Remaining useful life prediction of rotating machinery based on KPCA-LSTM
CAO Xiangang1,2，YE Yu1,2，ZHAO Youjun1，DUAN Yong1,2，YANG Xin1,2
1.College of Mechanical Engineering, Xi’an University of Science and Technology, Xi’an 710054, China;
2.Shaanxi Key Laboratory of Mine Electromechanical Equipment Intelligent Monitoring, Xi’an 710054, China
摘要旋转机械的剩余使用寿命预测(Remaining Useful Life, RUL)对工业设备预测和健康管理的具有重要意义。本文针对多传感器冗余数据导致旋转机械退化信息提取困难、剩余使用寿命预测效果差的问题，提出了一种基于核主成分分析-长短期记忆网络(Kernel Principal Component Analysis-Long Short Term Memory ,KPCA-LSTM)的方法对旋转机械剩余使用寿命预测。首先，分析旋转机械的多维退化数据，选择可以表征旋转机械退化的数据；其次，对退化数据进行核主成分分析 (kernel principal components analysis, KPCA)融合及特征提取，将降维融合的特征作为预测模型的输入；然后构建旋转机械的健康指标，并通过多阶微分划分旋转机械的不同健康状态，建立KPCA-LSTM模型对旋转机械的剩余使用寿命进行预测；最后，通过实验室搭建的矿用减速器平台上进行了实验验证。实验结果表明：本文所提方法与LSTM、粒子群优化LSTM的方法比较，该方法预测效果优于其他两种模型，并降低模型训练的复杂性，减少预测用时。
Abstract：The prediction of the Remaining Useful Life (RUL) of rotating machinery is of great significance to the prediction and health management of industrial equipment. This paper addresses the problems of harrowing extraction of degradation information and poor prediction of the RUL of rotating machinery due to redundant data from multiple sensors. This paper proposes a Kernel Principal Component Analysis-Long Short Term Memory (KPCA-LSTM)based method for predicting the RUL of rotating machines. Firstly, the multi-dimensional degradation data of rotating machinery is analyzed, and the data that can characterize the degradation of rotating machinery is selected. Secondly, KPCA fusion and feature extraction were carried out on the degraded data, and the features of dimensionality reduction fusion were used as the input of the prediction model. Then, the health indicators of rotating machinery were constructed, and KPCA-LSTM model was established to predict the remaining useful life of rotating machinery by dividing the different health states of rotating machinery by multi-order differentiation. Finally, the proposed method is also tested by the mine reducer platform organized by our laboratory. Experimental results show that compared with LSTM and particle swarm optimization LSTM, the proposed method has a better prediction effect than the other two models, and reduces the complexity of model training and the time of prediction.
曹现刚1，2，叶煜1，2，赵友军1，段雍1，2，杨鑫1，2. 基于KPCA-LSTM的旋转机械剩余使用寿命预测[J]. 振动与冲击, 2023, 42(24): 81-91.
CAO Xiangang1,2，YE Yu1,2，ZHAO Youjun1，DUAN Yong1,2，YANG Xin1,2. Remaining useful life prediction of rotating machinery based on KPCA-LSTM. JOURNAL OF VIBRATION AND SHOCK, 2023, 42(24): 81-91.
[1] 石慧,康辉,任谦力等.随机相关性影响的多部件系统剩余寿命预测[J].振动与冲击,2022,41(21):299-307+324.
Shi Hui, Kang Hui, Ren Qianli, et al. Prediction of Residual Life of Multi-Component System Influenced by Random Correlation [J]. Journal of Vibration and Shock, 2022, 41(21): 299-307+324.
[2] 葛阳,郭兰中,牛曙光,窦岩. 基于t-SNE和LSTM的旋转机械剩余寿命预测 [J].振动与冲击,2020,39(07):223-231.
Ge Yang, Guo Lanzhong, Niu Shuguang, Dou Yan. Prediction of Residual Life of Rotating Machinery Based on t-SNE and LSTM [J]. Journal of Vibration and Shock,20,39(07):223-231.
