摘要
本文对工业设备异常温度变化报警模型做了调研汇总,机器学习算法在温度预测与故障诊断过程中发挥了不可忽视的作用。基于高速轴承运行过程的温度样本做分析,比较了线性回归模型和GM(1,1)模型的预测误差,发现GM(1,1)模型在机械设备运转过程中的温度变化预测较线性回归模型更准确,模型精度达到99.59%。本文对机械设备部件运行过程中温度异常变化预警有一定参考意义。
This paper makes a survey and summary of the abnormal temperature change alarm model of industrial equipment,and the machine learning algorithm plays an important role in the process of temperature prediction and fault diagnosis.Based on the analysis of the temperature sample of high-speed bearing operation process,comparing the prediction error of linear regression model and GM(1,1)model,we found that the temperature change prediction of GM(1,1)model during the operation of mechanical equipment is more accurate than that of the linear regression model,and the model accuracy reached 99.59%.This paper has some reference significance for the early warning of abnormal temperature change in the operation process of mechanical equipment components.
作者
李腾龙
马卫平
Li Tenglong;Ma Weiping(School of Computer and Artificial Intelligence,Zhengzhou University,Zhengzhou,China;Zhengzhou Research Institute of Mechanical Engineering Co.,Ltd.,Zhengzhou,China)
出处
《科学技术创新》
2024年第17期21-24,共4页
Scientific and Technological Innovation
关键词
机械设备
灰色预测
线性回归
异常高温预测
mechanical equipment
gray prediction
linear regression
abnormal high temperature prediction
作者简介
李腾龙(1989-),男,硕士研究生在读,中级工程师,主要研究方向:计算机应用技术;通讯作者:马卫平(1976-),男,本科,高级工程师,主要从事机器状态监测、机械振动故障诊断及动平衡技术研究应用工作。
