摘要
提出了风机噪声信号的人耳听觉谱特征提取方法,利用人耳听觉谱特征模拟人耳听觉系统的特性,采用支持向量机分类器进行风机故障的分类识别;设计了基于听觉原理和支持向量机分类器的风机故障诊断系统,并应用于风机故障诊断。文中所用实验数据是在工厂现场采集获得,对现场实测数据的识别实验证明,人耳听觉谱特征可有效用于风机故障诊断,可正确识别99.18%的正常机器,故障类型诊断的正确识别率在91%以上。
In this paper, an auditory spectrum feature extraction method is proposed The psychophysics of hearing is simulated by auditory spectrum feature. Support vector machine （SVM） is used for the identification of fan fault. A fault diagnosis system is designed based on auditory principle and SVM, and is also applied to fault diagnosis for fan. A series of experiments were carried with the real data measured from a factory environment. The results show that the auditory spectrum feature is effective for fan fault diagnosis. The classification accuracy for normal fans is about 99.18% . and the classification accuracy of the types for faulty fans is above 91%.
出处
《仪器仪表学报》
EI
CAS
CSCD
北大核心
2009年第1期175-179,共5页
Chinese Journal of Scientific Instrument
关键词
人耳听觉谱特征
风机故障诊断
支持向量机
auditory spectrum feature
fault diagnosis of fan
support vector machine
作者简介
杨宏晖，于2006年在西北工业大学获得博士学位。现为西北工业大学副教授，主要研究方向为自动测试测控技术、模式识别、声信号信息处理。E—mail：hhyang@nwpu．edu．cn侯宏，于1999年在西北工业大学获得博士学位，现为西北工业大学教授。主要研究方向为噪声与振动控制，时域声阻抗测量等。E—mail：houhong@nwpu．edu．cn
