|
|
|
| Bearing life prediction method based on phase space reconstruction of state tracking features |
| BO Lin,YAN Kang,LIU Xiaofeng |
| State Key Laboratory of Mechanical Transmission, Chongqing University, Chongqing 400044, China |
|
|
|
Abstract Aiming at feature selection and model optimization problems in residual life prediction of rolling bearing, a bearing life prediction method based on phase space reconstruction of state tracking feature was proposed.Based on monotonicity and sensitivity assessment of bearing features, quantitative evaluation was done for tracking capability of bearing running state to screen the optimal feature set of bearing performance degradation.In order to uniformly describe each feature’s representation information for bearing degradation state, the adaptive chaos particle swarm optimization (ACPSO) algorithm was used to optimize support vector data description (SVDD), and construct the bearing health index.This index was used to accurately divide bearing operation states.Finally, based on the phase space reconstruction index of bearing recession, ACPSO-GRNN was used to predict bearing residual life.Test results showed that the proposed method can be used not only to find the decline time point of bearing operation as soon as possible, but also have higher prediction accuracy than those of SVR and BP neural networks.
|
|
Received: 11 October 2017
Published: 28 November 2019
|
|
|
|
[1] Ali J B, Fnaiech N, Saidi L, et al. Application of empirical mode decomposition and artificial neural network for automatic bearing fault diagnosis based on vibration signals [J]. Applied Acoustics, 2015, 89(3):16-27.
[2] Chen C, Vachtsevanos G, Orchard M E. Machine remaining useful life prediction: An integrated adaptive neuro-fuzzy and high-order particle filtering approach[J]. Mechanical Systems & Signal Processing, 2012, 28(9):597-607.
[3] Loutas T H, Roulias D, Georgoulas G. Remaining Useful Life Estimation in Rolling Bearings Utilizing Data-Driven Probabilistic E-Support Vectors Regression[J]. IEEE Transactions on Reliability, 2013, 62(4):821-832.
[4] Zhang Q, Tse W T, Wan X, et al. Remaining useful life estimation for mechanical systems based on similarity of phase space trajectory[J]. Expert Systems with Applications An International Journal, 2015, 42(5):2353-2360.
[5] Liu Y, He B, Liu F, et al. Remaining Useful Life Prediction of Rolling Bearings Using PSR, JADE, and Extreme Learning Machine[J]. Mathematical Problems in Engineering, 2016, 2016:1-13.
[6] 肖婷,汤宝平,秦毅,等. 基于流形学习和最小二乘支持向量机的滚动轴承退化趋势预测[J].振动与冲击, 2015, 34 (09): 149-153.
Xiao Ting, Tang Bao-ping, Qin Yi, et al. Degradation trend prediction of rolling bearing based on manifold learning and least squares support vector machine[J]. Journal of Vibration and Shock, 2015,34(09):149-153.
[7] Dong S, Sheng J, Tang B, et al. Bearings in simulated space conditions running state detection based on Tsallis entropy-KPCA and optimized fuzzy c-means model[J]. Noise Control Engineering Journal, 2017, 65(2): 62-70.
[8] 申中杰，陈雪峰，何正嘉，等.基于相对特征和多变量支持向量机的滚动轴承剩余寿命预测[J].机械工程学报，2013,49(2):183-189.
Shen Zhong-jie, Chen Xue-feng, He Zheng-jia, et al. Residual life prediction of rolling bearing based on relative feature and multivariable support vector machine[J]. Journal of Mechanical Engineering,2013,49(2):183-189.
[9] Ali J B, Chebel-Morello B, Saidi L, et al. Accurate bearing remaining useful life prediction based on Weibull distribution and artificial neural network[J]. Mechanical Systems & Signal Processing, 2015, s 56–57:150-172.
[10] 何群,李磊,江国乾,等.基于PCA和多变量极限学习机
的轴承剩余寿命预测[J].中国机械工程,2014,25（07）：984-989.
He Qun, Li Lei, Jiang Guo-qian, et al. Prediction of bearing residual life based on PCA and Multivariate extreme learning machine[J]. China Mechanical Engineering,2014,25(07):984-
989.
[11] Zhao M, Tang B, Tan Q. Bearing remaining useful life estimation based on time–frequency representation and supervised dimensionality reduction. Measurement 2016,86：41–55.
[12] Zhou Q, Yan P, Xin Y. Research on a knowledge modelling methodology for fault diagnosis of machine tools based on formal semantics[M]. Elsevier Science Publishers B. V. 2017.
[13] 谭晓栋. 面向装备健康状态评估的可测性设计关键技术研究[D].国防科学技术大学,2013.
Tan Xiao-dong. Research on Key Technologies of Design for Testability for Health State Evaluation [D]. National University of Defense Technology,2013.
[14] Zhu X, Zhang Y, Zhu Y. Bearing performance degradation assessment based on the rough support vector data description[J]. Mechanical Systems & Signal Processing, 2013, 34(1–2):203-217.
[15] Tax D M J, Duin R P W. Support Vector Data Description[J]. Machine Learning, 2004, 54(1):45-66.
[16] Kiranyaz S, Ince T, Gabbouj M. Multidimensional Particle Swarm Optimization for Machine Learning and Pattern Recognition[J]. Adaptation Learning & Optimization, 2015, 22(10):1448–1462.
[17] 赵志刚,常成.自适应混沌粒子群优化算法[J].计算机工程，2011,37(15):128-130.
Zhao Zhi-gang, Chang Cheng. Adaptive chaotic particle swarm optimization algorithm[J]. Computer Engineering,2011,37(15):
128-130.
[18] 柏林,陆超,赵鑫.基于相空间重构和ICA-R的轴承故障特征增强方法[J].振动、测试与诊断,2016,36(06): 1097-1102.
Bo Lin, Lu Chao, Zhao Xin. A method of enhancing the fault characteristics in early stage of rolling bearing based on phase-space reconstruction and ICA with reference[J]. Journal of Vibration, Measurement & Diagnosis,2016,36(06): 1097-1102.
[19] 王涛,李艾华,高运广,等.基于相空间重构和遗传优化SVR的机械设备状态趋势预测[J].噪声与振动控制,2014,34(03):176-181.
Wang Tao, Li Ai-hua, Gao Yun-guang, et al. Prediction of mechanical equipment state trend based on phase space reconstruction and genetic optimization SVR[J]. Noise and vibration control, 2014,34(03):176-181.
[20] 伊良忠,章超,裴峥.广义回归神经网络的改进及在交通预测中的应用[J].山东大学学报(工学版),2013,43(01):9-14.
Yi Liang-zhong, Zhang Chao, Pei Zheng. The improvement of generalized regression neural network and its application in traffic forecasting[J]. Journal of Shandong University (Engineering Science),2013,43(01):9-14.
[21] N. Patrick, G. Rafael, et al. PRONOSTIA: An experimental platform for bearings accelerated life test [C]. In Proceedings of IEEE International Conference on Prognostics and Health Management, 2012,1-8.
|
|
|
|
