Residual life prediction of aeroengine based on multi-scale permutation entropy and LSTM neural network
-
摘要: 针对航空发动机性能退化失效的变点和多状态参数的时间序列预测, 构建了基于多尺度排列熵算法和长短时记忆神经网络的剩余寿命预测模型; 使用多尺度排列熵算法对时间序列进行变点分析, 求解出性能退化过程中的突变点, 得到了有故障征兆的性能退化起始点; 构建了包含多变量的长短时记忆神经网络模型, 将多个状态参数代入到模型中得到对应的剩余寿命; 将变点后的航空发动机多状态参数和剩余寿命作为样本, 代入到长短时记忆神经网络模型中进行多步和多变量的时间序列预测; 通过综合航空发动机状态参数变点分析方法和时间序列预测模型, 得到最终的剩余寿命预测结果。研究结果表明: 多尺度排列熵算法能够及时监控各个状态参数的变化, 当发现状态参数异常时, 排列熵的值会发生跳变, 从而有助于及时发现故障征兆; 长短时记忆神经网络模型通过门控单元对长时间序列数据进行信息筛选, 充分保留了有效信息用于时间序列预测; 多变量长短时记忆神经网络能够对多状态参数进行同步分析, 并且将状态参数直接与剩余寿命相对应, 提高了模型效率; 通过多尺度排列熵算法和长短时记忆神经网络模型的结合, 能够考虑到航空发动机的多退化模式, 得到更符合实际退化过程的剩余寿命预测结果; 经过算例分析, 提出方法的剩余寿命预测的均方根误差为5.3, 与长短时记忆神经网络、反向传播神经网络和支持向量机相比, 误差分别降低了63%、72%和78%。Abstract: Aiming at the change point of aeroengine performance degradation failure and the time series prediction of multi-state parameters, the residual life prediction model based on the multi-scale permutation entropy(MPE) algorithm and long-short term memory(LSTM) neural network was constructed. The change points in time series were analyzed by the MPE algorithm, and the mutation points in the process of performance degradation were solved. The starting point of performance degradation with fault symptoms was obtained. The LSTM neural network model with multi-variables was constructed, and the corresponding residual life was obtained by introducing the multi-state parameter data into the model.The aeroengine multi-state parameters and residual life after the change point were taken as samples and substituted into the LSTM neural network model, the multi-step and multi-variable time series prediction was carried out.The final residual life prediction results were obtained by integrating the state parameter change point analysis method and time series prediction model of aeroengine. Research result shows that the MPE algorithm can monitor the changes of state parameters in time. When abnormal state parameters are found, the value of permutation entropy will jump, which is helpful to discover the fault symptoms in time. The LSTM neural network model selects the information of long time series data through the gated units, and the effective information can be fully reserved for the time series prediction. The multi-variable LSTM neural network can synchronously analyze the multi-state parameters, and directly correspond to the residual life, which improves the efficiency of the model. The combination of MPE algorithm and LSTM neural network model can take the multiple degradation modes of aeroengine into account, and the residual life prediction results of aeroengine are more in line with the actual degradation process. After an example analysis, the root mean square error of the proposed residual life prediction method is 5.3, which is 63%, 72% and 78% lower than that of LSTM neural network, back-propagation neural network and support vector machine, respectively.
-
图 5 基于LSTM和MPE的航空发动机剩余寿命预测
Figure 5. Residual life prediction of aeroengine based on LSTM and MPE
图 10 剩余寿命预测训练误差与测试误差
Figure 10. Training error and testing error of residual life prediction
表 1 航空发动机状态参数C-MAPSS仿真
Table 1. C-MAPSS simulation of aeroengine state parameters
状态参数 含义 P1 风扇入口总温度 P2 低压压缩机进气道总温度 P3 高压压缩机进气道总温度 P4 低压涡轮进气道总温度 P5 风机入口压力 P6 旁通管总压力 P7 高压压缩机出口处总压力 P8 物理风机转速 P9 物理核心速度 P10 发动机压力比 P11 高压压缩机出口静压 P12 燃料流量比率 P13 修正风机转速 P14 修正核心转速 P15 涵道比 P16 燃烧器的燃料-空气比 P17 放气热含量 P18 风扇转速要求 P19 修正风扇转速要求 P20 高压涡轮冷却剂释放速度 P21 低压涡轮冷却剂释放速度 
下载: 导出CSV
表 2 剩余寿命预测结果对比
Table 2. Comparison of residual life prediction results
方法 RMSE值 BP 23.6 LSTM 14.4 SVM 19.3 MPE-LSTM 5.3
下载: 导出CSV
-
