摘 要:近年来随着大数据技术的成熟,家用电器在线故障诊断也得到了普及。以洗衣机用的异步电机为对象,提出通过提取定子电流幅值作为特征向量与极端梯度提升算法结合的故障诊断方法。并将该方法与支持向量机、梯度提升决策树算法在实验采集数据和大数据支持下进行对比分析。其仿真结果表明,极端梯度提升算法在处理洗衣机用异步电机故障时,能有效地进行故障类型诊断,诊断精度和泛化能力较强,能够适用于日常生活和商业需要。
关键词:特征提取;梯度提升决策树;XGBoost;异步电机;故障诊断
中图分类号:TM407 文献标识码:A 文章编号:2096-4706(2020)08-0041-04
Fault Diagnosis of Household Three-phase Motor Based on XGBoost Algorithm
SUN Junyixiong,CHEN Yi
(School of Electronic Engineering and Automation,Guilin University of Electronic Technology,Guilin 541004,China)
Abstract:In recent years,with the maturity of big data technology,home appliances online fault diagnosis has also been popular.Taking the asynchronous motor for washing machine as the object,a fault diagnosis method is proposed,which combines the extractionof stator current amplitude as the eigenvector and the XGBoost algorithm. The method is compared with support vector machine and gradient lifting decision tree under the support of experimental data and big data. The simulation results show that the extreme gradient lifting algorithm can effectively diagnose the type of fault when dealing with the fault of asynchronous motor for washing machine,with high accuracy and generalization ability,and can be applied to daily life and commercial needs.
Keywords:feature extraction;gradient lifting decision tree;XGBoost;asynchronous motor;fault diagnosis
参考文献:
[1] 周东华,刘洋,何潇. 闭环系统故障诊断技术综述 [J]. 自动化学报,2013,39(11):1933-1943.
[2] 文成林,吕菲亚,包哲静,等. 基于数据驱动的微小故障诊断方法综述 [J]. 自动化学报,2016,42(9):1285-1299.
[3] 李航. 统计学习方法 [M]. 北京:清华大学出版社,2012.
作者简介:
孙俊佚雄(1993—),男,汉族,湖北荆州人,硕士研究生,研究方向:信号处理与信号集成系统;
通讯作者:
陈以(1963—),男,汉族,广西玉林人,教授,硕士研究生导师,主要研究方向:智能控制、计算机应用技术。