基于IFS的局部放电超声信号的数据压缩和模式识别

变压器局部放电超声信号具有连续不可导和非平稳的特性 ,通过仿射变换建立其分段自仿射IFS (IteratedFunctionSystem)。利用该方法一方面实现局部放电信号数据的压缩 ;另一方面提取IFS分形参数 ,包括IFS分形维数和空缺率 ,为局部放电模式识别提供新的特征参数 ,两者同时进行 ,为实现局部放电在线监测提供一种新的工具。同时进一步把IFS分形参数作为特征参量输入人工神经网络对放电模式进行识别 ,结果表明了利用超声波信号进行局部放电模式识别的有效性。

Data Compression and Pattern Recognition for Partial Discharge Supersonic Signal Based on Iterated Function System

The piecewise self affine iterated function system(IFS) of transformer partial discharge supersonic signals is established. It is according to the complex,non-stationary and non-derivative characteristics of partial discharge supersonic signal.The IFS fractal dimension is extracted based on this method which is provided for partial discharge pattern recognition.The novel route is that both the tasks of compression and feature extraction in a single step,and affords a new tool for on-line monitoring partial discharge in transformer.Then the artificial neural network is used to recognize discharge patterns.The result shows that the fractal method is effective for transformer partial discharge pattern recognition.