基于D-S证据理论的高压断路器故障诊断

发布时间：2018-12-19 12:18

【摘要】：高压断路器作为电力系统中的重要设备,其运行状态直接影响整个电力系统的稳定性和供电的可靠性。因此,对高压断路器故障诊断技术的研究不仅有利于保障电力系统的稳定可靠,而且能够为我国智能电网的建设提供保障。本文针对在实际工作中,由于获取、传输、外界干扰及丢失等原因造成高压断路器故障诊断结果不精确、不一致甚至相互矛盾的问题,采用基于D-S证据理论的高压断路器故障诊断技术,对不确定和不完备的初步诊断结果进行决策级融合得到最终的诊断结果。首先,本文深入研究了高压断路器的工作原理,分析了其常见故障类型及造成故障的原因。然后,介绍了D-S证据理论的基本原理及其在故障诊断中的优势,重点研究了其不足之处,并针对其在冲突证据融合方面的不足,提出了一种修正冲突证据的改进方法。对改进方法进行Matlab仿真实验,并与其他改进方法的结果进行对比,分析其优缺点。最后,将本文方法应用于高压断路器的故障诊断中,并通过Matlab进行仿真实验得出最终诊断结果。本文采集的高压断路器故障信号主要包括分合闸线圈电流信号、声波信号和振动信号。首先,对采集的故障信号进行特征提取,采用希尔伯特-黄变换进行经验模态分解得到固有模态函数作为原始信号的特征信息;然后采用支持向量机进行特征级融合,对故障特征信息进行训练和测试得到各故障类型识别的准确率,将待测故障信号特征信息通过支持向量机的融合识别,将识别结果进行支持向量机测试准确率加权处理后得到各故障类型的基本可信度;最后将各故障的基本可信度采用改进后的D-S证据理论融合得到最终的高压断路器故障诊断结果。
[Abstract]:As an important equipment in power system, the operation state of HV circuit breaker directly affects the stability of the whole power system and the reliability of power supply. Therefore, the research on fault diagnosis technology of HV circuit breakers is not only conducive to ensuring the stability and reliability of power system, but also can provide a guarantee for the construction of smart grid in China. In this paper, the fault diagnosis results of high voltage circuit breakers caused by acquisition, transmission, external interference and loss are inexact, inconsistent and even contradictory. The fault diagnosis technology of high voltage circuit breaker based on D-S evidence theory is used to fuse the uncertain and incomplete preliminary diagnosis results to obtain the final diagnosis results. Firstly, the working principle of high voltage circuit breaker is studied, and the common fault types and causes are analyzed. Then, the paper introduces the basic principle of D-S evidence theory and its advantages in fault diagnosis, focuses on its shortcomings, and puts forward an improved method to correct conflict evidence in view of its shortcomings in conflict evidence fusion. The improved method is simulated by Matlab, and compared with the results of other improved methods, and its advantages and disadvantages are analyzed. Finally, this method is applied to the fault diagnosis of high voltage circuit breaker, and the final diagnosis result is obtained by Matlab simulation experiment. The fault signals collected in this paper mainly include current signal, acoustic signal and vibration signal. Firstly, the fault signal is extracted, and the inherent mode function is obtained by using Hilbert-Huang transform to decompose the characteristic information of the original signal. Then the feature level fusion of support vector machine is used to train and test the fault feature information to obtain the accuracy of each fault type identification. The feature information of the fault signal is identified by the fusion of support vector machine. The recognition results are weighted by support vector machine (SVM) test accuracy, and the basic reliability of each fault type is obtained. Finally, the basic reliability of each fault is fused with improved D-S evidence theory to obtain the final fault diagnosis results of HV circuit breaker.
【学位授予单位】：华北电力大学
【学位级别】：硕士
【学位授予年份】：2017
【分类号】：TM561

【参考文献】