摘要
针对强力输送带钢丝芯漏磁检测信号成分复杂、噪声干扰严重、钢丝芯断丝损伤程度难以识别等问题,采用小波-支持向量机算法对钢丝芯断丝信号进行提取及识别。首先用小波分析技术滤除检测信号的噪声,并根据钢丝缺陷先验知提取断丝特征,形成断丝特征样本集;采用支持向量机对断丝损伤信号进行识别分级;最后使用实际数据进行实验验证。结果表明,该算法识别结果与实际情况基本一致,为钢丝芯损伤监测研究提供了一种新的方法。
Contraposing the problems of the complex composition and the serious noise of the magnetic flux leakage testing signal of the wire-core of heavy intensity conveyor belt, and the damage degree of the broken wire-core is difficultly identified, so the signals of the broken wire-core are extracted and discerned by using the wavelet-support vector machine algorithm. First, the noises of the detection signal are filtered with the technology of wavelet analysis, the features of the broken wires are verified and eollected in advance to form a sample set according to the defects of the wires. Second, the damage signals of the broken wires are identified and classyfied with the support vector machine. Finally, the experimental verification is carried out by using the actual data. The result shows that the identification results of this algorithm are basically consistent with the actual situation. It provides a new method for monitoring the broken wires of the wire core.
出处
《矿山机械》
北大核心
2009年第21期46-50,共5页
Mining & Processing Equipment
关键词
胶带机
输送带
钢丝芯
漏磁检测
小波分析
支持向量机
belt conveyor
belt
wire-core
magnetic flux leakage testing
wavelet analysis
sup-port vector machine
作者简介
程羽，男，1982年生，在读硕士研究生，研究方向为智能仪器检测。
