多支持向量机模型的输电线路故障诊断方法

Fault Diagnosis Method Based on Multi-support Vector Machine Model for Transmission Lines

为提高电力线路故障诊断的准确性,充分利用广域监测系统的同步量测信息,提出一种基于电气量故障信息特征的多支持向量机模型诊断方法。首先,获取同步监测信息,利用对称分量法提取故障信息特征,建立特征集。其次,采用遗传算法优化支持向量机模型参数,构建诊断模型。最后,利用D-S证据理论融合方法对不同支持向量机模型的诊断结果进行融合,获得最终的故障诊断结果。实例验证结果表明,依据特征量进行故障诊断的准确率能较稳定的达到97%,具备提高诊断精度和降低结构复杂度的优势。另外,与传统方法相比,多支持向量机诊断模型能准确识别故障特征,且有效提升诊断准确率在4%以上,具有更高的准确性与有效性。

In order to improve the accuracy of transmission line fault diagnosis, a power system fault diagnosis of multi-support vector machine(SVM) model based on the fault information characteristics of electrical quantity is proposed, where the synchronous monitoring information of the wide area measurement system is used. Firstly, the fault information feature is extracted by the symmetrical component method for the synchronous monitoring information, and the feature set is established. Secondly, the genetic algorithm(GA) is used to optimize the model parameters and build the diagnosis model. Finally, the D-S evidence theory is used to fuse the diagnosis results from different diagnosis models and obtain the final diagnosis results. The simulation results show that the accuracy of the diagnosis model based on the fault features can reach up to 97%, and this diagnosis model has advantages of improving accuracy and reducing complexity of model structural. Compared with the traditional methods, the multi-support vector machine diagnostic model can accurately identify the fault features, and can effectively improve the diagnosis accuracy by more than 4%, thus it has higher accuracy and effectiveness.