|
|
Prediction of remaining useful life based on t-SNE and LSTM for rotating machinery |
GE Yang1,2, GUO Lanzhong1,2, NIU Shuguang1,2, DOU Yan1,2 |
1. School of Mechanical Engineering, Changshu Institute of Technology, Changshu 215500, China;
2. Jiangsu elevator intelligent safety key construction laboratory, Changshu 215500, China |
|
|
Abstract Aiming at the problem of remaining useful life prediction of rotating machinery, a prediction method based on t-Distributed Stochastic Neighbor embedding (t-SNE) and Long Short-Term Memory network (LSTM) was proposed. First of all, the t-SNE dimensionality reduction method was introduced into the feature extraction of rotating machinery vibration signals, and the example verifies that no matter for the time-frequency domain features or energy features obtained by wavelet packet decomposition, the feature differentiation is more obvious after t-SNE dimensionality reduction, and the correct rate of fault mode recognition using the dimensionality reduction features is close to 100%. Secondly, it was proposed to use the divergence between samples as the degradation index of rotating machinery. the experimental results show that the divergence between samples has a more obvious performance on the performance degradation trend of rotating machinery than other indexes. Finally, the LSTM method was used to predict the remaining useful life with different training sample sizes. In order to verify the effectiveness of the LSTM method, it was compared with the BP neural network, grey prediction model, support vector machine and other methods. The results show that the LSTM method can predict the degradation trend of rotating machinery and significantly improve the prediction accuracy of the remaining useful life. It has a certain theoretical guiding significance for the health monitoring and life prediction of rotating machinery.
|
Received: 22 November 2018
Published: 28 March 2020
|
|
|
|
[1]ROBERTO R, MATTEO B, QUENTIN H, et al. On-line Bayesian model updating for structural health monitoring [J]. Mechanical Systems and Signal Processing, 2018, 103: 174-195.
[2]WALTER G, FLAPPER S D. Condition-based maintenance for complex systems based on current component status and Bayesian updating of component reliability [J]. Reliability Engineering and System Safety, 2017, 168: 227-239.
[3]SHIN J H, JUN H B. On condition based maintenance policy [J]. Journal of Computational Design and Engineering,2015, 2(2): 119-127.
[4]KAN M S, TAN A C C, MATHEW J. A review on prognostic techniques for non-stationary and non-linear rotating systems [J]. Mechanical Systems and Signal Processing, 2015, 62/63:1-20.
[5]ZHANG J L, SHANG D G, SUN Y J, et al. Multiaxial high-cycle fatigue life prediction model based on the critical plane approach considering mean stress effects [J]. International Journal of Damage Mechanics, 2018, 27(1): 32-46.
[6]HU J Q, ZHANG L B, MA L, et al. An integrated safety prognosis model for complex system based on dynamic Bayesian network and ant colony algorithm [J]. Expert Systems with Applications, 2011,38(3): 1431-1446.
[7]YANG L, LEE J. Bayesian belief network-based approach for diagnostics and prognostics of semiconductor manufacturing system [J]. Robotics and Computer Integrated Manufacturing, 2012, 28(1): 66-74.
[8]ZHAO Zeqi, LIANG Bin, WANG Xueqian, et al. Remaining useful life prediction of aircraft engine based on degradation pattern learning [J]. Reliability Engineering and System Safety, 2017, 164: 74-83.
[9]DJEZIRI M A, BENMOUSSA S, SANCHEZ R. Hybrid method for remaining useful life prediction in wind turbine systems [J]. Renewable Energy, 2017, 116: 173-187.
[10]SIKORSKA J Z, HODKIEWICZ M, MA L. Prognostic modelling options for remaining useful life estimation by industry [J]. Mechanical Systems and Signal Processing, 2011,25(5): 1803-1836.
[11]SI X S, WANG W, HU C H, et al. Remaining useful life estimation-a review on the statistical data driven approaches [J]. European Journal of Operational Research, 2011, 213(1): 1-14.
[12]GE Yang, JIANG Xiaomei. Mathematical morphology and deep learning-based approach for bearing fault recognition [J]. International Journal of Performability Engineering, 2018,14(5): 995-1003.
[13]LIAO L. Discovering prognostic features using genetic programming in remaining useful life prediction [J]. IEEE Transactions on Industrial Electronics, 2014, 61: 2464-472.
[14]YU J. A hybrid feature selection scheme and self-organizing map model for machine health assessment [J]. Applied Soft Computing, 2011, 11: 4041-4054.
[15]LIU F, LIU Y B, CHEN F L, et al. Residual life prediction for ball bearings based on joint approximate diagonalization of eigen matrices and extreme learning machine [J]. Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, 2015, 231(9): 1699-1711.
[16]欧璐,于德介. 基于监督拉普拉斯分值和主元分析的滚动轴承故障诊断[J].机械工程学报,2014, 50(5): 88-94.
OU Lu, YU Dejie. Rolling bearing fault diagnosis based on supervised laplaian score and principal component analysis [J]. Journal of Mechanical Engineering, 2014, 50(5): 88-94.
