An Embedded Condition Monitoring and Fault Diagnosis System for Rotary Machines

An intelligent machine is the earnest aspiration of people. From the point of view to construct an intelligent machine with self-monitoring and self-diagnosis abilities, the technology for realizing an internet oriented embedded intelligent condition monitoring and fault diagnosis system for the rotating machine with remote monitoring, diagnosis, maintenance and upgrading functions is introduced systematically. Based on the DSP （ Digital Signal Processor） and embedded microcomputer, the system can measure and store the machine work status in real time, such as the rotating speed and vibration, etc. In the system, the DSP chip is used to do the fault signal processing and feature extraction, and the embedded microcomputer with a customized Linux operation system is used to realize the internet oriented remote software upgrading and system maintenance. Embedded fault diagnosis software based on mobile agent technology is also designed in the system, which can interconnect with the remote fault diagnosis center to realize the collaborative diagnosis. The embedded condition monitoring and fault diagnosis technology proposed in this paper will effectively improve the intelligence degree of the fault diagnosis system.     

Maintenance and Condition-Based Maintenance

1IntroductionSystem reliability and availability have been widely studied in the literature because of their preva-lence in industry systems. Maintaining a high or required level of reliability and availability is oftenan essential requisite.Up to the 1950′s a fix it when it breaks′philosophy (BM, break maintenance) was mostly imple-mented due to lack of engineering knowledge in certain areas. The regular inspection regime of time-based maintenance (PM, preventive maintenance) was later in…     

破碎设备网络化在线状态监测与故障诊断系统

应用虚拟仪器技术进行破碎设备在线监测与故障诊断,并用网络技术实现数据的网络传输和远程监测.利用NI公司提供的G web Server实现系统监测显示面板的网页发布,利用Datasocket技术快速实现监测数据的网络传输.LabVIEW和网络技术的结合可以方便客户获取检测图像和检测结果.本系统在对破碎设备主要性能参数（如破碎机水平轴扭矩,振动,速度,间隙,温度,压力,流量等）的在线检测和远程故障诊断上均取得了较好的效果.     

基于LABVIEW的风机在线监测系统开发

基于LABVIEW设计了一种风机虚拟在线监测系统。利用WB-8100E监测仪表实现工艺参数超限报警和连锁保护。利用虚拟仪器实时采集和显示风机工况信号值，根据运行时的振动信号，采用频谱分析方法，可以很好地实现对风机状态实时监控和故障诊断。为矿井的安全生产提供了可靠保障。     

Evaluation of the use of envelope analysis and DWT on AE signals generated from degrading shafts

Vibration analysis is widely used in machinery diagnosis. Wavelet transforms and envelope analysis, which have been implemented in many applications in the condition monitoring of machinery, are applied in the development of a condition monitoring system for early detection of faults generated in several key components of machinery. Early fault detection is a very important factor in condition monitoring and a basic component for the application of condition-based maintenance (CBM) and predictive maintenance (PM). In addition, acoustic emission (AE) sensors have specific characteristics that are highly sensitive to high-frequency and low-energy signals. Therefore, the AE technique has been applied recently in studies on the early detection of failure. In this paper, AE signals caused by crack growth on a rotating shaft were captured through an AE sensor. The AE signatures were pre-processed using the proposed signal processing method, after which power spectrums were generated from the FFT results. In the power spectrum, some peaks from fault frequencies were presented. According to the results, crack growth in rotating machinery can be considered and detected using an AE sensor and the signal processing method.     

深度学习在机械设备诊断中的应用

传统的机械设备状态监测是根据经验通过提取现场采集的振动信号特征值构建特征空间,采用多种方法对特征值进行聚类、分类,从而实现对设备状态的分类。但这种方法严重依赖于专家经验,并且效果受到信号噪声等众多因素的影响。分别在经典一维和二维卷积神经网络的的基础上,提出两种机械设备智能故障诊断方法,并通过凯斯西储大学轴承数据中心发布的数据集比较两种模型的性能,实验结果表明,基于一维卷积神经网络的智能诊断方法更适用于一维振动信号。将基于一维卷积神经网络的智能诊断方法应用于石化厂的机泵设备,证明其能实现特征自适应提取,可取得较好诊断效果。     

振动监测系统的可调增益技术与实现

文章设计了一种具有可调增益功能的振动监测系统。首先从监测层和测量层两个方面提出了振动监测系统的整体框架,之后给出了硬件系统和软件系统的设计方法及软件实现代码,利用控制芯片和可调增益放大器,在监测系统中整合了一套可根据采集信号幅值大小调整增益的数据采集装置;利用模拟信号发生器对不加增益和设置可调增益之后的两种信号进行了对比分析,并在汽轮发电机组实际工况下进行了振动信号采集。结果表明,具备可调增益功能的振动监测系统可有效提高采集信号的信噪比,提高汽轮发电机组的振动监测能力。     

