云边端协同的机床刀具故障智能诊断系统研究

Research on Intelligent Tool Fault Diagnosis System of Machine Tools with Cloud-Edge-Device Collaboration

为提高机床刀具磨损故障诊断精度,借助三轴加速度传感器采集机床刀具磨损振动数据,并以此为基础,提出一种基于长短时记忆网络与多尺度卷积神经网络集成的机床刀具故障诊断算法,挖掘机床刀具在不同故障模式下的空时域多尺度特征,实现机床刀具磨损状态的精准识别。同时,为满足实际产线对故障诊断的高实时性要求,设计一种适用于机床刀具故障诊断的云边端协同架构,通过底层产线、边缘节点与工业云平台的高效协同,实现机床刀具故障的及时预警。研究结果表明,所提云边端协同的机床刀具故障智能诊断系统可实现机床刀具磨损状态的精准识别,同时可缩短故障诊断任务的完成时间。

In order to improve the accuracy of tool wearing fault diagnosis,three-axis acceleration sensors were adopted to collect the wearing vibration data of tools.Based on the data analysis,a fault diagnosis algorithm of tools was proposed based on the integration of long short-term memory and multi-scale convolutional neural networks,the multi-scale features in both spatial and temporal domains were captured,the accurate recognition of tool wearing status was realized.Meanwhile,a cloud-edge-device collaboration architecture applicable to tool fault diagnosis was designed to achieve the timely warning of tool faults by efficient collaboration among the bottom production lines,edge servers and the cloud industrial internet platform.The results show that the proposed system may accurately identify the tool faults and reduce the maximum completion time delay of fault diagnosis tasks.