Fault feature extraction method of rolling bearing based on adaptive MOMEDA
-
摘要:
由于环境噪声会掩盖滚动轴承故障信号，导致故障特征难以提取。为解决这一问题，提出一种基于烟花优化算法（fireworks optimization algorithm，FWA）优化多点最优最小熵解卷积算法（multi-point optimal minimum entropy deconvolution algorithm，MOMEDA）的强噪声干扰下滚动轴承早期故障特征提取方法。该方法首先以包络谱峰值因子作为适应度值，使用FWA的全局搜索能力自适应选择MOMEDA方法的最佳参数组合；其次利用MOMEDA算法增强早期故障信号；增强后的信号通过集成经验模态分解（ensemble empirical mode decomposition，EEMD）进行分解，并构建多尺度模糊熵特征集；最后通过支持向量机（support vector machine，SVM）进行分类识别。实验结果表明，与最小熵反卷积方法（Minimum entropy deconvolution，MED）和最大相关峭度解卷积方法（maximum correlated kurtosis deconvolution，MCKD）相比，该方法的分类准确率分别提高了12.5%和21.7%。
-
关键词:
- 滚动轴承 /
- 多点最优最小熵解卷积算法 /
- 烟花优化算法 /
- 特征提取 /
- 振动信号
Abstract:Because the environmental noise will mask the fault signal of the rolling bearing, it is arduous to extract the fault feature. To address this issue, a fireworks optimization algorithm (FWA) based on multi-point optimal minimum entropy deconvolution algorithm (MOMEDA) was presented to optimize the early fault feature extraction method of the rolling bearing under intense noise interference. In this approach, the peak factor of the envelope spectrum was regarded as the fitness value, and the global search capacity of FWA was utilized to adaptively select the optimal parameter combination of the MOMEDA method. Subsequently, the MOMEDA algorithm was employed to enhance the early fault signal. The enhanced signal was decomposed by ensemble empirical mode decomposition (EEMD), and the multi-scale fuzzy entropy feature set was constructed. Finally, the classification was identified by support vector machine (SVM). The experimental results indicated that, compared with minimum entropy deconvolution (MED) and maximum correlated kurtosis deconvolution (MCKD), the classification accuracy of this method increased by 12.5% and 21.7% respectively.
-
图 2 基于自适应MOMEDA的故障特征提取方法流程图
Figure 2. Flow chart of fault diagnosis method based on adaptive MOMEDA
图 3 内圈故障初始信号优化次数迭代图
Figure 3. Iteration diagram of initial signal optimization times for inner ring faults
图 4 内圈失效振动信号时域对比
Figure 4. Time domain comparison of inner ring failure vibration signal
图 6 滚动体故障振动信号时域对比图
Figure 6. Time domain comparison of rolling element failure vibration signal
表 1 6205轴承参数
Table 1. 6205 bearing parameters
内径/
mm外径/
mm高度/
mm滚动体
直径/mm节圆
直径/mm滚动体
个数25 52 15 7.9 39 9 
下载: 导出CSV
表 2 3种故障类型的最优参数L和T
Table 2. Optimal parameters L and T for the three fault types
故障类型 L T 无故障 133 72 内圈故障 344 74 外圈故障 111 77 滚动体故障 164 72
下载: 导出CSV
表 3 DDS的3种故障类型的最优参数L和T
Table 3. Optimal parameters L and T of the three fault types for DDS
故障类型 L T 内圈故障 268 79 外圈故障 427 76 滚动体故障 121 74
下载: 导出CSV
表 4 3种类型故障特征集的分类和识别率
Table 4. Classification and recognition rate of three types of fault feature sets
% 故障类型 方法 MED MCKD MOMEDA 自适应MOMEDA 内圈故障 87 99 93 93 外圈故障 59 64 79 94 滚动体故障 64 72 81 99 平均识别率 84.5 75.3 92.5 97.7
下载: 导出CSV
-
