基于声发射AR模型的滚动轴承故障诊断

Fault diagnosis of rolling bearing based on AR model of acoustic emission

滚动轴承是旋转机械中应用最广泛的零部件之一,滚动轴承故障诊断方法及其状态监测技术是保障机器安全平稳运行的关键技术之一。采用功率谱分析、经典谱估计等方法,从中提取故障特征信息,完成基于振动加速度信号的轴承状态分析;但由于感知受本体振动及高噪声环境影响,很难完成轴承早期故障损伤表征特征的识别。论文提出具有高频高灵敏度的感知方法与振动检测技术,具有较高信噪比特性,并能够感知小幅的轴承早期故障损伤冲击响应信息,同时采用AR模型方法与功率谱估计方法相结合,可实现轴承早期故障特征识别。此外,以天然气压缩机的高速轴承为分析实例,采用具有高频高灵敏度的声发射感知技术,实现故障特征状态识别与分析,结果表明优于经典谱估计的方法,为轴承故障损伤产生、演变至故障的状态监测及其修正提出可行的理论支持,进一步保障设备运行安全。

Rolling bearing is one of the most widely used parts in rotating machinery.The fault diagnosis method and condition monitoring technology of rolling bearing is one of the key technologies to ensure the safe and stable operation of the machine.Using power spectrum analysis,classical spectrum estimation and other methods,the fault feature information is extracted,and the bearing state analysis based on vibration acceleration signal is completed.However,due to the influence of vibration and high noise environment,it is difficult to complete the identification of bearing early fault damage characteristics.In this paper,a sensing method with high frequency and high sensitivity is proposed.Compared with vibration detection technology,it has higher signal-to-noise ratio and can sense the impact response information of small size bearing early fault damage.Meanwhile,the Auto-Regressive AR model method and the power spectrum estimation method are combined to realize the identification of bearing early fault characteristics.In addition,taking the high-speed bearing of natural gas compressor as an example,the acoustic emission sensing technology with high frequency and high sensitivity is used to realize the fault feature state identification and analysis.The results show that the method is better than the classical spectrum estimation method.It provides feasible theoretical support for the condition monitoring and correction of bearing fault damage generation,evolution to fault,and further ensure the safety of equipment operation.