| 引用本文: | 刘佳翰,陈克绪,马建,等.基于卷积神经网络和随机森林的三相电压暂降分类[J].电力系统保护与控制,2019,47(20):112-118. |
| LIU Jiahan,CHEN Kexu,MA Jian,et al.Classification of three-phase voltage dips based on CNN and random forest[J].Power System Protection and Control,2019,47(20):112-118 |
|
| 摘要: |
| 特征提取是电能质量扰动识别的关键步骤，然而传统的数学变换与浅层神经网络相结合的方法无法自动提取特征。为此，提出了一种基于卷积神经网络(CNN)和随机森林(RF)的混合模型来对三相电压暂降数据进行自动特征提取及分类。首先，将三相电压暂降数据转换为空间相量模型(SPM)；其次，利用CNN对SPM进行特征提取；最后，将RF应用于分类。为了加快CNN训练速度并缓解过拟合，引入了Dropout、学习率指数衰减和自适应矩估计权值更新算法。实验结果表明，与其他分类方法相比，所提方法具有较好的泛化性能和较高的分类准确率，这为电压暂降识别提供了一种客观、高效的辅助手段。 |
| 关键词: 空间相量模型 卷积神经网络 随机森林 电压暂降 电能质量 |
| DOI：10.19783/j.cnki.pspc.181337 |
| 分类号: |
| 基金项目:国家自然科学基金项目资助(61662047) |
|
| Classification of three-phase voltage dips based on CNN and random forest |
|
LIU Jiahan1,CHEN Kexu2,MA Jian2,XU Chunhua1,WU Jianhua1
|
|
(1. School of Information Engineering, Nanchang University, Nanchang 330031, China;2. State Grid Jiangxi Electric Power Research Institute, Nanchang 330096, China)
|
| Abstract: |
| Feature extraction is the critical step in power quality disturbances recognition, while the traditional methods combining the mathematical manipulations and shallow neural networks cannot extract the features automatically. Therefore, the paper proposes a hybrid model based on the Convolutional Neural Network (CNN) and Random Forest (RF) to perform the automatic feature extraction and classification of the three phase voltage dip data. Firstly, the three phase voltage dip data is transformed to the Space Phasor Model (SPM). Secondly, CNN is used for extracting the features of the SPM. Finally, RF is applied for classification. For the acceleration of the training of CNN and the relief of over-fitting, the dropout, exponential decay of learning rate and update of weights by adaptive moment estimation are introduced. Experimental results demonstrate that the proposed method has a better generalization performance and higher classification accuracy compared to other classification methods, which provides an objective and efficient auxiliary method for voltage dip recognition. This work is supported by National Natural Science Foundation of China (No. 61662047). |
| Key words: space phasor model convolutional neural network random forest voltage dip power quality |