[1] CHE Changchang, WANG Huawei, XIONG Minglan, et al. Few-shot fault diagnosis of rolling bearing under variable working conditions based on ensemble meta-learning[J]. Digital Signal Processing, 2022, 131: 103777. doi: 10.1016/j.dsp.2022.103777 [2] 陈仁祥, 唐林林, 胡小林, 等. 不同转速下基于深度注意力迁移学习的滚动轴承故障诊断方法[J]. 振动与冲击, 2022, 41(12): 95-101, 195. CHEN Renxiang, TANG Linlin, HU Xiaolin, et al. A rolling bearing fault diagnosis method based on deep attention transfer learning at different rotations[J]. Journal of Vibration and Shock, 2022, 41(12): 95-101, 195. (in ChineseCHEN Renxiang, TANG Linlin, HU Xiaolin, et al. A rolling bearing fault diagnosis method based on deep attention transfer learning at different rotations[J]. Journal of Vibration and Shock, 2022, 41(12): 95-101, 195. (in Chinese) [3] 陈璠. 环境激励下的场地振动衰减规律试验研究[D]. 北京: 北京建筑大学, 2019. CHEN Fan. Experimental study on vibration damping rule of free space under environmental excitation[D]. Beijing: Beijing University of Civil Engineering and Architecture, 2019. (in ChineseCHEN Fan. Experimental study on vibration damping rule of free space under environmental excitation[D]. Beijing: Beijing University of Civil Engineering and Architecture, 2019. (in Chinese) [4] ZHANG Xiao, ZHAO Boyang, LIN Yun. Machine learning based bearing fault diagnosis using the case western reserve university data: a review[J]. IEEE Access, 2021, 9: 155598-155608. doi: 10.1109/ACCESS.2021.3128669 [5] ENDO H, RANDALL R B. Enhancement of autoregressive model based gear tooth fault detection technique by the use of minimum entropy deconvolution filter[J]. Mechanical Systems and Signal Processing, 2007, 21(2): 906-919. doi: 10.1016/j.ymssp.2006.02.005 [6] 杨岗, 徐五一, 邓琴, 等. 基于振动信号的滚动轴承复合故障诊断研究综述[J]. 西华大学学报(自然科学版), 2024, 43(1): 48-69. YANG Gang, XU Wuyi, DENG Qin, et al. A review of rolling bearing compound fault diagnosis based on vibration signals[J]. Journal of Xihua University (Natural Science Edition), 2024, 43(1): 48-69. (in ChineseYANG Gang, XU Wuyi, DENG Qin, et al. A review of rolling bearing compound fault diagnosis based on vibration signals[J]. Journal of Xihua University (Natural Science Edition), 2024, 43(1): 48-69. (in Chinese) [7] TIAN Tian, TANG Guiji, TIAN Yinchu, et al. Blind deconvolution based on correlation spectral negentropy for bearing fault[J]. Entropy, 2023, 25(3): 543. doi: 10.3390/e25030543 [8] WIGGINS R A. Minimum entropy deconvolution[J]. Geoexploration, 1978, 16(1/2): 21-35. [9] GAO Yangde, AHMAD Z, KIM J M. Fault diagnosis of rotating machinery using an optimal blind deconvolution method and hybrid invertible neural network[J]. Sensors, 2024, 24(1): 256. doi: 10.3390/s24010256 [10] MCDONALD G L, ZHAO Qing, ZUO M J. Maximum correlated Kurtosis deconvolution and application on gear tooth chip fault detection[J]. Mechanical Systems and Signal Processing, 2012, 33: 237-255. doi: 10.1016/j.ymssp.2012.06.010 [11] MCDONALD G L, ZHAO Qing. Multipoint optimal minimum entropy deconvolution and convolution fix: application to vibration fault detection[J]. Mechanical Systems and Signal Processing, 2017, 82: 461-477. doi: 10.1016/j.ymssp.2016.05.036 [12] TAYYAB S M, CHATTERTON S, PENNACCHI P. Intelligent defect diagnosis of rolling element bearings under variable operating conditions using convolutional neural network and order maps[J]. Sensors, 2022, 22(5): 2026. doi: 10.3390/s22052026 [13] XIAO Chaoang, TANG Hesheng, REN Yan, et al. Adaptive MOMEDA based on improved advance-retreat algorithm for fault features extraction of axial piston pump[J]. ISA Transactions, 2022, 128: 503-520. doi: 10.1016/j.isatra.2021.10.033 [14] 祝小彦, 王永杰. 