基于监测数据相关性分析的谐波趋势预警方法

Harmonic trend warning method based on correlation analysis of monitoring data

针对传统谐波监测数据预警方法仅考虑短时或单一时刻的数值大小分布,未关注到长期趋势变化的问题,文章提出了基于谐波监测数据相关性分析的趋势预警方法:在分析了长期运行过程中谐波监测数据随时间变化趋势的周期规律性以及相似性基础上,对比实时监测数据与正常状态数据的变化趋势,若趋势差异大,则预警。使用滑动均值法提取数据整体趋势变化,避免短时波动等干扰对整体趋势分析的影响;根据动态时间规整算法,量化不同时段数据变化规律的差异,并进行异常趋势预警;利用现场实测数据,验证了文章方法的正确性和有效性。

Aiming at the problem that the traditional harmonic monitoring data early warning method,which only considers the distribution of data value in a short period or a single moment,rather than paying attention to the change of long-term trend,this paper proposes a trend warning method based on the correlation analysis of harmonic monitoring data:on the basis of analyzing the periodic regularity and similarity of the trend change of harmonic monitoring data over time during long-term operation,the change trend of real-time monitoring data and normal state data is compared.If the trend difference is large,early warning will be given.Firstly,the moving average smoothing method is adopted to extract the overall trend change of data to avoid the influence of short-term fluctuations and other interferences on the overall trend analysis.Then,according to the dynamic time warping algorithm,the difference of data change law in different periods is quantified,and abnormal trend warning is given.Finally,the correctness and effectiveness of the proposed method are verified by on-site monitoring data.