基于数据融合模型的励磁系统参数辨识算法

Parameter Identification Algorithm for the Excitation System Based on a Data Fusion Model

确认真实可靠的发电机励磁系统参数对电力系统安全稳定分析具有重要意义。基于人工网络融合法,提出了一种基于数据融合模型的辨识算法实现对励磁系统的参数辨识。首先,使用灰狼算法、粒子群算法和遗传算法分别对励磁系统进行参数辨识。然后,利用人工神经网络算法对三种方法的辨识结果进行合成决策。最后,数据融合模型输出合成辨识值。仿真结果表明,基于融合模型的励磁系统参数辨识方法较单一辨识法具有更高的辨识精度与稳定性。

Confirmation of genuine and reliable parameters of the generator excitation system is of great significance for the analysis of the safety and reliability of the electric power system.Based on the artificial network fusion approach,an identification algorithm based on a data fusion model was proposed to realize parameter identification for the excitation system.Firstly,grey wolf optimization(GWO),particle swarm optimization(PSO)and genetic algorithm(GA)were used respectively to identify parameters of the excitation system.Then,the identification results of those three methods were synthesized by the artificial neural network algorithm.Finally,the data fusion model gave the synthetic identification value.Simulations indicated that the parameter identification method based on the fusion model achieved a higher accuracy and stability than a single identification approach.