A Web-based Condition Monitoring and Diagnostic System of Rolling Mill

1　ＩｎｔｒｏｄｕｃｔｉｏｎＢｅｉｎｇｔｈｅｅｓｓｅｎｔｉａｌｅｑｕｉｐｍｅｎｔ,ｏｎｃｅｔｈｅｒｏｌｌｉｎｇｍｉｌｌｂｒｅａｋｓｄｏｗｎｕｎｅｘｐｅｃｔｅｄｌｙｔｈｅｌｏｓｓｅｓｃａｕｓｅｄｂｙｕｎｓｃｈｅｄｕｌｅｄｓｈｕｔｄｏｗｎａｎｄｑｕａｌｉｔｙａｂｎｏｒｍａｌｉｔｙｃａｎｂｅｖｅｒｙｓｅｖｅｒｅ.Ｔｏｄｅａｌｗｉｔｈｔｈｉｓｐｒｏｂｌｅｍ ,ｍｏｒｅａｎｄｍｏｒｅｌａｒｇｅｓｔｅｅｌｗｏｒｋｓｉｎｔｈｅｗｏｒｌｄｒｅｓｅａｒｃｈｅｄｏｎｔｈｅＣＭＡＦＤＳｏｆａｒｏｌｌｉｎｇｍｉｌｌａｎｄｄ…     

印刷机设备状态监测与故障诊断研究进展

通过对国内外印刷机状态监测与故障诊断研究情况和发展趋势的分析,认为当前对印刷机监测的研究主要集中在振动信号的测试研究、专家经验知识的应用、模式识别算法引入等几个方面,并论述了当前基于印刷图像处理的印刷机故障诊断这一新方向的研究情况。由于印刷机不断朝着高速度、高精度、高自动化程度方向发展,传统故障诊断方法在印刷机系统中的应用已受到很大限制,研究认为,兼顾多元信息实现全面状态监测,融合经验知识与先进识别算法建立故障决策体系,从印刷画面信息中提取设备参数,将是今后印刷机故障诊断研究的重点。     

Research on the Correlation Between Oil Menitoring and Vibration Monitoring in Information Collecting and Processing Monitoring

Oil monitoring and vibration monitoring are two principal techniques for mechanical fault diagnosis and condition monitoring at present. They monitor the mechanical condition by different approaches, nevertheless, oil and vibration monitoring are related in information collecting and processing. In the same mechanical system, the information obtained from the same information source can be described with the same expression form. The expressions are constituted of a structure matrix, a relative matrix and a system matrix. For oil and vibration monitoring, the information source is correlation and the collection is independent and complementary. And oil monitoring and vibration monitoring have the same process method when they yield their information. This research has provided a reasonable and useful approach to combine oil monitoring and vibration monitoring.     

大型风力机组远程智能监测与诊断系统的研究与开发

该文研究了大型风力机组的远程智能监测与诊断系统的关键技术问题,介绍了系统的开发情况。整个系统采用分布式架构,由数据采集与处理、实时数据存储、智能监测与诊断和人机交互4个子系统组成。智能监测与诊断子系统采用了知识库/推理机架构,推理机是一个自主开发的基于模糊Rete算法的模糊专家系统,知识库中存储了来源于风力机故障实验研究的常见振动故障的诊断知识。通过故障仿真,验证了整套系统的有效性。     

A data acquisition system for machine tool condition monitoring. Part 2—some of the signals acquired

This paper presents some of the machine tool condition monitoring signals logged by the data acquisition system (DAS) designed and implemented as part of the European Union research project BREU-CT91–0463. Cause and effect relationships between machine components and signal features are highlighted, along with a demonstration of the suitability of vibration signal kurtosis as a measure of machine tool spindle bearing condition.     

Research on Key Techniques of Condition Monitoring and Fault Diagnosing Systems of Machine Groups

This paper describes the development of the condition monitoring and fault diagnosing system of a group of rotating machinery. The data management is performed by means of double redundant data bases stored simultaneously in both the analyzing server and monitoring client. In this way, high reliability of the storage of data is guaranteed. Condensation of trend data releases much space resource of the hard disk. Diagnosing strategies orientated to different typical faults of rotating machinery are developed and incorporated into the system. Experimental verification shows that the system is suitable and effective for condition monitoring and fault diagnosing for a rotating machine group.     

