摘要
为了提高油液污染度分析和磨粒识别的准确率,在对油液在线监测系统中的磨粒图像特点深入分析的基础上,给出了磨粒图像处理和目标提取的主要流程;分析了磨粒图像模糊退化模型,研究了基于微分图像自相关的磨粒图像模糊尺度计算方法;提出了基于差值图像粗分割和Otsu算法相结合的磨粒图像分割方法。实例分析结果表明:提出的方法对磨粒图像处理效果较好。利用颗粒计数器和铁谱分析系统分别对油液在线监测系统的检测性能进行了检验,结果表明:系统的油液污染度分析和磨粒识别准确率均达到95%以上,具有较高的检测精度,满足磨粒在线监测要求。
To improve the accurate rates of oil contamination level analysis and wear particle recognition, the main process of wear particle image processing and object extraction is given on the basis of analysis of image characteristics of oil on-line monitoring system. The degrading module of the blurred wear particle image is analyzed. The method on the blur parameters calculation of the blurred wear particle image based on difference and autocorrelation is studied. The wear particle image segmentation method based on oil background image and Otsu is proposed. The results of the examples show that the proposed methods are fit for the wear particle image processing. The system performance is tested by particle counter and the ferrography technology respectively. The results show that the accurate rates of oil contamination level analysis and wear particle recognition are higher than 95 %. This system has high detection precision and can meet the demand of wear particle on-line monitoring.
出处
《传感器与微系统》
CSCD
北大核心
2011年第9期37-40,43,共5页
Transducer and Microsystem Technologies
基金
江苏高校优势学科建设工程资助项目
南京林业大学高学历人才基金资助项目(B2010-31)
关键词
磨粒
在线监测
模糊尺度
OTSU
wear particle
on-line monitoring
blur extent
Otsu