企业离散式智能设备预测性维护综述

Overview of Predictive Maintenance for Discrete Intelligent Equipment in Enterprises

针对智能设备的大量使用且缺乏根据监测大数据进行故障自动分析、判断与处理的问题,研究了基于物联网技术、大数据技术、边云协同技术的智能设备预测性维护框架和模式。提出针对非智能设备安装传感器实现设备智能化的方法。指出边缘计算负责设备工况数据的实时采集、分析,可快速甄别设备故障并实时报警;云计算聚焦同类设备运行海量历史数据的挖掘和分析,形成故障自动预测分析和诊断模式并下载至智能边缘设备。在研究了模型驱动、数据驱动、概率统计驱动、数字孪生和概率数字孪生驱动等故障预测模式后,提出了采用数据驱动的多层级数据融合模式,为制定企业性智能设备维保方案提供借鉴作用。

In order to solve the problem of large usage of intelligent equipment and lack of automatic fault analysis,judgment and processing based on monitoring big data,the all-around intelligent equipment predictive maintenance framework and mode based on IoT technology,big data technology and edge cloud collaboration technology are studied.For the non-intelligent equipment,sensors are installed to realize the equipment intellectualization.The edge computing is responsible for the real-time collection and analysis of equipment condition data,and quickly identifying equipment failures and real-time alarms.Cloud computing focuses on the mining and analysis of massive historical data of similar equipment,so the automatic failure prediction analysis and diagnosis mode is formed,which is downloaded to the intelligent edge equipment.After studying the fault prediction modes of model driven,data driven,probability statistical driven,digital twin and probability digital twin drive,a data-driven multilevel data fusion model is proposed,which can be used as a reference for making the maintenance plan of all-round intelligent equipment in enterprises.