[1] 马小骏, 任淑红, 左洪福, 等. 基于LS-SVM算法和性能可靠性的航空发动机在翼寿命预测方法[J]. 交通运输工程学报, 2015, 15(3): 92-100. doi: 10.3969/j.issn.1671-1637.2015.03.013MA Xiao-jun, REN Shu-hong, ZUO Hong-fu, et al. Prediction method of aero-engine life on wing based on LS-SVM algorithm and performance reliability[J]. Journal of Traffic and Transportation Engineering, 2015, 15(3): 92-100. (in Chinese). doi: 10.3969/j.issn.1671-1637.2015.03.013 [2] HUANG Ze-yi, XU Zheng-guo, KE Xiao-jie, et al. Remaining useful life prediction for an adaptive skew-Wiener process model[J]. Mechanical Systems and Signal Processing, 2017, 87: 294-306. doi: 10.1016/j.ymssp.2016.10.027 [3] HU Yao-gang, LI Hui, SHI Ping-ping, et al. A prediction method for the real-time remaining useful life of wind turbine bearings based on the Wiener process[J]. Renewable Energy, 2018, 127: 452-460. doi: 10.1016/j.renene.2018.04.033 [4] WANG Xing-jian, LIN Si-ru, WANG Shao-ping, et al. Remaining useful life prediction based on the Wiener process for an aviation axial piston pump[J]. Chinese Journal of Aeronautics, 2016, 29(3): 779-788. doi: 10.1016/j.cja.2015.12.020 [5] ZHANG Yu-jie, PENG Xi-yuan, PENG Yu, et al. Weighted bagging Gaussion process regression to predict remaining useful life of electro-mechanical actuator[C]∥IEEE. 2016 Prognostics and System Health Management Conference. New York: IEEE, 2016: 1-6. [6] AYE S A, HEYNS P S. An integrated Gaussian process regression for prediction of remaining useful life of slow speed bearings based on acoustic emission[J]. Mechanical Systems and Signal Processing, 2017, 84: 485-498. doi: 10.1016/j.ymssp.2016.07.039 [7] KUMAR A, CHINNAM R B, TSENG F. An HMM and polynomial regression based approach for remaining useful life and health state estimation of cutting tools[J]. Computers and Industrial Engineering, 2019, 128: 1008-1014. doi: 10.1016/j.cie.2018.05.017 [8] CHEN Zhen, LI Ya-ping, XIA Tang-bin, et al. Hidden Markov model with auto-correlated observations for remaining useful life prediction and optimal maintenance policy[J]. Reliability Engineering and System Safety, 2019, 184: 123-136. doi: 10.1016/j.ress.2017.09.002 [9] RAI A, UPADHYAY S H. The use of MD-CUMSUM and NARX neural network for anticipating the remaining useful life of bearings[J]. Measurement, 2017, 111: 397-410. doi: 10.1016/j.measurement.2017.07.030 [10] LIU Zhen, CHENG Yu-hua, WANG Pan, et al. A method for remaining useful life prediction of crystal oscillators using the Bayesian approach and extreme learning machine under uncertainty[J]. Neurocomputing, 2018, 305: 27-38. doi: 10.1016/j.neucom.2018.04.043 [11] 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 and Signal Processing, 2015, 56/57: 150-172. doi: 10.1016/j.ymssp.2014.10.014 [12] ZHAO Ze-qi, LIANG Bin, WANG Xue-qian, et al. Remaining useful life prediction of aircraft engine based on degradation pattern learning[J]. Reliability Engineering and System Safety, 2017, 164: 74-83. doi: 10.1016/j.ress.2017.02.007 [13] WU Jun, SU Yong-heng, CHENG Yi-wei, et al. Multi-sensor information fusion for remaining useful life prediction of machining tools by adaptive network based fuzzy inference system[J]. Applied Soft Computing, 2018, 68: 13-23. doi: 10.1016/j.asoc.2018.03.043 [14] REN Lei, SUN Ya-qiang, CUI Jin, et al. Bearing remaining useful life prediction based on deep autoencoder and deep neural networks[J]. Journal of Manufacturing Systems, 2018, 48: 71-77. doi: 10.1016/j.jmsy.2018.04.008 [15] GUO Liang, LI Nai-peng, JIA Feng, et al. A recurrent neural network based health indicator for remaining useful life prediction of bearings[J]. Neurocomputing, 2017, 240: 98-109. doi: 10.1016/j.neucom.2017.02.045 [16] ZHANG Jian-jing, WANG Peng, YAN Ru-qiang, et al. Long short-term memory for machine remaining life prediction[J]. Journal of Manufacturing Systems, 2018, 48: 78-86. doi: 10.1016/j.jmsy.2018.05.011 [17] WU Yi-ting, YUAN Mei, DONG Shao-peng, et al. Remaining useful life estimation of engineered systems using vanilla LSTM neural networks[J]. Neurocomputing, 