Research on fault diagnosis of self-aligning ball bearing based on FCMMWPE-BSASVM combined algorithm
-
摘要: 为了提高机械旋转系统上调心球轴承特征提取和故障识别能力,设计了一种精细复合多元多尺度加权排列熵(fine composite multivariate multi-scale weighted permutation entropy, FCMMWPE)与天牛须搜索支持向量机算法(beetle antennae search algorithm-supportvectormachine, BSASVM)相结合的故障特征提取方法,并采用等度规映射(Isomap)进行故障识别,最后开展故障诊断实例分析。研究结果表明:采用FCMMWPE算法处理状态熵值达到最高,形成更平滑的熵值曲线,广义粗粒化方法具备明显优势。轴承产生局部故障时,形成具有规律特征的振动信号,表明采用FCMMWPE提取调心球轴承故障特征满足可靠性条件并具备明显优势。对文章构建的FCMMWPE与Isomap特征集进行运行故障识别时实现了99.9%的准确率,实现调心球轴承故障高效识别。BSASVM满足更优的故障识别性能,具备更优的模式识别性能和更高处理效率。该研究可以拓宽到其他的机械传动领域,具有很好的应用价值。
-
关键词:
- 精细复合多元多尺度加权排列熵 /
- 支持向量机 /
- 等度规映射 /
- 调心球轴承 /
- 故障诊断
Abstract: In order to improve the ability of feature extraction and fault identification of allocatable ball bearings in mechanical rotating system, A fault feature extraction method combined FCMMWPE and BSASVM was designed. and Isomap was used for fault identification. And the fault diagnosis case analysis was carried out. The results show that the FCMMWPE algorithm achieves the highest state entropy and forms a smoother entropy curve, and the generalized coarse-grained method has obvious advantages. When local faults occur, vibration signals with regular characteristics are formed, which indicates that FCMMWPE can meet the reliability conditions and has obvious advantages in extracting fault features of self-allot ball bearings. When FCMMWPE and Isomap feature sets constructed in this paper are used for operation fault identification, 99.9% accuracy is achieved, and self-aligning ball bearing fault identification is realized efficiently. BSASVM provides better fault identification performance, pattern recognition performance, and processing efficiency. The research can be extended to other mechanical transmission fields and has good application value. -
表 1 平均识别时间
分类器 平均识别时间/s 分类器 平均识别时间/s PSO-SVM 2.283 SVM 5.582 SA-SVM 4.734 改进SVM 0.284 -
[1] 赵小强, 张亚洲. 利用改进卷积神经网络的电机轴承变工况故障诊断方法[J]. 西安交通大学学报, 2021, 55(12): 108-118. [2] 余萍, 曹洁. 优化堆叠降噪自动编码器电机轴承故障诊断[J]. 太阳能学报, 2021, 42(11): 307-314. [3] 周付明, 杨小强, 申金星, 等. 改进多元层次波动色散熵及其在电机轴承故障诊断中的应用[J]. 振动与冲击, 2021, 40(22): 167-174. [4] 路小娟, 石成基. 一种基于概率盒—HGWO优化SVM的电机轴承故障诊断方法[J]. 振动与冲击, 2021, 40(22): 234-241. [5] 邢婷婷, 关阳, 孙登云, 等. 基于FSDPC_Otsu算法的电机轴承故障研究[J]. 计量学报, 2021, 42(11): 1466-1471. doi: 10.3969/j.issn.1000-1158.2021.11.09 [6] 刘颖, 陶建峰, 黄武涛, 等. 小波包能量与CNN相结合的电机轴承故障诊断方法[J]. 机械设计与制造, 2021(11): 127-131. doi: 10.3969/j.issn.1001-3997.2021.11.029 [7] 石怀涛, 尚亚俊, 白晓天, 等. 基于贝叶斯优化的SWDAE-LSTM电机轴承早期故障预测方法研究[J]. 振动与冲击, 2021, 40(18): 286-297. [8] Yin Y, Shang P J. Weighted multiscale permutation entropyof financial time series[J]. Nonlinear Dynamics, 2017, 78(4): 2921-2939. [9] 张龙, 彭小明, 熊国良, 等. 基于MSE与PSO-SVM的机车轮对轴承智能诊断方法[J]. 铁道科学与工程学报,2021(9):2408-2417. [10] 王振亚, 姚立纲, 蔡永武, 等. 基于熵-流特征和樽海鞘群优化支持向量机的故障诊断方法[J]. 振动与冲击, 2021, 40(6): 107-114. doi: 10.13465/j.cnki.jvs.2021.06.014 [11] 陆凤君. 轴承故障的排列熵特征提取与GK模糊识别方法[J]. 组合机床与自动化加工技术, 2020(5): 95-98,102. doi: 10.13462/j.cnki.mmtamt.2020.05.023 [12] 马小平, 李博华, 蔡蔓利, 等. 基于谱熵梅尔积和改进VMD的轴承故障预警[J]. 北京理工大学学报, 2021, 41(11): 1179-1187. [13] 丁嘉鑫, 王振亚, 姚立纲, 等. 广义复合多尺度加权排列熵与参数优化支持向量机的调心球轴承故障诊断[J]. 中国机械工程, 2021, 32(2): 147-155. doi: 10.3969/j.issn.1004-132X.2021.02.004 [14] 刘武强, 申金星, 杨小强. 基于精细复合多元多尺度加权排列熵与流形学习的调心球轴承故障诊断[J]. 轴承, 2021(9): 54-60.