基于工业互联网的生产设备故障诊断方法

Fault Diagnosis Method of Production Equipment Based on Industrial Internet

故障诊断作为生产设备健康管理的重要组成部分,在提高设备使用寿命和降低安全风险上起着至关重要的作用。特征提取直接影响数据驱动型故障诊断方法的有效性,为了提高故障类型诊断的准确性,利用工业互联网,将高频的振动信号数据批量发送到数据分析服务器,结合集合经验模态分解与曲线二次编码,获得特征信息更加丰富的高阶编码特征。实验表明,所提出的方法有效提高了故障类型的诊断正确率。

Fault diagnosis,as an important part of production equipment health management,plays a vital role in improving equipment life and reducing safety risks.Feature extraction directly affects the effectiveness of data-driven fault diagnosis methods.In order to improve the accuracy of fault type diagnosis,this paper uses the industrial Internet to send high-frequency vibration signal data in batch to a data analysis server,combining ensemble empirical modal decomposition with curve quadratic coding to obtain higher-order coded features with richer feature information.Experiments show that the proposed method,effectively improves the correct diagnosis rate of fault types.