为满足电力系统实时动态观测的要求,需要精确估计电网络参数,基于电力系统的任何网络参数误差都会影响状态估计中的量测残差,通过对量测残差的分析提出了一个基于最小二乘的电网络参数误差估计方法。分两步完成电网络参数误差的估计:首...为满足电力系统实时动态观测的要求,需要精确估计电网络参数,基于电力系统的任何网络参数误差都会影响状态估计中的量测残差,通过对量测残差的分析提出了一个基于最小二乘的电网络参数误差估计方法。分两步完成电网络参数误差的估计:首先根据动态系统的量测方程,利用加权最小二乘法(weighted least squares method,以下简称WLS),同时引入网络节点虚拟量测量作为等式约束条件建立最优化模型,利用拉格朗日乘法提出量测残差的表达式,网络节点虚拟量测量的引入加强了算法的精确性和收敛速度;第二步首先利用递推最小二乘建立量测残差方程中偏差项的的迭代公式,电网络参数误差包含在量测残差方程的偏差项中,通过迭代得出一个无偏估计的初始状态量,最后求得电网络参数误差。IEEE9节点系统的仿真验证了算法的正确性和有效性。展开更多
In order to improve the effectiveness of traditional time domain identification methods in identifying damping ratios, a new damping ratio identification method based on pattern search is proposed by fluctuating the r...In order to improve the effectiveness of traditional time domain identification methods in identifying damping ratios, a new damping ratio identification method based on pattern search is proposed by fluctuating the reliable natural frequency obtained through traditional time domain identification methods by about 10% to build the boundary conditions, using all the initial identification results to establish the free decay response of the system, and using the pattern search method to correct the initial identification results with the residual sum of squares between the free decay response and the actually measured free-decay signal as the objective function. The proposed method deals with the actually measured free-decay signal with curve fitting and avoids enlarging the identified error caused by intermediate conversion, so it can effectively improve the identified accuracy of damping ratios. Simulations for a room-sized vibration isolation foundation show that the relative errors of analyzed three damping ratios are down to 1.05%, 1.51% and 3.7% by the proposed method from 8.42%, 5.85% and 8.5% by STD method when the noise level is 10%.展开更多
文摘为满足电力系统实时动态观测的要求,需要精确估计电网络参数,基于电力系统的任何网络参数误差都会影响状态估计中的量测残差,通过对量测残差的分析提出了一个基于最小二乘的电网络参数误差估计方法。分两步完成电网络参数误差的估计:首先根据动态系统的量测方程,利用加权最小二乘法(weighted least squares method,以下简称WLS),同时引入网络节点虚拟量测量作为等式约束条件建立最优化模型,利用拉格朗日乘法提出量测残差的表达式,网络节点虚拟量测量的引入加强了算法的精确性和收敛速度;第二步首先利用递推最小二乘建立量测残差方程中偏差项的的迭代公式,电网络参数误差包含在量测残差方程的偏差项中,通过迭代得出一个无偏估计的初始状态量,最后求得电网络参数误差。IEEE9节点系统的仿真验证了算法的正确性和有效性。
基金Sponsored by the National Natural Science Foundation of China (Grant No.50675052)
文摘In order to improve the effectiveness of traditional time domain identification methods in identifying damping ratios, a new damping ratio identification method based on pattern search is proposed by fluctuating the reliable natural frequency obtained through traditional time domain identification methods by about 10% to build the boundary conditions, using all the initial identification results to establish the free decay response of the system, and using the pattern search method to correct the initial identification results with the residual sum of squares between the free decay response and the actually measured free-decay signal as the objective function. The proposed method deals with the actually measured free-decay signal with curve fitting and avoids enlarging the identified error caused by intermediate conversion, so it can effectively improve the identified accuracy of damping ratios. Simulations for a room-sized vibration isolation foundation show that the relative errors of analyzed three damping ratios are down to 1.05%, 1.51% and 3.7% by the proposed method from 8.42%, 5.85% and 8.5% by STD method when the noise level is 10%.
