基于分形插值的电力系统故障录波数据压缩与还原算法研究

Research about Compression and Reproduction Algorithm of Digital Recorded Data From a Faulted Power System Based on Fractal Interpolation

针对电力系统故障信号波形在特定时间段内具有自相似性,提出一种基于分形插值的电力系统故障录波数据压缩与还原算法;对原始录波数据的分维数进行计算,并提取原始录波信号的大体轮廓后进行抽样得到插值点集合,将这两个特征信息作为故障信号的编码参数对故障信号进行压缩,基于分段分形插值原理还原电力系统故障录波数据;在该方法中,针对录波数据特点,对分形插值中的插值点选取方法进行改进,对分形插值理论中的分维数定理的应用条件做详细的论证;对10kV中性点不接地系统的单相接地故障波形进行仿真,结果表明:该方法能够提高故障录波数据的压缩倍数并且减小赋范均方误差、失真率低,能够有效地还原故障录波信号。

Power system fault signal waveforms have self--similarity in a specific period of time. A method is proposed to compress and reproduce digital recorded data from a faulted power system based on foetal interpolation. And this method makes short--time box--count- ing dimension and general outline of original recorded data as encoding parameters to compress the fault signal. A method to improve interpo- lation points selection in fraetal interpolation, about features for recorded data. A detailed argument is made about fractal dimension theorem application conditions in fractal interpolation theory. 10kV ungrounded system single--phase ground fault waveforms is simulated. Simula- tion results show that the method can improve the compression ratio of the disturbance recorder data and reduce the normed mean square er- ror, low distortion. And it is possible to effectively restore the disturbance signal.