|
| 摘要: |
| 传统的ＡＮＮ（人工神经网络）训练过程多建立在Ｈｅｂｂ学习机制的基础上的，但基本的Ｈｅｂｂ学习机制的收敛性往往难以令人满意；在ＡＤＡＬＩＮＥ模型的基础上，提出了一种新的、适用于电力系统谐波分析的ＡＮＮ算法，该算法的训练过程采用了Ｏｊａ学习规则，较好地保证了算法的收敛性。文中给出了利用该算法进行谐波分析的仿真结果，并与傅氏自救和最小二算算法的计算结果进行了比较。算例表明，新算法具有精度高、收敛速度快的 |
| 关键词: 谐波分析 人工神经网络 Oja学习规则 |
| DOI： |
| 分类号:TM712 |
| 基金项目: |
|
| A New ANN Harmonic Analysis Algorithm Based on Oja''''s Learning Rule |
|
Jin Ming
|
| Abstract: |
| Most training procedures of ANN are designed on the
basis of Hebb's learning mechanism. But in some cases,the convergent property of the
algorithm is not satisfactory.A new ANN algorithm for analyzing harmonics in power system
based on ADALINE model and Oja's learning rule is described. This algorithm ensures a
satisfactory convergent property. The simulation result and its comparison with that from
Fourier algorithm and the least square algorithm are given. |
| Key words: harmonic analysis, ANN, Oja's learning rule |
