摘要
由振动系统的运动方程建立了描述系统输入、输出和噪声特性的受控自回归滑动平均模型(ARMAX)。采用基于限定记忆的增广最小二乘算法估计其参数,克服了以往传统方法计算的复杂性,以及难以在线的缺点。仿真结果表明本文方法鲁棒性较好。
Based on motion eqations of vibrating systems, the paper establishes the ARMAX model, which describes input,output and noise characteristice of the system. The recursive extended least squares algorithm based on limited memory is adopted for estimating ARMAX model parameters. The method overcomes some drawbacks such as high computational complexities and difficulties of online identification. Simulation results show that the proposed method exhibits good robust properties.
出处
《机械科学与技术》
CSCD
北大核心
2005年第12期1515-1518,共4页
Mechanical Science and Technology for Aerospace Engineering
基金
国家自然科学基金项目(50105021)
国家教育部<高等学校骨干教师资助计划>资助
军械工程学院创新人才启动基金资助
关键词
振动系统建模
ARMAX模型
增广最小二乘
vibrating system modeling
ARMAX model
recursive extended least squares
