摘要
给出了一种自动识别轴心轨迹形状的新方法。首先将采集到的轴心轨迹线图,用边界颜色填充各区域,形成轴心轨迹图象,计算其不变矩特征向量。然后将仿真生成的各种轴心轨迹不变矩特征向量作为参考模式,将实际检测的轴心轨迹不变矩特征向量作为待识别模式,利用关联度进行识别。最后成功地识别了 MJF-30-6 型发电机在空转、并网正常运行、转子短路故障运行、A 相接地四种工况的轴心轨迹形状,并揭示了发电机电气故障对转子轴心轨迹的影响。
This paper presents a new method for automatically identifying the axis orbit shape.It acquires the axis orbit,fills all regions of axis orbit and forms the axis orbit image.The moment invariants of the axis orbit image are calculated.Then it selects the moment invariants of simulated axis orbit for reference patterns.The practically acquired axis orbit shape will be automatically identified based on the interconnect degree.By the method,it successfully identifies the MJF-30-6 generator axis orbit shape under the four conditions of no load operation, normal operation,rotor inter turn short circuit fault and phase A grounded fault.
出处
《华北电力大学学报（自然科学版）》
CAS
北大核心
2004年第5期26-29,共4页
Journal of North China Electric Power University：Natural Science Edition
基金
2004 年华北电力大学重大项目预研基金资助项目.
