基于遗传KNN聚类的机械加工故障趋势预测模型
|
摘要
为了提高机械加工过程中的故障状态监测能力,提出一种基于遗传KNN聚类的机械加工故障趋势预测模型。采用大数据关联规则挖掘方法进行机械加工的故障特征信息采集,对采集的机械加工故障状态特征量采用K均值(KNN)方法进行数据聚类处理,结合遗传进化方法进行机械加工故障状态趋势的特征分类学习,采用Hilbert谱提取方法把机械零部件加工过程中的异常状态数据进行特征分解和状态参量提取,根据机械加工的故障状态特征参量提取值进行信息融合,建立机械加工故障趋势预测的专家系统模型,实现机械加工故障趋势预测。
In order to improve the ability of fault state monitoring in machining, a fault trend prediction model based on genetic KNN clustering was proposed. Big data association rule mining method is used to collect fault feature information of machining, and K-means(KNN) method is used to cluster data. Combined with genetic evolution method, the feature classification of fault state trend in machining is studied, and the abnormal state data in machining process are decomposed and state parameters are extracted by Hilbert spectrum extraction method. According to the characteristic parameters of the fault state of machining, the information fusion is carried out, and the expert system model for predicting the fault trend of machining is established, which realizes the prediction of fault trend in machining.
In order to improve the ability of fault state monitoring in machining, a fault trend prediction model based on genetic KNN clustering was proposed. Big data association rule mining method is used to collect fault feature information of machining, and K-means(KNN) method is used to cluster data. Combined with genetic evolution method, the feature classification of fault state trend in machining is studied, and the abnormal state data in machining process are decomposed and state parameters are extracted by Hilbert spectrum extraction method. According to the characteristic parameters of the fault state of machining, the information fusion is carried out, and the expert system model for predicting the fault trend of machining is established, which realizes the prediction of fault trend in machining.
引文
[1] 高志春,陈冠玮,胡光波,等.倾斜因子K均值优化数据聚类及故障诊断研究[J].计算机与数字工程,2014,42(1):14-18.
[2] 黄潮.云计算环境下的海量光纤通信故障数据挖掘算法研究[J].激光杂志,2017,38(1):96-100.
[3] 孙云嵩,于德介,陈向民,等.基于信号共振稀疏分解的阶比分析及其在齿轮故障诊断中的应用[J].振动与冲击,2013,32(16):88-94.
[4] 彭雄斌,龚国芳,廖湘平,等.微位移控制液压系统建模与模型辨识[J].机械工程学报,2017,53(22):206-211.
[5] 马子魁,陈文华.基于滚动蠕滑理论的球轴承摩擦力矩计算方法[J].机械工程学报,2017,53(22):219-224.
[6] Bauer F,Romer U,Fidlin A,et al.Optimization of energy efficiency of walking bipedal robots by use of elastic couplings in the form of mechanical springs[J].Nonlinear Dynamics,2016,83(3):1275-1301.
[7] 李兵,徐榕,贾春宁,等.基于自适应形态提升小波与改进非负矩阵分解的发动机故障诊断方法[J].兵工学报,2013,34(3):353-360.
[8] 王姝,常玉清,杨洁,等.时段划分的多向主元分析间歇过程监测及故障变量追溯[J].控制理论与应用,2011,28(2):149-156.
[9] 陈炜,余跃庆,张绪平,等.欠驱动柔性机器人的动力学建模与耦合特性[J].机械工程学报,2006,42(6):16-23.
[10] 方群,张则强,李明.面向多目标拆卸线平衡问题的一种改进粒子群优化算法[J].现代制造工程,2016(4):8-15.
[11] Wang D X,Song A G,Wen X L,et al.Measurement uncertainty evaluation of conicity error inspected on CMM[J].Chinese Journal of Mechanical Engineering,2016,29(1):212-218.
[12] 杨俊,周丙寅,张毅,等.基于递归图分析的压缩机故障诊断方法研究[J].计算机与数字工程,2013,41(6):984-986.
[2] 黄潮.云计算环境下的海量光纤通信故障数据挖掘算法研究[J].激光杂志,2017,38(1):96-100.
[3] 孙云嵩,于德介,陈向民,等.基于信号共振稀疏分解的阶比分析及其在齿轮故障诊断中的应用[J].振动与冲击,2013,32(16):88-94.
[4] 彭雄斌,龚国芳,廖湘平,等.微位移控制液压系统建模与模型辨识[J].机械工程学报,2017,53(22):206-211.
[5] 马子魁,陈文华.基于滚动蠕滑理论的球轴承摩擦力矩计算方法[J].机械工程学报,2017,53(22):219-224.
[6] Bauer F,Romer U,Fidlin A,et al.Optimization of energy efficiency of walking bipedal robots by use of elastic couplings in the form of mechanical springs[J].Nonlinear Dynamics,2016,83(3):1275-1301.
[7] 李兵,徐榕,贾春宁,等.基于自适应形态提升小波与改进非负矩阵分解的发动机故障诊断方法[J].兵工学报,2013,34(3):353-360.
[8] 王姝,常玉清,杨洁,等.时段划分的多向主元分析间歇过程监测及故障变量追溯[J].控制理论与应用,2011,28(2):149-156.
[9] 陈炜,余跃庆,张绪平,等.欠驱动柔性机器人的动力学建模与耦合特性[J].机械工程学报,2006,42(6):16-23.
[10] 方群,张则强,李明.面向多目标拆卸线平衡问题的一种改进粒子群优化算法[J].现代制造工程,2016(4):8-15.
[11] Wang D X,Song A G,Wen X L,et al.Measurement uncertainty evaluation of conicity error inspected on CMM[J].Chinese Journal of Mechanical Engineering,2016,29(1):212-218.
[12] 杨俊,周丙寅,张毅,等.基于递归图分析的压缩机故障诊断方法研究[J].计算机与数字工程,2013,41(6):984-986.