基于LMD和逻辑回归的滚动轴承故障状态类型识别
Roller Bearing Fault Type Identification Based on LMD and Logistic Regression

作者: 王晶晶 * , 魏永合 , 冯睿智 , 魏 超 :沈阳理工大学,机械工程学院,辽宁 沈阳;

关键词: 局部均值分解(LMD)逻辑回归滚动轴承遗传算法(GA)故障状态识别Local Mean Decomposition (LMD) Logistic Regression Roller Bearing CA Fault Type Identification

摘要:
针对滚动轴承的故障振动信号的非线性非平稳性,提出了一种基于局部均值分解(Local Mean Decomposition, LMD)方法和逻辑回归(LR)的滚动轴承故障诊断方法。该方法将采集到的滚动轴承内圈、外圈振动信号进行LMD方法处理后,采用遗传算法(GA)和逻辑回归结合进行模型中的参数选择,通过逻辑回归进行训练和测试,结果表明该方法可以有效地对滚动轴承故障类型进行识别。

Abstract: Aiming at the nonlinear and non-stationary vibration signal of the rolling bearing, a method based on local mean decomposition (Local Mean Decomposition, LMD) and logistic regression is proposed. This method processed collected vibration signals of rolling bearing inner ring and outer ring by LMD method, then selected the parameter of the model by genetic algorithm (GA) combined with logistic regression, and finally trained and tested the parameter by logistic regression. The result shows that the method can be effectively applied in roller bearing fault type identification.Aiming at the nonlinear and non-stationary vibration signal of the rolling bearing, a method based on local mean decomposition (Local Mean Decomposition, LMD) and logistic regression is proposed. This method processed collected vibration signals of rolling bearing inner ring and outer ring by LMD method, then selected the parameter of the model by genetic algorithm (GA) combined with logistic regression, and finally trained and tested the parameter by logistic regression. The result shows that the method can be effectively applied in roller bearing fault type identification.

Abstract:

文章引用: 王晶晶 , 魏永合 , 冯睿智 , 魏 超 (2016) 基于LMD和逻辑回归的滚动轴承故障状态类型识别。 机械工程与技术, 5, 174-181. doi: 10.12677/MET.2016.52021

参考文献

[1] 钟鑫, 刘文彬, 杨剑锋. 基于逻辑回归的滚动轴承性能退化评估[J]. 科技信息, 2010(16): 504-505.

[2] 钟先友. 旋转机械故障诊断的时频分析方法及其应用研究[D]: [博士学位论文]. 武汉: 武汉科技大学, 2014.

[3] 陈果, 邓堰. 遗传算法特征选取中的几种适应度函数构造新方法及其应用[J]. 机械科学与技术, 2011, 30(1): 124-132.

[4] 史美丽. 基于LMD的滚动轴承故障诊断研究[D]: [硕士学位论文]. 长沙: 湖南大学, 2011.

[5] Ma, J., Wu, J.D., Fan, Y.G., Wang, X.D. and Yan, X.G. (2015) The Rolling Bearing Fault Feature Extraction Based on the LMD and Envelope Demodulation. Mathematical Problems in Engineering, 2015, Article ID: 429185.
http://dx.doi.org/10.1155/2015/429185

[6] 张亢. 局部均值分解方法及其在旋转机械故障诊断中的应用研究[D]: [博士学位论文]. 长沙: 湖南大学, 2012.

[7] Pandya, D.H., Upadhyay, S.H. and Harsha, S.P. (2014) Fault Diagnosis of Rolling Element Bearing by Using Multinomial Logistic Regression and Wavelet Packet Transform. Soft Computing, 18, 255-265.
http://dx.doi.org/10.1007/s00500-013-1055-1

[8] 李峰峰. 基于Logistic回归模型的旋转机械状态健康评估研究[J]. 维修与管理, 2009(5): 20-23.

[9] 刘英. 遗传算法中适应度函数的研究[J]. 兰州工业高等专科学校学报, 2006, 13(3): 1-4.

[10] 周培毅, 张新燕, 张华中. 基于遗传算法与BP神经网的风力发电机齿轮箱故障诊断研究[J]. 华北电力技术, 2010(7): 6-11.

[11] 崔春英, 段礼祥, 张来斌. 基于LMD和FCM的滚动轴承故障诊断方法[J]. 科学技术与工程, 2013, 13(7): 1764-1767.

分享
Top