检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
出 处:《上海交通大学学报》2015年第12期1761-1767,共7页Journal of Shanghai Jiaotong University
基 金:国防预研基金项目(401080102)资助
摘 要:针对基于特征参数的导弹制导控制系统状态预测存在的状态数据不等间隔、小样本的问题,并考虑各性能特征参数间的相互影响、相互关联的关系,提出了一种基于非等间距灰色联合最小二乘支持向量机(UGM-ULSSVM)的退化状态预测方法.在UGM-ULSSVM模型的训练阶段,根据特征参数序列建立其非等间距灰色预测模型(UGM(1,1)),将UGM(1,1)的拟合值作为输入,原始数据序列作为输出,分别训练得到时间型最小二乘支持向量机(TLSSVM)与空间型最小二乘支持向量机(SLSSVM);在模型的预测阶段,由建立的UGM(1,1)模型和通过证据理论融合TLSSVM和SLSSVM建立的ULSSVM模型组合得到UGM-ULSSVM状态预测模型.以导弹制导控制系统为例,实现了关键参数预测,结果验证了方法的合理性与有效性.Aimed at the unequal interval and small sample condition data in the condition prediction of missile guidance and control systems,a method of degraded state prediction based on the unequal interval grey model-unification of least squares support vector machine(UGM-ULSSVM)was proposed considering the correlation between feature parameters.A unequal interval grey model(UGM(1,1))was established according to feature parameter series in UGM-ULSSVM training.The time-like least squares support vector machine(TLSSVM)and space-like least squares support vector machine(SLSSVM)could be trained to get through taking the fitted values of UGM(1,1)as the input and actual values of parameter series as the output.The UGM-ULSSVM state prediction model was obtained by combining UGM(1,1)and unification of least squares support vector machine(ULSSVM)established by fusing TLSSVM and SLSSVM in UGM-ULSSVM prediction.Taking missile guidance and control systems as an example,the key parameter predicting was realzed.Finally,the results validated the rationality and effectiveness of the ULS-SVM prediction model.
分 类 号:TJ760[兵器科学与技术—武器系统与运用工程]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.15