L1正则化和BiGRU模型的轴承状态预测研究  

Research on bearing condition prediction based on L1 regularization and BiGRU model

作　　者：孙柳萌 杨永杰[1] 张宁涛 Sun Liumeng;Yang Yongjie;Zhang Ningtao(School of Information Science and Technology,Nantong University,Nantong 226019,China)

机构地区：[1]南通大学信息与科学技术学院,南通226019

出　　处：《电子测量技术》2024年第4期58-65,共8页Electronic Measurement Technology

摘　　要：针对轴承健康状态无法直观监测以及预测问题,设计了一种L1正则化的双向门控循环单元模型和Bray-Curtis距离共同构建的健康指标,该指标能够直观表示轴承的健康状态。首先运用L1正则化对现阶段轴承振动数据提取有效特征作为退化特征,振动数据第一个时间窗的特征作为健康特征,然后计算轴承退化特征和健康特征之间的Bray-Curtis距离,构建轴承的HI。通过云监控平台实时监测轴承的健康状态并采用BiGRU模型预测未来的健康状态,一旦轴承的HI超过变化率阈值,平台即刻报警,实现了轴承的健康状态预测。将本模型与双向长短期记忆网络以及双向长短期记忆网络-注意力机制模型作比较,结果表明本模型的准确度为97.52%,远高于另外两种模型,且模型更加轻量化,体现出本方法的实用性。Aiming at the problem that the health status of bearings cannot be directly monitored and predicted,we designed a L1 regularized bidirectional gating recurrent unit model and a health index constructed by Bray Curtis distance,which can directly represent the health status of bearings.Firstly,L1 regularization is used to extract effective features from the current bearing vibration data as degradation features,and the features of the first time window of the vibration data as health features.Then,the Bray Curtis distance between the bearing degradation features and health features is calculated to construct the HI of the bearing.The health status of the bearing is monitored in real time through the cloud monitoring platform,and the future health status is predicted using the BiGRU model.Once the HI of the bearing exceeds the change rate threshold,the platform will alarm immediately,and the health status of the bearing is predicted.The model is compared with bidirectional long short term memory and bidirectional long short term memory with attention models.The results show that the accuracy of this model is 97.52%,much higher than the other two models,and the model is more lightweight,which reflects the practicability of this method.

关 键 词：双向门控循环单元 特征提取 健康指标 状态监测 

分 类 号：TP277[自动化与计算机技术—检测技术与自动化装置]