声发射检测技术在故障诊断中的应用研究
发布时间：2018-11-04 19:38
【摘要】：声发射检测技术作为近些年来发展起来的一种无损检测技术，正以其特有的优势受到了广泛的关注。本文从不同方面研究了声发射检测技术在故障诊断领域中的应用，主要内容如下： 对声发射及声发射技术相关理论的基本知识、概念和特点及声发射信号的相关处理方法进行了介绍。阐述了常用声发射信号定位方法的原理，，并根据四传感器阵列平面定位原理结合MATLAB程序，实现了平面声发射源定位。通过实验验证了定位程序的有效性，同时分析了影响定位精度的因素。 研究了轴承声发射信号的不同处理与分析方法，实现了滚动轴承的故障诊断。主要利用时域相关特征参数分析了轴承在不同状态下所产生声发射信号的特征；通过传统傅里叶变换的方法，在频域处理与分析了轴承声发射信号；针对小波分析在时频分析中的优势，采用小波分析对轴承声发射信号进行分析。重点研究了基于BP神经网络的智能诊断方法，提出了一种基于主成分分析与粗糙集相结合的属性约简方法，并具体介绍了该方法的实现过程，最后利用约简后的参数输入到BP神经网络进行故障类型识别。同时，通过对实验数据进行分析，验证了该方法能够有效提高神经网络收敛速度和识别精度。 阐述了声发射技术分别在疲劳裂纹检测、压力容器检测和变压器局部放电检测中的应用原理、特点与方法。结合实例详细介绍了声发射技术在三种情况下的检测过程，从实际的角度证明了声发射技术在这几方面应用的有效性。
[Abstract]:As a kind of nondestructive testing technology developed in recent years, acoustic emission (AE) detection technology has attracted wide attention due to its unique advantages. In this paper, the application of acoustic emission detection technology in fault diagnosis is studied from different aspects. The main contents are as follows: the basic knowledge of acoustic emission and acoustic emission technology related theory, The concept and characteristics of acoustic emission signal are introduced. The principle of commonly used acoustic emission (AE) signal localization method is described. According to the four sensor array plane positioning principle and MATLAB program, the planar acoustic emission source location is realized. The validity of the program is verified by experiments, and the factors influencing the positioning accuracy are analyzed. The different processing and analysis methods of bearing acoustic emission signal are studied, and the fault diagnosis of rolling bearing is realized. The characteristics of acoustic emission signals produced by bearings in different states are analyzed by using time-domain correlation characteristic parameters, and the acoustic emission signals of bearings are processed and analyzed in frequency domain by the traditional Fourier transform method. Aiming at the advantage of wavelet analysis in time frequency analysis, wavelet analysis is used to analyze the acoustic emission signal of bearing. This paper focuses on the intelligent diagnosis method based on BP neural network, proposes a attribute reduction method based on principal component analysis and rough set, and introduces the realization process of this method in detail. Finally, the reduced parameters are input into the BP neural network for fault type identification. At the same time, through the analysis of the experimental data, it is proved that this method can effectively improve the convergence speed and recognition accuracy of the neural network. The application principle, characteristics and methods of acoustic emission technology in fatigue crack detection, pressure vessel detection and transformer partial discharge detection are described. The detection process of acoustic emission technology in three cases is introduced in detail with an example, and the effectiveness of acoustic emission technology in these aspects is proved from the practical point of view.
【学位授予单位】：北京化工大学
【学位级别】：硕士
【学位授予年份】：2012
【分类号】：TH165.3
本文编号：2310940
[Abstract]:As a kind of nondestructive testing technology developed in recent years, acoustic emission (AE) detection technology has attracted wide attention due to its unique advantages. In this paper, the application of acoustic emission detection technology in fault diagnosis is studied from different aspects. The main contents are as follows: the basic knowledge of acoustic emission and acoustic emission technology related theory, The concept and characteristics of acoustic emission signal are introduced. The principle of commonly used acoustic emission (AE) signal localization method is described. According to the four sensor array plane positioning principle and MATLAB program, the planar acoustic emission source location is realized. The validity of the program is verified by experiments, and the factors influencing the positioning accuracy are analyzed. The different processing and analysis methods of bearing acoustic emission signal are studied, and the fault diagnosis of rolling bearing is realized. The characteristics of acoustic emission signals produced by bearings in different states are analyzed by using time-domain correlation characteristic parameters, and the acoustic emission signals of bearings are processed and analyzed in frequency domain by the traditional Fourier transform method. Aiming at the advantage of wavelet analysis in time frequency analysis, wavelet analysis is used to analyze the acoustic emission signal of bearing. This paper focuses on the intelligent diagnosis method based on BP neural network, proposes a attribute reduction method based on principal component analysis and rough set, and introduces the realization process of this method in detail. Finally, the reduced parameters are input into the BP neural network for fault type identification. At the same time, through the analysis of the experimental data, it is proved that this method can effectively improve the convergence speed and recognition accuracy of the neural network. The application principle, characteristics and methods of acoustic emission technology in fatigue crack detection, pressure vessel detection and transformer partial discharge detection are described. The detection process of acoustic emission technology in three cases is introduced in detail with an example, and the effectiveness of acoustic emission technology in these aspects is proved from the practical point of view.
【学位授予单位】：北京化工大学
【学位级别】：硕士
【学位授予年份】：2012
【分类号】：TH165.3
【参考文献】
相关期刊论文 前10条
1 高佃波;刘红光;陆森林;;基于BP神经网络和振动测量的轴承故障诊断[J];长沙交通学院学报;2006年02期
2 金鑫;任献彬;周亮;;智能故障诊断技术研究综述[J];国外电子测量技术;2009年07期
3 袁臣;;声发射信号处理分析[J];电子设计工程;2011年21期
4 霍志红,张志学,郭江,唐必光;基于神经网络的故障诊断研究[J];工业控制计算机;2001年10期
5 宋建恒;;频谱分析法诊断滚动轴承故障[J];青海科技;2007年03期
6 司娟宁;刘金园;董泽;廖薇;;基于主成分分析与支持向量机的汽轮机故障诊断[J];汽轮机技术;2011年02期
7 宋京伟;主分量分析法及在故障诊断中的应用[J];中国设备工程;2001年10期
8 王砚军,俞美,程鸿机,吕振;设备状态监测与故障诊断技术的基本原理与方法——声发射技术[J];山东建材;2000年04期
9 马智明,阳宪惠;主成分分析法在故障诊断中的应用[J];数理统计与管理;2000年06期
10 王牛俊;陈莉;;声发射检测技术的原理及应用[J];陕西国防工业职业技术学院学报;2010年02期
相关硕士学位论文 前2条
1 杨杰;声发射信号处理与分析技术的研究[D];吉林大学;2005年
2 郝宇宁;基于DSP的小波分析在声发射信号处理中的应用研究[D];广西大学;2007年
本文编号：2310940
本文链接：https://www.wllwen.com/kejilunwen/jixiegongcheng/2310940.html