[3] YAO D C,LI B Y,LIU H C,et al.Remaining useful life prediction of roller bearings based on improved 1D-CNN and simple recurrent unit [J]. Measurement, 2021, 175: 109169.
[4] Yan H , Liu K , Zhang X ,et al. Multiple Sensor Data Fusion for Degradation Modeling and Prognostics Under Multiple Operational Conditions [J]. IEEE Trans. Reliability, 2016, 65(3) : 1416-1426.
[5] X. Fang, K. Paynabar, N. Gebraeel. Multistream sensor fusion-based prognostics model for systems with single failure modes [J]. Reliability Engineering & System Safety. 2017; 159: 322-331.
[6] 李乃鹏,蔡潇,雷亚国,徐鹏程,王文廷,王彪.一种融合多传感器数据的数模联动机械剩余寿命预测方法 [J].机械工程学报,2021,57(20):29-37.
Li Naipeng, CAI Xiao, Lei Yaguo, Xu Pengcheng, Wang Wenting, Wang Biao. A Method for Predicting Residual Life of Digital-Analog Linkage Machinery Based on Multi-Sensor Data [J].Chinese Journal of Mechanical Engineering,2021, 57(20):29-37.
[7] Tse PW, Wang D. Enhancing the abilities in assessing slurry pumps' performance degradation and estimating their remaining useful lives by using captured vibration signals [J]. Journal of Vibration and Control,2017,23:1925-37.
[8] Cao Y , Jia M , Ding P ,et al.Transfer learning for remaining useful life prediction of multi-conditions bearings based on bidirectional-GRU [J].Measurement,2021,178:109287.
[9] Chen J, Jin H, Chang Y, Liu Q. Gated recurrent unit-based recurrent neural network for remaining useful life prediction of the nonlinear deterioration process.Reliability Engineering & System Safety [J].2019:185:372-82.
[10] Yaping Wang,Jiajun Zhao,Chaonan Yang,et al. Remaining useful life prediction of rolling bearings based on Pearson correlation-KPCA multi-feature fusion [J]. Measurement, 2022, 201:111572.
[11] Liu Lilan,Wan Xiang,Li Jiaying,et al. An Improved Entropy-Weighted Topsis Method for Decision-Level Fusion Evaluation System of Multi-Source Data [J]. Sensors, 2022, 22(17) : 6391-6391.
[12] 裴洪,胡昌华,司小胜,张建勋,庞哲楠,张鹏.基于机器学习的设备剩余寿命预测方法综述[J].机械工程学报,2019,55(08):1-13.
Pei Hong, Hu Chang-hua, SI Xiao-sheng, ZHANG Jian-xun, PANG Zhen-nan, ZHANG Peng. Review of Equipment Remaining Life Prediction Methods Based on Machine Learning [J].Journal of Mechanical Engineering,2019, 55(08):1-13.
[13] Ramezani S, Moini A, Riahi M, et al. A model to determine the remaining useful life of rotating equipment, based on a new approach to determining the state of degradation [J].Journal of Central South University,2020. 27: 2291–2310.
[14] Zeng, Yuhang Song, Guiqiu. An online transfer learning-based remaining useful life prediction method of ball bearings [J]. Measurement, 2021, 176(1):109201.
[15] 赵志宏,李晴,杨绍普等.基于BiLSTM与注意力机制的剩余使用寿命预测研究 [J].振动与冲击,2022,41(06):44-50+196.
Zhao Zhihong, Li Qing, Yang Shaopu,et al. Prediction of Residual Service Life Based on BiLSTM and Attention Mechanism [J]. Journal of Vibration and Shock,202, 41(06):44-50+196.
[16] 李卓漫,王海瑞.基于PSO优化LSTM的滚动轴承剩余寿命预测 [J].化工自动化及仪表,2021,48(04):353-357.
