[1]杨华芬.大数据处理环境下大型机组设备故障可视化诊断方法研究[J].机械与电子,2022,(05):38-41.
　YANG Huafen.Research on Visualized Diagnosis Method of Large Unit Equipment Failure in Big Data Processing Environment[J].Machinery & Electronics,2022,(05):38-41.
点击复制

大数据处理环境下大型机组设备故障可视化诊断方法研究()

分享到：

机械与电子[ISSN:1001-2257/CN:52-1052/TH]

Title:: Research on Visualized Diagnosis Method of Large Unit Equipment Failure in Big Data Processing Environment

Author(s):: YANG Huafen; ( School of Intelligent Manufacturing and Information Engineering , Shanghai Institute of Commerce and Foreign Languages , Shanghai 201314 , China )

Keywords:: big data processing ; fuzzy subtraction ; large units ; equipment failure ; visual diagnosis ; frequency spectrum

摘要:: 为了提升大型机组设备故障信息的提取效率,实现故障可视化诊断,提出大数据处理环境下大型机组设备故障可视化诊断方法。采用基于工作变形分析( ODS )的振动可视化技术完成大型机组设备的振动分析,获取设备不同模态下的故障频率响应信号,并将其频率谱作为故障特征,利用模糊减法聚类算法获取故障诊断结果;并利用三维平行散点图与人机交互将故障诊断结果可视化呈现。测试结果表明,该方法可通过数据聚类有效完成大型机组设备故障诊断,并且具备较好的可视化效果,可满足大型机组设备故障的可视化需求。

Abstract:: In order to improve the extraction efficiency of large-scale unit equipment fault information and realize the visual diagnosis of faults , a visual diagnosis method for large-scale unit equipment faults in a big data processing environment is proposed.The vibration visualization technology based on operational deformation shape( ODS ) is used to complete the vibration analysis of large unit equipment.The fault frequency response signals under different modes of the equipment are obtained , and the frequency spectrum is taken as the fault feature.The fuzzy subtraction clustering algorithm is used to obtain the fault diagnosis results ; The results of fault diagnosis are visualized by 3D parallel scatter diagram and human-computer interaction.The test results show that the method can effectively complete the fault diagnosis of large scale unit equipment through data clustering , and has a good visualization effect , which can meet the visualization requirements of large-scale unit equipment failure.

[ 1 ] 张健 . 基于 ACSEEMD 和模糊 C 均值聚类的风电机组齿轮箱故障预警[ J ] . 电子器件, 2019 , 42 ( 6 ): 1410-1415.

[ 2 ] 于昊,张吉礼 . 基于在线减法聚类的变频水泵模糊建模方法[ J ] . 暖通空调, 2019 , 49 ( 3 ): 80-86.

[ 3 ] 胡军,尹立群,李振,等 . 基于大数据挖掘技术的输变电设备故障诊断方法[ J ] . 高电压技术,2017 , 43 ( 11 ):3690-3697.

[ 4 ] 陈东宁,张运东,姚成玉,等 . 基于 FVMD 多尺度排列熵和 GK 模糊聚类的故障诊断[ J ] . 机械工程学报, 2018 , 54( 14 ): 16-27.

[ 5 ] 孙鹤旭,孙泽贤,张靖轩 . 基于并行模糊 C 均值聚类的风电机组发电机故障诊断研究 [ J ] . 太阳能学报,2020 , 41 ( 3 ): 8-14.

[ 6 ] 梁耘,王维庆,王海云 . 基于分裂合并策略改进多特征聚类算法的风电机组故障分析[ J ] . 可再生能源, 2017 ,35 ( 10 ): 1537-1543.

[ 7 ] 慈嘉伟,罗健旭 . 基于加权模糊聚类的污水处理过程故障检测[ J ] . 华东理工大学学报(自然科学版), 2018 , 44( 4 ): 504-510.

[ 8 ] 王印松,商丹丹,王艳飞,等 . 改进的模糊聚类在控制系统故障诊断中的应用[ J ] . 计算机工程与科学, 2018 , 40( 2 ): 326-330.

[ 9 ] 吴定海,任国全,王怀光,等 . 基于卷积神经网络的机械故障诊断方法综述[ J ] . 机械强度, 2020 , 42 ( 5 ): 1024-1032.

[ 10 ] 马宏忠,徐艳,魏海增 . 基于 MPE 和改进 K-means算法的分接开关机械故障诊断方法[ J ] . 高压电器,2020 , 56 ( 8 ): 198-204.

[ 11 ] 刘嘉蔚,李奇,陈维荣,等 . 基于多分类相关向量机和模糊 C 均值聚类的有轨电车用燃料电池系统故障诊断方法[ J ] . 中国电机工程学报, 2018 , 38 ( 20 ): 6045-6052.

[ 12 ] 史丽萍,宋朝鹏,李明泽,等 . 基于 SAAFSA 优化加权模糊聚类算法的变压器故障诊断[ J ] . 电测与仪表,2018 , 55 ( 11 ): 12-18.

[ 13 ] 余辉敏,徐永能,陈新,等 . 基于 Bi-LSTM 模型的车载 ATC 设备故障诊断方法[ J ] . 兵器装备工程学报,2021 , 42 ( 2 ): 147-151.

[ 14 ] 杨洪柏,张宏利,刘树林 . 基于可视化异类特征优选融合的滚动轴承故障诊断 [ J ] . 计算机应用,2017 , 37( 4 ): 1207-1211.

更新日期/Last Update: 2022-05-25