用多核学习方法代替传统的单核学习已经成为一个新的研究热点,它在处理异构、不规则和分布不平坦的样本数据情况下,表现出了更好的灵活性、可解释性以及更优异的泛化性能.结合有监督学习中的多核学习方法,提出了基于Lp范数约束的多核半监督支持向量机(semi-supervised support vector machine,简称S3VM)的优化模型.该模型的待优化参数包括高维空间的决策函数fm和核组合权系数m.同时,该模型继承了单核半监督支持向量机的非凸非平滑特性.采用双层优化过程来优化这两组参数,并采用改进的拟牛顿法和基于成对标签交换的局部搜索算法分别解决模型关于fm的非平滑及非凸问题,以得到模型近似最优解.在多核框架中同时加入基本核和流形核,以充分利用数据的几何性质.实验结果验证了算法的有效性及较好的泛化性能.
