基于混沌理论和KPCM聚类的变压器绕组松动状态监测

运行中的变压器会产生持续振动,通过振动的变化可以判断变压器内部运行状态。变压器振动信号中包含了大量状态信息,难以从中提取有效特征来监测绕组松动状态。为此,提出了基于混沌理论和核可能性聚类算法KPCM的变压器绕组松动状态监测方法。首先,从振动信号的混沌动力学特性出发,通过选择最佳嵌入维数和时间延迟,对实测变压器振动信号进行相空间重构。然后,针对重构信号的高维空间分布,使用KPCM聚类方法对分布模式进行识别,据此对绕组松动状态进行监测。现场实测数据的计算结果表明,使用Wolf法计算得到的最大李雅普诺夫指数为正,证实了变压器振动信号的混沌特性,基于KPCM聚类分析得到的聚类中心位移矢量的变化能够有效识别出绕组松动的机械故障隐患。研究结果为从混沌动力学角度监测变压器绕组的松动状态提供了理论依据。

Looseness State Monitoring of Transformer Winding Based on Chaos Theory and KPCM Clustering Method

The change of transformer vibration can be used to estimate its internal operation state.However,it is difficult to extract effective features of vibration signals to monitor winding looseness state since it contains a large amount of state information.Therefore,a method of monitoring looseness state of transformer winding based on chaos theory and kernel-based possibilistic c-means clustering algorithm KPCM is presented.Firstly,the measured transformer vibration signal sate reconstructed in thephase space with the optimal embedding dimension and time delay based on the chaotic featuresof vibration signals.Then,the KPCM clustering method is used to identify the distribution mode according to high dimensional spatial distribution of reconstructed signals.Consequently, the looseness state of transformer winding can be analyzed successfully.Calculated results of measured vibration signals show that the largest Lyapunov exponent calculated by the Wolf algorithm is positive,which confirms the chaotic characteristics of transformer vibration signals.Winding loosing mechanical fault can be identified effectively based on the changes of displacement vector of cluster centers obtained by KPCM clustering analysis.The obtained results provide a theoretical basis for the looseness state monitoring of transformer windings from the view of chaotic dynamics.