基于单向表示字典学习的电能质量扰动识别方法

电能质量扰动识别是电能质量数据分析问题中极其重要的一个部分。目前已经实现的电能质量扰动识别方法普遍存在识别速度较慢,识别准确率仍有较大提升空间等问题。本文提出一种计算简单但能有效识别分类的方法,即基于单向表示字典学习的电能质量扰动识别方法。首先对电能质量数据的训练样本进行训练得到与各个类别对应的子字典,提出单向约束以使样本在字典中的表示系数方向可以区分,然后通过计算测试样本的表示系数方向以及大小来区分所属类别。实验结果表明,本文所提方法不但识别准确度高于已有的识别方法,而且计算效率也有较大提升。

Power Quality Disturbance Recognition Method Based on Unidirectional Representation Dictionary Learning

Power quality disturbance recognition is an extremely important part of power quality data analysis problems.The currently implemented power quality disturbance recognition methods generally suffer from slow recognition speed and low recognition accuracy.This paper proposes a method that is simple to calculate and can effectively recognize classification, that is, a power quality disturbance recognition method based on unidirectional representation dictionary learning.First, train the training samples of the power quality data to obtain sub-dictionaries corresponding to each type, propose a unidirectional constraint so that the direction of the coefficients of the samples in the dictionary can be distinguished.Then distinguish the type by calculating the direction and size of the representation coefficient of the test sample.The experimental results show that the method proposed in this paper not only has higher recognition accuracy than existing recognition methods, but also improves the calculation efficiency.