基于模糊与虚拟仪器的滚动轴承故障诊断系统研究

发布时间：2018-04-28 03:16

本文选题：滚动轴承 + 故障诊断　；参考：《大连交通大学》2011年硕士论文

【摘要】：滚动轴承是旋转机械中应用广泛,同时也是易损零件之一。由于滚动轴承特定的使用环境,造成其寿命的随机性较大,目前还无法准确预测其寿命的长短,但它的运行状态直接影响到整个机械设备的状态。据统计,在旋转机械的故障中,有30%是由滚动轴承故障引起的。对滚动轴承进行状态监测及故障诊断能及时发现故障,能有效保护工厂财产及工人人身安全。因此,研究滚动轴承故障诊断技术有很重要的现实意义。振动检测法是现在滚动轴承故障诊断研究和应用的主流。由于滚动轴承本身在工作时必然伴随旋转而产生振动,其运行状况的好坏往往直接反映在振动信号中,而且振动信号测试简单、直观。通过测量、分析轴承的振动信号来判断轴承状态、进行故障诊断方便可靠。模糊神经网络系统是近年来计算机智能领域中一个新的研究方向。它融合了神经网络和模糊系统的各自优点,将模糊推理系统架构于神经网络上,充分发挥模型对于系统不确定性与不精确性的处理能力,同时具有自我学习与组织能力,能够调整模型的参数,因此被用于滚动轴承的故障诊断。本文提出了一种基于频带能量和自适应神经模糊推理系统(ANFIS)的滚动轴承故障诊断方法。通过对滚动轴承振动信号进行时域分析,提取频段能量参数,实时判断滚动轴承故障状态,然后再利用ANFIS作为分类器进行故障模式识别。利用ANFIS进行滚动轴承故障诊断,可以降低对操作人员的专业知识的要求,将故障诊断从传统方法转向人工智能方向。同时,诊断系统中智能技术的应用能大大降低维修人员工作强度。利用虚拟仪器设计开发了振动信号采集系统。同时结合LabVIEW和MATLAB两款软件的特点,开发了采用两者混合编程的滚动轴承故障诊断系统。通过对实测的齿轮减速机滚动轴承故障信号数据进行验证。结果表明,本文设计的基于模糊与虚拟仪器的滚动轴承故障诊断系统具有可靠、实用等特点。
[Abstract]:Rolling bearing is widely used in rotating machinery, and it is also one of the vulnerable parts. Due to the special use environment of rolling bearing, the life of rolling bearing is random, so it is not possible to predict the life of rolling bearing accurately, but its running state directly affects the state of the whole mechanical equipment. According to statistics, 30% of the faults of rotating machinery are caused by rolling bearing faults. The condition monitoring and fault diagnosis of rolling bearing can find the fault in time, and can effectively protect the factory property and the personal safety of workers. Therefore, the study of rolling bearing fault diagnosis technology has a very important practical significance. Vibration detection method is the main research and application of rolling bearing fault diagnosis. Because the rolling bearing itself produces vibration with rotation when it works, its running condition is often reflected directly in the vibration signal, and the vibration signal test is simple and intuitionistic. Through the measurement, the vibration signal of the bearing is analyzed to judge the bearing state, and the fault diagnosis is convenient and reliable. Fuzzy neural network system is a new research direction in the field of computer intelligence in recent years. It combines the respective advantages of neural network and fuzzy system. The fuzzy inference system is constructed on neural network, which makes full use of the model's ability to deal with system uncertainty and imprecision, at the same time, it has the ability of self-learning and organizing. The parameters of the model can be adjusted and thus used for fault diagnosis of rolling bearings. This paper presents a fault diagnosis method for rolling bearings based on band energy and adaptive neural fuzzy inference system (ANFIS). By analyzing the vibration signal of rolling bearing in time domain, the energy parameter of frequency band is extracted, and the fault state of rolling bearing is judged in real time. Then the fault pattern is identified by using ANFIS as classifier. Using ANFIS to diagnose rolling bearing fault can reduce the requirement of professional knowledge of operator and turn fault diagnosis from traditional method to artificial intelligence. At the same time, the application of intelligent technology in diagnosis system can greatly reduce the working intensity of maintainers. The vibration signal acquisition system is designed and developed by using virtual instrument. Combined with the characteristics of LabVIEW and MATLAB, a rolling bearing fault diagnosis system is developed. The fault signal data of rolling bearing of gear reducer are verified. The results show that the rolling bearing fault diagnosis system based on fuzzy and virtual instrument is reliable and practical.
【学位授予单位】：大连交通大学
【学位级别】：硕士
【学位授予年份】：2011
【分类号】：TH165.3

【相似文献】