论文部分内容阅读
有源电力滤波器补偿性能与所采用的谐波检测方法有很大的依赖关系,针对现有的检测方法存在精度不高、对电网频率变化比较敏感、自适应能力不强的缺点,提出了一种基于蚁群聚类算法优化Elman神经网络的谐波检测方法。算法通过对Elman神经网络的权值、阈值寻优,建立了基于ACC-ENN算法的谐波检测模型。试验结果表明,该方法较其他检测方法具有更好的泛化能力和更高的预测精度。
The compensation performance of the active power filter has a great dependence on the harmonic detection method used. In view of the shortcoming of the existing detection methods that the accuracy is not high, the frequency of the power grid is sensitive to changes and the adaptability is not strong, A Harmonic Detection Method Based on Ant Colony Clustering Algorithm to Optimize Elman Neural Network. The algorithm establishes the harmonic detection model based on ACC-ENN algorithm by optimizing the weights and thresholds of Elman neural network. Experimental results show that this method has better generalization ability and higher prediction accuracy than other methods.