论文部分内容阅读
针对钢铁企业传统高压线路行波检测器易出现误报警的问题,提出了采用支持向量机(SVM)的分类辨识方法,用于故障信号和扰动信号的辨识。首先,从行波法定位装置数据库中提取报警时的信号特征,构造支持向量的输入向量,建立基于数据驱动的支持向量机模型;然后采用仿真策略确定支持向量机径向基函数中的参数σ和惩罚系C的值,并分析了参数σ及惩罚系数C的值对故障和扰动分类准确率的影响。将所提出的方法应用到莱钢高压线路行波检测器中,结果表明:采用支持向量机的分类辨识方法,可以使行波检测器检测的准确率接近90%,大大提高了莱钢高压线路行波检测器故障检测的可靠性。
Aiming at the problem that the false alarm is easy to occur in the traveling wave detector of the traditional high voltage line in the iron and steel enterprise, a classification identification method based on Support Vector Machine (SVM) is proposed to identify the fault signal and disturbance signal. First, we extract the signal characteristics of the alarm from the traveling wave locator device database, construct the input vector of the support vector and establish the data driven support vector machine model. Then we use the simulation strategy to determine the parameter σ in the radial basis function of the support vector machine And the value of penalty system C, and analyzed the influence of the parameter σ and the penalty coefficient C on the accuracy of the fault and disturbance classification. The proposed method is applied to the traveling wave detector of the high voltage line in Laiwu Steel. The results show that the classification accuracy of the SVM can make the detection accuracy of the traveling wave detector close to 90%, greatly improving the high voltage line Reliability of Traveling Wave Detector Fault Detection.