Focusing on strip steel surface defects classification, a novel support vector machine with adjustable hyper-sphere （AHSVM） is formulated. Meanwhile, a new multi-class classification method is proposed. Originated f...Focusing on strip steel surface defects classification, a novel support vector machine with adjustable hyper-sphere （AHSVM） is formulated. Meanwhile, a new multi-class classification method is proposed. Originated from support vector data description, AHSVM adopts hyper-sphere to solve classification problem. AHSVM can obey two principles： the margin maximization and inner-class dispersion minimization. Moreover, the hyper-sphere of AHSVM is adjustable, which makes the final classification hyper-sphere optimal for training dataset. On the other hand, AHSVM is combined with binary tree to solve multi-class classification for steel surface defects. A scheme of samples pruning in mapped feature space is provided, which can reduce the number of training samples under the premise of classification accuracy, resulting in the improvements of classification speed. Finally, some testing experiments are done for eight types of strip steel surface defects. Experimental results show that multi-class AHSVM classifier exhibits satisfactory results in classification accuracy and efficiency.展开更多
Multi-level inverters(MLIs)have become popular in different applications such as industrial power control systems and distributed generations.There are different forms of MLIs.The cascaded MLIs(CMLIs)have some special...Multi-level inverters(MLIs)have become popular in different applications such as industrial power control systems and distributed generations.There are different forms of MLIs.The cascaded MLIs(CMLIs)have some special advantages among them such as more different output voltage levels using the same number of components and higher power quality.In this paper,a 27-level inverter switching algorithm considering total harmonic distortion(THD)minimization is investigated.Switching angles of the inverter switches are achieved by minimizing a THD-based objective function.In order to minimize the THD-based objective function,the hyper-spherical search(HSS)algorithm,as a novel optimization algorithm,is improved and the results of improved HSS(IHSS)are compared with HSS algorithm and other five evolutionary algorithms to show the advantages of IHSS algorithm.展开更多
连续潮流(continuous power flow,CPF)是电力系统电压稳定分析的有效工具,也是解决常规潮流中病态潮流问题的方法之一。针对无平衡节点孤岛运行微电网系统的无平衡节点、且有下垂控制分布式电源装置的特性,提出一种无平衡节点孤岛运行...连续潮流(continuous power flow,CPF)是电力系统电压稳定分析的有效工具,也是解决常规潮流中病态潮流问题的方法之一。针对无平衡节点孤岛运行微电网系统的无平衡节点、且有下垂控制分布式电源装置的特性,提出一种无平衡节点孤岛运行微电网CPF计算方法。采用不要求雅可比矩阵非奇异,且具有全局收敛性的LM-TR方法求解初始点。预测环节采用结合局部参数化方法的切线法。校正环节提出新型的超球面参数化方法,并采用结合传统牛顿法和带Armijo型线性搜索牛顿法的组合牛顿法进行校正,以保证CPF校正计算成功,及实现整个CPF过程中在较高计算精度下一直采用较大定步长预测。对改造后的37节点和17节点无平衡节点孤岛运行微电网系统采用所提方法进行CPF计算,验证了其正确性和有效性。展开更多
