节点文献

基于图像分形的故障特征提取方法

A FAULT FEATURE EXTRACTION METHOD BASED ON FRACTAL IMAGE

  • 推荐 CAJ下载
  • PDF下载
  • 不支持迅雷等下载工具,请取消加速工具后下载。

【作者】 郝志华王艳茹

【Author】 Hao Zhihua Wang Yanru (Tangshan College,Tangshan 063000)

【机构】 唐山学院

【摘要】 提出了一种图像分形的故障特征提取方法。介绍了分形维数的理论计算公式,分析了计盒维数的计算方法。对现场测试的柴油机爆燃阶段振动信号波形图像和切片Wigner高阶矩谱图像进行了分形维数计算。研究结果表明柴油机缸套活塞不同磨损状态的分形维数差异明显,能够表征不同状态的特征参数。

【Abstract】 In this paper the fault feature extraction method based on fractal image was put forwarded.Theoretical calculation formulas of fractal dimension were introduced.The calculation method about box-counting dimension based on image processing was analyzed.The vibration signals measured from diesel engine in the stage of deflagrate are analyzed with slide Wigner higher order moment spectrum.Then the dimensions of fractal image extracted from the signal waves and the wigner higher order moment spectrums were calculated by fractal dimension calculation program.The result indicates that different wearing stage of piston-cylinder can be discriminated depending on feature parameters of fractal dimension because the fractal dimensions of images are different apparently.

  • 【会议录名称】 2008年全国振动工程及应用学术会议暨第十一届全国设备故障诊断学术会议论文集
  • 【会议名称】2008年全国振动工程及应用学术会议暨第十一届全国设备故障诊断学术会议
  • 【会议时间】2008-08
  • 【会议地点】中国青海西宁
  • 【分类号】TP391.41
  • 【主办单位】中国振动工程学会故障诊断专业委员会
节点文献中: 

本文链接的文献网络图示:

本文的引文网络