求解粒径问题的线性约束二次规划方法  

Solving the problem of size estimation using linear constrained quadratic programming method

作　　者：周铭[1] 谢炜[2] 刘文中[1] 孔力[1] 

机构地区：[1]华中科技大学控制科学与工程系,湖北武汉430074 [2]武汉第二船舶设计研究所,湖北武汉430064

出　　处：《华中科技大学学报（自然科学版）》2010年第5期24-27,共4页Journal of Huazhong University of Science and Technology(Natural Science Edition)

基　　金：高等学校博士学科点专项科研基金资助项目(200804871136);湖北省自然科学基金资助项目(2008CDB320);国家科技重大专项资助项目(2009ZX03003-009);国家科技支撑计划资助项目(2008BAH30B12);武汉市科技攻关项目(20097063264)

摘　　要：针对经典奇异值分解求解方法所导致的虚假震荡信号,提出基于约束二次规划的磁纳米粒子粒径分布函数求解方法.在求解粒径分布函数中,以解的二模最小化为目标函数,将磁纳米粒子磁化曲线的数值不定式和解的非负性条件作为约束条件,建立了该线性约束二次规划问题的优化模型.在Matlab环境下利用软件Mosek进行优化计算,并使用无噪声、含有模拟噪声的仿真数据和实际数据分别进行了对比实验,验证了方法的有效性.A method to solve the size distribution of magnetic nano-particle using constrained quadratic programming instead of previous singular value decomposition, in which artifical oscillation was caused. In the solution of particle size distribution, the minimum of second moment was set to be the objective function. And the indeterminate equation of magnetization of magnetic nano-particles, as well as the non-negative property of solution was used as constraints to establish the optimization model of the linear constrained quadratic programming problem. In optimizing by using commercial optimization software Mosek in Matlab, noise-free simulated data, the simulation data with noise and experimental data were compared, respectively. A preliminary validation of the method is effective.

关 键 词：磁纳米粒子 粒径分布 线性约束二次规划 虚假震荡 奇异值分解 

分 类 号：TN911.72[电子电信—通信与信息系统]