摘要
针对热量表使用寿命只能粗略判断(通过耐久性试验,估算使用寿命为5年)的问题,提出一种基于回归分析的热量表使用寿命预测模型建立方法,利用灰色关联分析法确定各因素与使用寿命的关联度大小,通过一元多项式回归分析和多元非线性回归分析,多方向获取各个影响因素与其使用寿命的变化关系,采用残差分析、拟合优度检验和置信区间检验验证了模型的准确性。结果表明,基于回归分析的热量表使用寿命预测方法与试验数据契合度高,为其型式评价、质量分析等奠定了基础。
Aiming at the problem that the service life of heat meters can only be roughly judged(through the durability test,the service life is 5 years),a method of predicting the service life of heat meters based on regression analysis is proposed.Grey relational degree analysis was used to determine the degree of correlation between each factor and its service life.The variable relationship between each influencing factor and its service life was obtained in multiple directions by one-element polynomial regression analysis and multiple nonlinear regression analysis.The accuracy of the model was verified by residual analysis,goodness of fit test and confidence interval test.The results show that the method based on regression analysis is accurate and reliable,which lays a foundation for its type evaluation and quality analysis.
作者
李锋
周秉直
张俊亮
韩婉婷
周彬
LI Feng;ZHOU Bingzhi;ZHANG Junliang;HAN Wanting;ZHOU Bin(Shaanxi Institute of Metrology Science,Shaanxi Xi′an 710100,China)
出处
《工业仪表与自动化装置》
2024年第5期122-128,共7页
Industrial Instrumentation & Automation
关键词
耐久性试验
寿命预测
灰色关联分析
回归分析
durability test
service life prediction
grey relational analysis
regression analysis