摘要
分析了金属电阻丝成像机理与识别方法,建立了聚乙烯电熔接头缺陷形态特征与超声图谱之间的对应关系。基于数学方法定量表征了缺陷的参数,提出一种缺陷自动识别的方法,并设计了相应软件。通过对大量带未知缺陷的接头的检测、识别和解剖,验证了所提出的缺陷自动识别方法的有效性。结果表明,该方法对含多种缺陷的接头识别准确率达93.9%,对含有单一缺陷的接头识别准确率达100%。
The imaging mechanism and identification method of metal coils were investigated,and the corresponding relations between the characteristics of defects and the ultrasonic images of polyolefin electro-fusion joint were proposed.Furthermore,the integrated characteristics were presented using mathematic analysis,and the method and software for automatic defect recognition were designed.A large number of defect inspection,identification and dissection experiments were conducted on unknown defects,and the method of automatic defect recognition was verified to be an effective and fast method.Results show that the accuracy rate can reach 93.9%for joints with complex defects and 100%for those with single defects.
出处
《无损检测》
2017年第6期13-18,72,共7页
Nondestructive Testing
关键词
聚乙烯电熔接头
超声相控阵
金属电阻丝
缺陷自动识别
polyolefin electro-fusion joint
ultrasonic phased array
metal coils
automatic defect recognition