针对发动机性能评估参数存在多重共线性且数量过多的问题,提出一种依据类间方差和距离判别的聚类方法。将相似个体化为一类,并取类中均值作为分析对象,大大减少了参数维数;在支持向量数据描述(Support Vector Data Description)算法基础...针对发动机性能评估参数存在多重共线性且数量过多的问题,提出一种依据类间方差和距离判别的聚类方法。将相似个体化为一类,并取类中均值作为分析对象,大大减少了参数维数;在支持向量数据描述(Support Vector Data Description)算法基础上,引入超球体核距离度量,将多参数转化为单参数,解决了参数过多相互矛盾的问题。特征空间上一点与超球体中心的距离表征发动机的性能衰退程度,并给出了性能开始衰退与性能明显恶化的阀值曲线。考虑聚类后类中参数对发动机性能评估的贡献不同,提出基于改进粒子群算法优化多尺度核函数参数和惩罚因子C。仿真结果表明:考虑了多尺度参数后,发动机性能状况较单尺度参数能更好的符合实际使用情况。聚类后多尺度参数与原参数的评估结果基本一致。展开更多
文摘Focusing on strip steel surface defects classification, a novel support vector machine with adjustable hyper-sphere （AHSVM） is formulated. Meanwhile, a new multi-class classification method is proposed. Originated from support vector data description, AHSVM adopts hyper-sphere to solve classification problem. AHSVM can obey two principles： the margin maximization and inner-class dispersion minimization. Moreover, the hyper-sphere of AHSVM is adjustable, which makes the final classification hyper-sphere optimal for training dataset. On the other hand, AHSVM is combined with binary tree to solve multi-class classification for steel surface defects. A scheme of samples pruning in mapped feature space is provided, which can reduce the number of training samples under the premise of classification accuracy, resulting in the improvements of classification speed. Finally, some testing experiments are done for eight types of strip steel surface defects. Experimental results show that multi-class AHSVM classifier exhibits satisfactory results in classification accuracy and efficiency.
文摘Multi-level inverters(MLIs)have become popular in different applications such as industrial power control systems and distributed generations.There are different forms of MLIs.The cascaded MLIs(CMLIs)have some special advantages among them such as more different output voltage levels using the same number of components and higher power quality.In this paper,a 27-level inverter switching algorithm considering total harmonic distortion(THD)minimization is investigated.Switching angles of the inverter switches are achieved by minimizing a THD-based objective function.In order to minimize the THD-based objective function,the hyper-spherical search(HSS)algorithm,as a novel optimization algorithm,is improved and the results of improved HSS(IHSS)are compared with HSS algorithm and other five evolutionary algorithms to show the advantages of IHSS algorithm.
文摘连续潮流(continuous power flow,CPF)是电力系统电压稳定分析的有效工具,也是解决常规潮流中病态潮流问题的方法之一。针对无平衡节点孤岛运行微电网系统的无平衡节点、且有下垂控制分布式电源装置的特性,提出一种无平衡节点孤岛运行微电网CPF计算方法。采用不要求雅可比矩阵非奇异,且具有全局收敛性的LM-TR方法求解初始点。预测环节采用结合局部参数化方法的切线法。校正环节提出新型的超球面参数化方法,并采用结合传统牛顿法和带Armijo型线性搜索牛顿法的组合牛顿法进行校正,以保证CPF校正计算成功,及实现整个CPF过程中在较高计算精度下一直采用较大定步长预测。对改造后的37节点和17节点无平衡节点孤岛运行微电网系统采用所提方法进行CPF计算,验证了其正确性和有效性。
文摘针对发动机性能评估参数存在多重共线性且数量过多的问题,提出一种依据类间方差和距离判别的聚类方法。将相似个体化为一类,并取类中均值作为分析对象,大大减少了参数维数;在支持向量数据描述(Support Vector Data Description)算法基础上,引入超球体核距离度量,将多参数转化为单参数,解决了参数过多相互矛盾的问题。特征空间上一点与超球体中心的距离表征发动机的性能衰退程度,并给出了性能开始衰退与性能明显恶化的阀值曲线。考虑聚类后类中参数对发动机性能评估的贡献不同,提出基于改进粒子群算法优化多尺度核函数参数和惩罚因子C。仿真结果表明:考虑了多尺度参数后,发动机性能状况较单尺度参数能更好的符合实际使用情况。聚类后多尺度参数与原参数的评估结果基本一致。
基金国家自然科学基金(the National Natural Science Foundation of China under Grant No.60603023)国家重点基础研究发展规划(973)(the National Grand Fundamental Research 973 Program of China under Grant No.2001CCA00700)
