CTD气流式烘丝机设备故障预测  

Fault Prediction of CTD Air Flow Dryer

作　　者：詹伟剑 刘永明 谢鹏 刘志博 赵转哲[1] ZHAN Wei-jian;LIU Yong-ming;XIE Peng;LIU Zhi-bo;ZHAO Zhuan-zhe(School of Mechanical Engineering,Anhui Polytechnic University,Wuhu Anhui 241000,China;Wuhu Cigarette Factory of China Tobacco Industry Company,Wuhu Anhui 241003,China)

机构地区：[1]安徽工程大学机械工程学院,安徽芜湖241000 [2]安徽中烟工业公司芜湖卷烟厂,安徽芜湖241003

出　　处：《淮阴工学院学报》2023年第1期12-17,共6页Journal of Huaiyin Institute of Technology

基　　金：2021年度安徽省市场监督管理局科技计划项目(2021MK005);工业装备质量大数据工业和信息化部重点实验室开放课题(2021-IEQBD-05)。

摘　　要：CTD气流式烘丝机是目前烟草行业主流的设备,其在生产过程中存在出丝不均匀、干燥不达标、断流、堵丝等故障,最终影响卷烟的品质、降低生产效率。为准确预测工艺过程中的故障,提出一种基于朴素贝叶斯方法的CTD烟丝干燥设备故障预测模型。首先从获取的CTD气流式烘丝机的日常运行数据中提取特征量信息,在此基础上完成数据模型的建立,然后将建立好的数据集带入到朴素贝叶斯模型、决策树模型和线性判别模型进行对比分析。结果显示朴素贝叶斯模型的预测效果优于决策树模型和线性判别模型,且预测的准确率达到99.8%,说明该故障预测的评估模型实现了对CTD烟丝干燥设备故障的准确预测,能够解决工艺过程中故障预测的问题。CTD air flow dryer is the mainstream equipment in the tobacco industry at present.There are some faults in the production process,such as uneven silk output,substandard drying,cut-off and silk blockage,which will eventually affect the quality of cigarettes and reduce the production efficiency.How to accurately predict the faults in the process has become an urgent problem to be solved.For this reason,a Bayesian prediction method based on CTD is proposed.Firstly,the required feature information is extracted from the daily operation data of CTD air dryer,and then the data model is established based on the extracted information,and then the established data set is brought into naive Bayesian model,decision tree model and linear discriminant model for comparative analysis.The results show that the prediction effect of naive Bayesian model is better than decision tree model and linear discriminant model,and the prediction accuracy reaches 99.8%,which shows that the evaluation model of fault prediction realizes the accurate prediction of CTD cut tobacco drying equipment fault,and solves the problem that it is difficult to predict the fault in the process.

关 键 词：朴素贝叶斯方法 故障预测 CTD气流式烘丝机 特征量 准确率 

分 类 号：TH17[机械工程—机械制造及自动化]