摘要
以矿井排水系统的离心泵为研究对象,介绍了包括机器学习方法、多元统计分析方法、特征量提取方法和信息融合方法在内的4种基于数据驱动的矿井主排水设备寿命预测方法的基本原理、相关案例、优缺点、尚未解决的问题及其在离心泵寿命预测中的应用;指出了离心泵寿命预测的发展趋势:寿命衰退指标应多样化,只有离心泵的各类指标正常,才能表明离心泵运行正常,多变量综合考虑使预测可靠性更高;决策层信息应高度融合,振动信号、动态摩擦力矩、扬程等因素都会随着寿命的衰退发生一定的变化,将这些信息融合用于寿命预测,效果会更好;融合特征层信息,将多种预测模型进行融合,或者建立一个集更多优点于一体的混合模型,才能更好地满足工业要求。
Taking centrifugal pump of mine drainage system as research object,the paper introduced basic principles,related cases,advantages and disadvantages,unsolved problems of four kinds of life prediction methods based on data driven,namely machine learning method,multivariate statistical analysis method,characteristic extracting method and information fusion method,and expounded their applications in centrifugal pump life prediction.Meanwhile it pointed out development trend of the centrifugal pump life prediction：life recession index should be diversified,and all kinds of normal centrifugal pump indexes show that the centrifugal pump works normally,the more comprehensive consideration,the higher theprediction reliability;decision layer information should be highly integrated,and factors such as vibration signal,dynamic friction torque and pump head will change with decay of life,so results will be better to fuse these information into life prediction;feature layer information should be integrated,and integrating various prediction models or establishing a hybrid model with many advantages can better meet industrial requirements.
出处
《工矿自动化》
北大核心
2017年第11期39-48,共10页
Journal Of Mine Automation
基金
山西省科技重大专项项目(20131101029)
关键词
离心泵
寿命预测
数据驱动
机器学习
多元统计分析
特征量提取
信息融合
centrifugal pump
life prediction
data driven
machine learning
multivariate statistical analysis
feature extraction
information fusion
作者简介
郭文琪（1991-），男，山西忻州人，硕士研究生，研究方向为矿井主排水设备的状态监测与寿命管理，E-mail：18234132660@163．com。