Li Zhuoman, Wang Hairui. Predicting the remaining service life of rolling bearings based on PSO-LSTM network model [J]. Automation & Instrumentation in Chemical Industry,2021,48(04):353-357.
[17] J. Guo, Z. Si, J. Xiang, A compound fault diagnosis method of rolling bearing based on wavelet scattering transform and improved soft threshold denoising algorithm [J].Measurement 2022,196:111276.
[18] YuYang,ShangQiang,XieTian.A hybrid model for short-term traffic flow prediction based on variational mode decomposition,wavelet threshold denoising, and long short- term memory neural network [J].Complexity,2021, 7756299.
[19] 张恒,赵荣珍.故障特征选择与特征信息融合的加权KPCA方法研究 [J].振动与冲击,2014,33(09):89-93+121.
Zhang Heng, Zhao Rongzhen. Research on Weighted KPCA Method of Fault Feature Selection and Feature Information Fusion [J]. Journal of Vibration and Shock,2014,33(09): 89-93+121.
[20] Li Zhenbao,Jiang Wanlu,Zhang Sheng,et al. Research on Prediction Method of Hydraulic Pump Remaining Useful Life Based on KPCA and JITL [J]. Applied Sciences, 2021, 11(20) : 9389-9389.
[21] A. Abid, M.T. Khan, M.S. Khan.Multidomain features-based GA optimized artificial immune system for bearing fault detection [J].IEEE Transactions on Systems Man Cybernetics- Systems,2020,50 (1) :348-359.
[22] Shen-Junxian, Xu-Feiyun. Method of fault feature selection and fusion based on poll mode and optimized weighted KPCA for bearings [J]. Measurement, 2022, 194:110950.
[23] 蒋全胜,许伟洋,朱俊俊等.基于动态加权卷积长短时记忆网络的滚动轴承剩余寿命预测方法 [J].振动与冲击, 2022, 41(17):282-291.
Jiang Quansheng, Xu Weiyang, Zhu Junjun,et al. Residual Life Prediction Method of Rolling Bearing Based on Dynamic Weighted Convolution Long and Short Time Memory Network [J]. Journal of Vibration and Shock,202,41(17): 282-291.
[24] Ahmed Elsheikh,Soumaya Yacout,Mohamed-Salah Ouali,et al. Bidirectional Handshaking LSTM for Remaining Useful Life Prediction [J]. Neurocomputing, 2018, 323: 148-156.
[25] 许艳雷,邱明,李军星等.基于SKF-KF-Bayes的滚动轴承剩余使用寿命预测方法 [J].振动与冲击,2021, 40(19): 26-31+40.
Xu Yanlei, Qiu Ming, Li Junxing et al. Prediction Method of Residual Service Life of Rolling Bearing Based on SKF-KF-Bayes [J]. Journal of Vibration and Shock, 2021, 40(19):26-31+40.
[26] Wang F , Liu X , Deng G ,et al.Remaining Life Prediction Method for Rolling Bearing Based on the Long Short-Term Memory Network [J]. Neural Processing Letters, 2019, 50(2): 2437-2454.
[27] Gundu V , Simon S P .PSO–LSTM for short term forecast of heterogeneous time series electricity price signals [J].Journal of Ambient Intelligence and Humanized Computing, 2021, 12(2):2375-2385.
[28] Li Y , Huang X , Ding P ,et al.Wiener-based remaining useful life prediction of rolling bearings using improved Kalman filtering and adaptive modification [J].Measurement, 2021, 182:109706.
[29] Bi J X , Fan W Z , Wang S B .Remaining Life Prediction for Aircraft Turbine Engines Based on LSTM-RNN-HMM- APPROACH [J].IOP Conference Series: Materials Science and Engineering, 2021, 1043(2):022033.
[30] Chen Z,Wu M,Zhao R,et al. Machine Remaining Useful Life Prediction via an Attention Based Deep Learning Approach [J]. IEEE Transactions on Industrial Electronics, 2020, PP(99):1-1.
