支持向量机理论的研究与进展

回顾了支持向量机理论的发展历程,介绍了支持向量机的标准训练算法及其分解算法、变形算法、几何算法以及多类分类算法,重点描述了最小二乘支持向量机算法,总结了支持向量机理论及其应用的现状与存在问题,对支持向量机的未来发展方向进行了展望。     

基于解耦矢量控制的五相永磁同步电机容错控制策略

针对五相永磁同步电机两相开路故障的运行工况,提出了一种基于解耦矢量控制理论的故障容错控制策略.该策略通过在两相开路故障下的同步旋转坐标系内建立电机的数学模型,构造解耦变换矩阵,将电流控制中id和iq轴解耦,达到两相开路故障下容错运行的目的 .仿真结果表明,在五相永磁同步电机两相开路故障下,基于解耦矢量控制理论的故障容错控制策略能够实现电机驱动系统的高品质运行,具有控制简单、转矩波动小、容错能力强等优点.     

Reliability analysis of arresting hook engaging arresting cable for carrier-based aircraft influenced by multifactors

The carrier-based aircraft landing and arrest process is complex and nonlinear, and includes the coupling effect between the aircraft and arresting system. It has many uncertain factors, which lead to difficulty in the reliability analysis. To make the reliability analysis more accurate and effective, this paper presents some studies. Taking a certain type of carrier-based aircraft as the research object, a dynamic model of the landing and arrest cable was established, and the accuracy of the model was verified using laboratory test results. Based on the model, this paper shows how the key parameters, including the sinking velocity, pitch angle and horizontal velocity, affect the collision rebound performance of the arresting hook. After that, a limit state equation of the arresting hook system’s reliability was established. For the implicit limit state equation, a surrogate model of the reliability of the arresting hook was established using the Support Vector Machine (SVM) method, and then reliability analysis was carried out using the Monte Carlo method. Finally, it was explained in detail how the key parameters affect the reliability of the hook engaging the arresting cable, and some meaningful conclusions were obtained. This analysis method and its results can provide a reference for the top-level parameter design of carrier-based aircraft and reliability research on the arresting systems.     

基于支持向量机的抗干扰决策技术

为了应对日益复杂的电磁环境，认知雷达的概念被引入电子战中。认知电子战系统包括认知侦察、认知对抗和认知效能评估3个重要环节。针对认知电子战系统对抗干扰决策技术的需求，为实现自适应的决策抗干扰措施，将支持向量机(SVM)算法运用于抗干扰决策中。仿真结果表明:基于SVM的抗干扰决策技术可以自适应地决策抗干扰措施，进行干扰对抗，该算法完成了认知电子战中的最后的一步，使认知电子战系统实现闭环。     

扰动线运动对惯性系粗对准影响分析及优化方法

针对扰动线运动对惯性系粗对准精度影响较大的问题，通过分析惯性体坐标系下重力加速度积分矢量的物理含义，给出了受扰动线运动影响的惯性系粗对准的误差分析。并在此基础上提出了基于位移积分矢量构造定姿矢量矩阵的抗扰动粗对准算法，利用对速度积分矢量进一步积分得到的3个时间点的位移积分矢量构建姿态解算矩阵，抑制扰动线运动对粗对准精度的影响。仿真结果表明，该算法可有效减小扰动线运动影响下的对准结果振动幅值，能够快速收敛到满足精对准使用的精度范围，从而提高武器装备环境适应性。     

“珠海一号”高光谱数据城市不透水面提取研究

不透水面是评估城市化进程和评价城市环境的重要参考指标，研究城市不透水面的空间覆盖程度对城市生态环境保护、宜居城市建设具有重要意义。本文以“珠海一号”高光谱影像为数据源、珠海市陆域为研究区域，选取支持向量机和随机森林机器学习算法，结合光谱特征，实现城市不透水面信息提取。结果表明：使用“珠海一号”高光谱数据提取不透水面可行性较强，且支持向量机算法更适用于“珠海一号”不透水面提取，总体精度和Kappa系数分别达到92.4%、0.78；基于“珠海一号”高光谱数据进行城市不透水面提取，可为城市规划建设、分析城市土地扩张、评估城市灾害风险提供可靠理论依据和数据支撑。