[17]PARK W J, LEE S H, JOO W K, et al. A mixed algorithm of PCA and LDA for fault diagnosis of induction motor [J]. Advanced Intelligent Computing Theories and Applications 2007,4682: 934-942.
[18]BELLAS A, BOUVEYRON C, COTTRELL M, et al. Model-based clustering of high-dimensional data streams with online mixture of probabilistic PCA [J]. Advances in Data Analysis and Classification, 2013, 7(3): 281-300.
[19]LIU Y B, HE B, LIU F, et al. Feature fusion using kernel joint approximate diagonalization of eigen-matrices for rolling bearing fault identification [J]. Journal of Sound and Vibration, 2016, 385:389-401.
[20]CAESARENDRA W, WIDODO A, YANG B. Combination of probability approach and support vector machine towards machine health prognostics [J]. Probabilistic Engineering Mechanics, 2011, 26: 165-173.
[21]SUN C, ZHANG Z, HE Z. Research on bearing life prediction based on support vector machine and its application [J]. Journal of Physics: Conference Series, 2011,305: 012028.
[22]FU A, WANG X Z, HE Y L, et al. A study on residence error of training an extreme learning machine and its application to evolutionary algorithms [J]. Neurocomputing, 2014, 146: 75-82.
[23]QIAN Yuning, YAN Ruqiang. Remaining useful life prediction of rolling bearings using an enhanced particle filter [J]. IEEE Transactions on Instrumentation and Measurement, 2015, 64(10): 2696-2707.
[24]REN Lei, CUI Jin, SUN Yaqiang, et al. Multi-bearing remaining useful life collaborative prediction: A deep learning approach [J]. Journal of Manufacturing Systems, 2017, 43: 248-256.
[25]LAURENS V D M, HINTON G, HINTON V D M G. Visualizing Data using t-SNE [J]. Journal of Machine Learning Research, 2008, 9: 2579-2605.
[26]徐森, 花小朋, 徐静, 等. 一种基于T-分布随机近邻嵌入的聚类集成方法[J]. 电子与信息学报, 2018, 40(6): 1316-1322.
XU Sen, HUA Xiaopeng, XU Jing, et al. Cluster ensemble approach based on t-distributed stochastic neighbor embedding [J]. Journal of Electronics & Information Technology, 2018, 40(6): 1316-1322.
[27]朱冰, 蒋渊德, 邓伟文, 杨顺, 何睿, 苏琛. 基于 KL 散度的驾驶员驾驶习性非监督聚类[J]. 汽车工程, 2018, 40 (1):1317-1323.
Zhu Bing, Jiang Yuande, Deng Weiwen, Yang Shun, He Rui, Su Chen, Unsupervised Clustering of Driving Styles Based on KL Divergence [J]. Automotive Engineering, 2018, 40 (1):1317-1323.
[28]贾正荣, 王航宇, 卢发兴. 基于梯度下降法的离散概率空间区域射击瞄准点求解方法[J]. 兵工学报, 2018, 39 (12): 2470-2479.
Jia Zhengrong, Wang Hangyu, Lu Faxing. Gradient Descent-based Aiming Point Solving Method for Area Firing in Discrete Probability Space [J]. ACTA ARMAMENTARII, 2018, 39 (12): 2470-2479.
[29]喻以明, 陈才扣. 局部嵌入投影及其在人脸识别中的应用[J]. 计算机工程, 2011, 37 (2): 175-177.
Yu Yiming, Chen Caikou. Locality Embedding Projection and Its Application to Face Recognition [J]. Computer Engineering, 2011, 37 (2): 175-177.
[30]芦效峰, 张胜飞, 伊胜伟. 基于CNN和RNN的自由文本击键模式持续身份认证[J]. 清华大学学报(自然科学版), 2018, 58 (12): 1072-1078.
Lu Xiaofeng, Zhang Shengfei, Yi Shengwei, Free-text keystroke continuous authentication suing CNN and RNN [J]. J Tsinghua Univ (Sci& Technol), 2018, 58 (12): 1072-1078.
[31]PASCANU R,MIKOLOV T,BENGIO Y. On the difficulty of training recurrent neural networks[C]// Proceedings of the 30th International Conference on Machine Learning (ICML-13). 2013: 1310-1318.
[32]HOCHREITER S,SCHMIDHUBER J. Long short-term memory[J].Neural computation,1997,9(8) : 1735-1780.
[33]王立, 张谧. 基于LSTM的POI个性化推荐框架[J]. 计算机系应用, 2018, 27 (12): 56-61.
Wang Li, Zhang Mi. LSTM-Based Neural Network Framework for Next POI Recommendation [J]. Computer Systems & Applications, 2018, 27 (12): 56-61.
[34]Liu Yongbin, He Bing, Liu Fang, et al. Feature fusion using kernel joint approximate diagonalization of eigen-matrices for rolling bearing fault identification [J]. Journal of Sound and Vibration, 2016, 385: 389-401.
|
|
|
|