轴承故障音频诊断系统设计与开发  

Design and Development of Acoustic Fault Diagnosis System for Bearings

作　　者：杨胜跃[1] 陆汝华[1] 周宴宇[1] 何正明[1] 

机构地区：[1]中南大学信息科学与工程学院,湖南长沙410075

出　　处：《计算机仿真》2008年第4期335-338,共4页Computer Simulation

基　　金：湖南省自然科学基金(06JJ50141);国家自然科学基金(60774023)

摘　　要：轴承音频信号包含了其运行状态的许多重要信息,通过这些信息的恰当分析、处理就能对轴承故障进行有效诊断.与振动信号相比,音频信号的采集是非接触式的,具有使用方便、成本低廉等优势.因此,将基于音频信号的隐马尔可夫模型(Hidden Markov Model,HMM)建模方法引入到轴承故障诊断研究,以PC机为平台,在Visual C++ 7.0环境下设计开发了一套功能完善、操作方便、界面友好的轴承音频故障诊断系统。主要介绍了诊断系统的体系结构,HMM方法建模的步骤和故障诊断过程中的具体应用操作。多次实验结果表明,效果良好。Plentiful significant information about the operation status of bearings potential for the fault diagnose after processed properly is contained in their acoustic signals. Compared with vibration signals, acoustic signals can be collected with non - contact sensors, so as to be convenient and cheap. Therefore, the method of Hidden Markov Modeling （HMM）, based on acoustic signal, is proposed for the bearing fault diagnosis. Besides, a diagnosis system running on PC, which can be operated easily and with perfect functions and friend interface, is developed based on Visual C ＋ ＋ 7.0. In the text, architecture of the diagnosis system, steps for HMM modeling and fault diagnosis are introduced in detail. At last, experimentations are introduced to demonstrate the effectiveness of the new developed diaanosis system.

关 键 词：轴承 故障诊断 音频信号 臆马尔可夫模型 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]