基于混沌理论与麻雀优化K-means算法的变压器铁心松动缺陷分析方法

Analysis Method of Transformer Iron Core Loosening Defects Based on Chaos Theory and Sparrow Optimized K-means Algorithm

为了更加有效地对变压器铁心状态进行分析,提出一种基于混沌理论与麻雀优化K-means算法的变压器铁心松动缺陷特征分析方法。首先,运用C-C法求解重构相空间的嵌入维数与延迟时间,重构变压器振动信号的相空间。其次,计算变压器振动信号的最大Lyapunov指数来判断系统是否具有混沌特性,选取关联维数、Kolmogorov熵作为一组混沌特征以识别铁心的松动程度。再次,将麻雀搜索算法引入K-means聚类算法优化初始中心簇的选取并使用簇中心与簇类点的位移平均值作为描述变压器铁心松动状态的定量特征。最后,将两组特征结合起来形成变压器铁心松动故障的诊断指标,为变压器铁心的松动故障诊断提供理论依据,并投入分类器进行故障诊断,验证两组特征结合的优越性。

In order to analyze the status of the transformer core more effectively,a method for analyzing the characteristics of loosening defects in the transformer core based on chaos theory and sparrow optimization K-means algorithm was proposed.Firstly,the C-C method was used to solve the embedding dimension and delay time of the reconstructed phase space,and reconstruct the phase space of the transformer vibration signal.Secondly,the maximum Lyapunov index of the transformer vibration signal was calculated to determine whether the system has chaotic characteristics,and the correlation dimension and Kolmogorov entropy were selected as a set of chaotic characteristics to identify the degree of looseness of the core.Thirdly,the sparrow search algorithm was introduced into the K-means clustering algorithm to optimize the selection of the initial center cluster and use the average displacement of the cluster center and cluster points as a quantitative feature to describe the loose state of the transformer core.Finally,the two sets of characteristics were combined to form a diagnostic index for the loosening fault of the transformer core,which provides a theoretical basis for the diagnosis of the loosening fault of the transformer core and put the classifier into fault diagnosis to verify the superiority of the combination of the two sets of features.