基于录波数据的变电站继电保护装置采样回路智能预警技术及算法研究

Research on Intelligent Early Warning Technology and Algorithm of Sampling Circuit of Substation Relay Protection Device Based on Fault Recording Data

随着电力系统的不断发展和变电站规模的扩大,继电保护装置的采样回路的稳定性对系统运行的重要性日益凸显;然而,由于采样回路存在故障隐患和性能衰减的风险,及时监测和预警变得至关重要。提出了一种基于录波数据的变电站继电保护装置的采样回路智能预警技术:首先,通过突变点查找,从大量的录波数据中查找到有效的采样回路同源数据,并获取该数据的突变窗口;然后,针对存在有同源数据,采用重采样与滤波相结合暂稳态特性对比方法,针对单通数据的瞬时异常,采用一阶导数的方式,实现采样数据的缺陷提取;最后利用特征提取,完成针对采样回路的预警。实际电网数据的验证表明,所提出的方法与工程实际贴合,实现了变电站的采样回路的实时监测,保证了电网的安全稳定运行。

With the continuous development of power systems and the expansion of substation sizes,the stability of sampling circuits of relay protection devices has become increasingly important for system operation.However,due to the risk of fault hazards and performance degradation of sampling circuits,timely monitoring and early warning have become critical.This paper proposes a sampling circuit intelligent warning technology for substation relay protection device based on recorded wave data:first,through the mutation point search,find the effective sampling circuit homologous data from a large number of recorded wave data,and obtain the mutation window of the data;then,for the existence of homologous data,using the combination of re-sampling and filtering of the temporary steady state characteristics of the comparison method,and for the transient abnormality of the single-pass data,the first-order derivative method,to realize the sampling circuit status of the single-pass data.The first-order derivative is used to realize the defect extraction of the sampled data;finally,the feature extraction is used to complete the early warning for the sampled circuit.The verification of actual grid data shows that the method proposed in this paper fits the engineering reality,realizes the real-time monitoring of sampling circuits in substations,and ensures the safe and stable operation of the power grid.