基于MOMEDA与Teager能量算子的滚动轴承故障诊断[J]. 振动与冲击, 2018, 37(6): 104-110, 123. ZHU Xiaoyan, WANG Yongjie. Fault diagnosis of rolling bearings based on the MOMEDA and Teager energy operator[J]. Journal of Vibration and Shock, 2018, 37(6): 104-110, 123. (in Chinese doi: 10.13465/j.cnki.jvs.2018.06.017ZHU Xiaoyan, WANG Yongjie. Fault diagnosis of rolling bearings based on the MOMEDA and Teager energy operator[J]. Journal of Vibration and Shock, 2018, 37(6): 104-110, 123. (in Chinese) doi: 10.13465/j.cnki.jvs.2018.06.017 [15] TAN Ying, ZHU Yuanchun. Fireworks algorithm for optimization[M]//Advances in Swarm Intelligence. Berlin, Heidelberg: Springer, 2010: 355-364. [16] 周鑫. 基于多策略改进烟花算法的多目标配电网优化重构研究[D]. 阜新: 辽宁工程技术大学, 2023. ZHOU Xin. Research on multi-objective distribution network optimization and reconstruction based on multi-strategy improved fireworks algorithm[D]. Fuxin: Liaoning Technical University, 2023. (in ChineseZHOU Xin. Research on multi-objective distribution network optimization and reconstruction based on multi-strategy improved fireworks algorithm[D]. Fuxin: Liaoning Technical University, 2023. (in Chinese) [17] 申晓宁, 游璇, 陈庆洲, 等. 采用双档案协同进化离散多目标烟花算法的低碳疫苗冷链优化配送[J]. 计算机工程与科学, 2022, 44(12): 2255-2265. SHEN Xiaoning, YOU Xuan, CHEN Qingzhou, et al. A multi-objective fireworks algorithm with two-archive coevolution for low-carbon cold chain distribution optimization of vaccines[J]. Computer Engineering & Science, 2022, 44(12): 2255-2265. (in Chinese doi: 10.3969/j.issn.1007-130X.2022.12.020SHEN Xiaoning, YOU Xuan, CHEN Qingzhou, et al. A multi-objective fireworks algorithm with two-archive coevolution for low-carbon cold chain distribution optimization of vaccines[J]. Computer Engineering & Science, 2022, 44(12): 2255-2265. (in Chinese) doi: 10.3969/j.issn.1007-130X.2022.12.020 [18] 汪和平, 赵登宇, 陈梦凯. 基于改进多目标烟花算法的预制构件配送优化研究[J]. 管理评论, 2022, 34(10): 282-290. WANG Heping, ZHAO Dengyu, CHEN Mengkai. Research on distribution optimization of prefabricated components based on improved multi-objective fireworks algorithm[J]. Management Review, 2022, 34(10): 282-290. (in Chinese doi: 10.3969/j.issn.1003-1952.2022.10.glpl202210024WANG Heping, ZHAO Dengyu, CHEN Mengkai. Research on distribution optimization of prefabricated components based on improved multi-objective fireworks algorithm[J]. Management Review, 2022, 34(10): 282-290. (in Chinese) doi: 10.3969/j.issn.1003-1952.2022.10.glpl202210024 [19] 郑健. 烟花算法在多目标优化中的应用研究[D]. 桂林: 桂林理工大学, 2017. ZHENG Jian. Application research of fireworks algorithm in multi-objective optimization[D]. Guilin: Guilin University of Technology, 2017.ZHENG Jian. Application research of fireworks algorithm in multi-objective optimization[D]. Guilin: Guilin University of Technology, 2017. [20] Case Western Reserve University. Seeded fault test data[OL]. [2024-09-17]. https://engineering.case.edu/bearingdatacenter. [21] SMITH W A, RANDALL R B. Rolling element bearing diagnostics using the case western reserve university data: a benchmark study[J]. Mechanical Systems and Signal Processing, 2015, 64/65: 100-131. -
点击查看大图
计量
- 文章访问数: 86
- HTML浏览量: 60
- PDF量: 18
- 被引次数: 0