A Study on a Remote Monitoring and Diagnosis System and Its Application

Remote monitoring and diagnosis （RMD） is a new kind of monitoring and diagnosis technology that combines computer science, communication technology and fault diagnosis technology. Via the Internet a remote monitoring and diagnosis system can be established. In this paper, the model of an Internet based remote monitoring and diagnosis system is presented; the function of every part of the RMD system is discussed. Then, we introduce a practical example of a remote monitoring and diagnosis system that we established in a factory; its traits and functions are described.     

UML建模和组件技术在远程监测和故障诊断系统中的应用

随着WEB应用技术的不断发展和人们对远程分布式在线监测和故障诊断的要求不断提高,原有的系统开发模式已经不能胜任现阶段的软件开发需求,为有效地解决这一问题,采用UML(统一建模语言)对整个监测和诊断系统进行框架建模,并结合组件技术(ActiveX/COM/DCOM),开发完成了一个远程分布式在线监测和故障诊断系统。重点对UML和组件技术如何在系统中实现有效组合进行了详细地分析,对未来状态监测和故障诊断方面的系统开发具有一定的实际应用价值和参考价值。     

风机的运行状态监测与故障诊断及其MATLAB实现

本文介绍了时间序列分析在风机模型构建、状态监测与故障诊断方面的应用原理，并用MATLAB语言建立了风机运行状态的AR模型，并以此模型为基础，实现了风机的运行状态监测与故障诊断。     

燃气轮机发电机组的振动信号监测与分析系统

研发了一套燃气轮机振动监测、故障诊断系统，系统集数据采集、分析，振动状态检测，振动故障预报、诊断为一体。系统常规的分析功能主要有频谱分析、转子轴心轨迹分析、小波分析、短时傅立叶变换、相关分析等；另外配有趋势分析、报警功能，并建立了振动故障诊断数据库，实现对燃气轮机主要部件的故障诊断。电站现场的6台燃气轮机测试结果表明，本系统的软件功能和硬件功能可以满足燃气轮机振动监测和振动故障诊断的要求。     

Fault diagnosis in injection moulding via cavity pressure signals

In this paper we demonstrate the feasibility of applying pattern recognition techniques for monitoring and diagnosis to an injection moulding process. Mould cavity pressure signals collected during the process are utilized for monitoring and diagnosis. Principal component analysis is applied to reduce the dimensionality of multivariate signals to a univariate representative signal, while preserving the characteristics of the original signals. Process ‘fingerprints’ are gleaned through wavelet decomposition and multi-resolution analysis of the ‘reduced’ signal. Feature elements defined from these fingerprints are interpreted by an artificial neural network for process condition monitoring and fault diagnosis. The experimental results indicate that this approach is effective for ‘run to run’ process monitoring, diagnostics and control. The diagnostic system can be updated adaptively as new process faults are identified.     

A New Spectral Average-Based Bearing Fault Diagnostic Approach

The diagnosis of bearing health through the quantification of accelerometer data has been an area of interest for many years and has resulted in numerous signal processing methods and algorithms. This paper proposes a new diagnostic approach that combines envelope analysis, time synchronous resampling, and spectral averaging of vibration signals to extract condition indicators (CIs) used for rolling-element bearing fault diagnosis. First, the accelerometer signal is digitized simultaneously with tachometer signal acquisition. Then, the digitized vibration signal is band pass filtered to retain the information associated with the bearing defects. Finally, the tachometer signal is used to time synchronously resample the vibration data which allows the computation of a spectral average and the extraction of the CIs used for bearing fault diagnosis. The proposed technique is validated using the vibration output of seeded fault steel bearings on a bearing test rig. The result is an effective approach validated to diagnose all four bearing fault types: inner race, outer race, ball, and cage.     

基于Multi-Agent技术的大型机电设备故障诊断系统

通过对大型机电设备的故障特点的分析,以及对Multi-Agent系统架构的描述,提出了一种基于Multi-Agent技术的大型机电设备故障诊断结构模型.此MAS系统结构采用了层次模型设计,符合故障诊断的推理方法.文章着重阐述了各类Agent的功能以及它们之间的协作方式.该模型分为监测层、数据处理层和管理层等三个层次,其中监测层用于数据采集和简单故障诊断,数据处理层用于复杂故障诊断和人机交互,管理层用于管理整个MAS系统和协调各Agent的合作关系.各Agent之间通信以KQML语言为基础,并扩展了一组专用的动作表达式以满足故障诊断的需要;文章还描述了复杂故障诊断任务中各Agent之间的协作方式.