矩阵补全特别是具有结构化矩阵的低秩矩阵补全得到国内外学者的广泛关注。基于此,笔者在详细叙述hankel矩阵补全的交替方向算法(Alternating Direction Method ADM)的基础上研究此算法在我国航空货运量预测中的应用,以1995-2010年我国...矩阵补全特别是具有结构化矩阵的低秩矩阵补全得到国内外学者的广泛关注。基于此,笔者在详细叙述hankel矩阵补全的交替方向算法(Alternating Direction Method ADM)的基础上研究此算法在我国航空货运量预测中的应用,以1995-2010年我国航空货运量的统计数据为基础,利用Matlab软件求解相应Hankel矩阵补全问题可得我国航空货运量逐年预测值。通过预测误差分析可知,此方法可应用于短期内预测我国的航空货运量,为我国航空货运市场的中长期调控提供有效的理论依据。展开更多
An improved covariance driven subspace identification method is presented to identify the weakly excited modes. In this method, the traditional Hankel matrix is replaced by a reformed one to enhance the identifiabilit...An improved covariance driven subspace identification method is presented to identify the weakly excited modes. In this method, the traditional Hankel matrix is replaced by a reformed one to enhance the identifiability of weak characteristics. The robustness of eigenparameter estimation to noise contamination is reinforced by the improved Hankel matrix, in combination with component energy index （CEI） which indicates the vibration intensity of signal components, an alternative stabilization diagram is adopted to effectively separate spurious and physical modes. Simulation of a vibration system of multiple-degree-of-freedom and experiment of a frame structure subject to wind excitation are presented to demonstrate the improvement of the proposed blind method. The performance of this blind method is assessed in terms of its capability in extracting the weak modes as well as the accuracy of estimated parameters. The results have shown that the proposed blind method gives a better estimation of the weak modes from response signals of small signal to noise ratio （SNR）and gives a reliable separation of spurious and physical estimates.展开更多
文摘矩阵补全特别是具有结构化矩阵的低秩矩阵补全得到国内外学者的广泛关注。基于此,笔者在详细叙述hankel矩阵补全的交替方向算法(Alternating Direction Method ADM)的基础上研究此算法在我国航空货运量预测中的应用,以1995-2010年我国航空货运量的统计数据为基础,利用Matlab软件求解相应Hankel矩阵补全问题可得我国航空货运量逐年预测值。通过预测误差分析可知,此方法可应用于短期内预测我国的航空货运量,为我国航空货运市场的中长期调控提供有效的理论依据。
基金This project is supported by National Natural Science Foundation of China (No.10302019).
文摘An improved covariance driven subspace identification method is presented to identify the weakly excited modes. In this method, the traditional Hankel matrix is replaced by a reformed one to enhance the identifiability of weak characteristics. The robustness of eigenparameter estimation to noise contamination is reinforced by the improved Hankel matrix, in combination with component energy index （CEI） which indicates the vibration intensity of signal components, an alternative stabilization diagram is adopted to effectively separate spurious and physical modes. Simulation of a vibration system of multiple-degree-of-freedom and experiment of a frame structure subject to wind excitation are presented to demonstrate the improvement of the proposed blind method. The performance of this blind method is assessed in terms of its capability in extracting the weak modes as well as the accuracy of estimated parameters. The results have shown that the proposed blind method gives a better estimation of the weak modes from response signals of small signal to noise ratio （SNR）and gives a reliable separation of spurious and physical estimates.
