针对传统模糊聚类（FCM）方法对故障进行聚类的依据是原始数据之间的相似性,在滚动轴承的故障诊断中无法提取轴承数据的深层特征,对于耦合故障、微弱故障等复杂情况下,不同故障的特征难以有效区分,导致故障诊断准确率较低的问题,提出AE-IFCM轴承故障诊断方法。利用自动编码器（AE）网络提取轴承故障的样本特征,再利用改进的FCM（IFCM）进行故障诊断,通过对AE网络提取的抽象特征聚类,不仅可最大限度地利用样本数据,也能降低模型陷入局部极小值的风险。通过在凯斯西储大学轴承故障数据集中的实验表明,AE-IFCM能提高轴承故障诊断的准确性。
Abstract
The traditional fuzzy clustering method clustering the fault is based on the similarity between the original data. But in the fault diagnosis of rolling bearings, that way cannot extracted the deep features of the bearing data well. Especially, in the complex conditions such as coupling faults and weak faults, it is difficult to effectively distinguish the different faults features, which results in low accuracy. In order to solve that problem, we propose the AE-IFCM bearing fault diagnosis method. In this framework, the Auto-Encoder（AE） network is used to extract the deep features of the bearing fault samples, and then we utilize the improved FCM for fault diagnosis. It clusters the abstract features extracted by the AE network to maximize the utilization of the sample data and reduce the risk of the model falling into a local minimum. Experiments in the Case Western Reserve university bearing fault data collection show that AE-IFCM can improve the accuracy of bearing fault diagnosis.
关键词
故障诊断 /
自编码器 /
模糊聚类 /
滚动轴承
Key words
fault diagnosis /
autoencoder /
fuzzy clustering /
roll bearing
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 周东华, 胡艳艳. 动态系统的故障诊断技术[J]. 自动化学报, 2009, 35(6): 748-758.
ZHOU D H, HU Y Y.Fault diagnosis techniques for dynamic systems[J]. Acta automatica sinica, 2009, 35(6): 748-758.
[2] 李昂, 付敬奇, 沈华明, 等. 基于模糊聚类和猫群算法的室内定位算法[J]. 仪器仪表学报, 2020, 41(1): 185-194.
LI A, FU J Q, SHEN H M, et al.Indoor positioning algorithm based on fuzzy clustering and cat swarm optimization[J]. Chinese journal of scientific instrument, 2020, 41(1): 185-194.
[3] 张天瑞, 于天彪, 赵海峰, 等. 数据挖掘技术在全断面掘进机故障诊断中的应用[J]. 东北大学学报(自然科学版), 2015, 36(4): 527-531, 541.
ZHANG T R, YU T B, ZHAO H F, et al.Application of data mining technology in fault diagnosis of tunnel boring machine[J]. Journal of Northeastern University (natural science), 2015, 36(4): 527-531, 541.
[4] FAN H, SHAO S, ZHANG X, et al.Intelligent fault diagnosis of rolling bearing using FCM clustering of EMD-PWVD vibration images[J]. IEEE access, 2020, 8:145194-145206.
[5] BESSA I V D, PALHARES R M, D'ANGELO M F S V, et al. Data-driven fault detection and isolation scheme for a wind turbine benchmark[J]. Renewable energy, 2016, 87:634-645.
[6] LYU G, CHENG H, ZHAN H, et al.Fault diagnosis of power transformer based on multi-layer SVM classifier[J]. Proceedings of electric power system & automation, 2005, 75(1): 9-15.
[7] 石鑫, 朱永利, 萨初日拉, 等. 基于深度信念网络的电力变压器故障分类建模[J]. 电力系统保护与控制, 2016, 44(1): 71-76.
SHI X, ZHU Y L, SACHURILA, et al. Power transformer fault classifying model based on deep belief network[J]. Power system protection and control, 2016, 44(1): 71-76.
[8] 张秦梫, 宋辉, 姜勇, 等. 基于OS-ELM的变压器局部放电模式识别[J]. 高电压技术, 2018, 44(4): 1122-1130.
ZHANG Q Q, SONG H, JIANG Y, et al.Partial discharge pattern recognition of transformer based on OS-ELM[J]. High voltage engineering, 2018, 44(4): 1122-1130.
[9] NOORI M, EFFATNEJAD R, HAJIHOSSEINI P.Using dissolved gas analysis results to detect and isolate the internal faults ofpower transformers by applying a fuzzy logic method[J]. IET generation, transmission & distribution, 2017, 11(10): 2721-2729.
[10] 贾亚飞, 朱永利, 高佳程, 等. 基于样本加权FCM聚类的未知类别局部放电信号识别[J]. 电力自动化设备, 2018, 38(12): 107-112.
JIA Y F, ZHU Y L, GAO J C,et al.Recognition of unknown partial discharge signals based on sample- weighted FCM clustering[J]. Electric power automation equipment, 2018, 38(12): 107-112.
[11] 肖满生, 张龙信, 张晓丽, 等. 一种改进的区间型不确定数据模糊聚类方法[J]. 电子与信息学报, 2020, 42(8): 1968-1974.
XIAO M S, ZHANG L X, ZHANG X L, et al.An improved fuzzy clustering method for interval uncertain data[J]. Journal of electronics and information technology, 2020, 42(8): 1968-1974.
[12] 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.
SUN H X, SUN Z X, ZHANG J X.Fault diagnosis of wind turbine alternator based on parallel fuzzy c-means clustering algorithm[J]. Acta energiae solaris sinica, 2020, 41(3): 8-14.
[13] CHUAN L, MARIELA C, DIEGO C, et al.A comparison of fuzzy clustering algorithms for bearing fault diagnosis[J]. Journal of intelligent and fuzzy systems, 2018, 34(6): 1-16.
[14] WANG C, YANG H, MENG C.An efficient fault diagnosis strategy based on SVDD and fuzzy clustering for ground-based electronic equipment[C]//2019 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC), Dalian, China, 2019.
[15] 尹爱军, 王昱, 戴宗贤, 等. 基于变分自编码器的轴承健康状态评估[J]. 振动·测试与诊断, 2020, 40(5): 1011-1016, 1030.
YIN A J, WANG Y, DAI Z X, et al.Evaluation method of bearing health state based on variational auto encoder[J]. Vibration test and diagnosis, 2020, 40(5): 1011-1016, 1030.
基金
国家自然科学基金（62063020; 61763028）; 甘肃省自然科学基金（20JR5RA463）
PDF(1666 KB)