2018, 275: 167-179. doi: 10.1016/j.neucom.2017.05.063 [18] WEN Yu-xin, WU Jian-guo, DAS D, et al. Degradation modeling and RUL prediction using Wiener process subject to multiple change points and unit heterogeneity[J]. Reliability Engineering and System Safety, 2018, 176: 113-124. doi: 10.1016/j.ress.2018.04.005 [19] SON J, ZHANG Yi-lu, SANKAVARAM C, et al. RUL prediction for individual units based on condition monitoring signals with a change point[J]. IEEE Transactions on Reliability, 2015, 64(1): 182-196. doi: 10.1109/TR.2014.2355531 [20] WANG Ping-ping, TANG Yin-cai, BAE S J, et al. Bayesian analysis of two-phase degradation data based on change-point Wiener process[J]. Reliability Engineering and System Safety, 2018, 170: 244-256. doi: 10.1016/j.ress.2017.09.027 [21] LIU Lian-sheng, WANG Shao-jun, LIU Da-tong, et al. Quantitative selection of sensor data based on improved permutation entropy for system remaining useful life prediction[J]. Microelectronics Reliability, 2017, 75: 264-270. doi: 10.1016/j.microrel.2017.03.008 [22] ZHANG Xiao-yuan, LIANG Yi-tao, ZHOU Jian-zhong, et al. A novel bearing fault diagnosis model integrated permutation entropy, ensemble empirical mode decomposition and optimized SVM[J]. Measurement, 2015, 69: 164-179. doi: 10.1016/j.measurement.2015.03.017 [23] LI Yong-bo, XU Min-qiang, WEI Yu, et al. A new rolling bearing fault diagnosis method based on multiscale permutation entropy and improved support vector machine based binary tree[J]. Measurement, 2016, 77: 80-94. doi: 10.1016/j.measurement.2015.08.034 [24] 姚德臣, 杨建伟, 程晓卿, 等. 基于多尺度本征模态排列熵SA-SVM的轴承故障诊断研究[J]. 机械工程学报, 2018, 54(9): 168-176. https://www.cnki.com.cn/Article/CJFDTOTAL-JXXB201809021.htmYAO De-chen, YANG Jian-wei, CHENG Xiao-qing, et al. Railway rolling bearing fault diagnosis based on multi-scale IMF permutation entropy and SA-SVM classifier[J]. Journal of Mechanical Engineering, 2018, 54(9): 168-176. (in Chinese). https://www.cnki.com.cn/Article/CJFDTOTAL-JXXB201809021.htm [25] AZAMI H, ESCUDERO J. Improved multiscale permutation entropy for biomedical signal analysis: interpretation and application to electroencephalogram recordings[J]. Biomedical Signal Processing and Control, 2016, 23: 28-41. doi: 10.1016/j.bspc.2015.08.004 [26] ZHANG Yong-zhi, XIONG Rui, HE Hong-wen, et al. Long short-term memory recurrent neural network for remaining useful life prediction of lithium-ion batteries[J]. IEEE Transactions on Vehicular Technology, 2018, 67(7): 5695-5705. doi: 10.1109/TVT.2018.2805189 [27] TAN J H, HAGIWARA Y, PANG W, et al. Application of stacked convolutional and long short-term memory network for accurate identification of CAD ECG signals[J]. Computers in Biology and Medicine, 2018, 94: 19-26. doi: 10.1016/j.compbiomed.2017.12.023 [28] YANG Jing, GUO Ying-qing, ZHAO Wan-li. Long short-term memory neural network based fault detection and isolation for electro-mechanical actuators[J]. Neurocomputing, 2019, 360: 85-96. [29] LEI Jin-hao, LIU Chao, JIANG Dong-xiang. Fault diagnosis of wind turbine based on long short-term memory networks[J]. Renewable Energy, 2019, 133: 422-432. [30] ZHANG Bin, ZHANG Shao-hui, LI Wei-hua. Bearing performance degradation assessment using long short-term memory recurrent network[J]. Computers in Industry, 2019, 106: 14-29. [31] SMITH W A, RANDALL R B. Rolling element bearing diagnostics using the Case Western Reserve University data: a benchmark study[J]. Mechanical Systems and Signal Processing, 2015, 64/65: 100-131. [32] BOUDIAF A, MOUSSAOUI A, DAHANE A, et al. A comparative study of various methods of bearing faults diagnosis using the Case Western Reserve University data[J]. Journal of Failure Analysis and Prevention, 2016, 16(2): 271-284. -
点击查看大图
图(12) / 表(2)
计量
- 文章访问数: 1021
- HTML全文浏览量: 162
- PDF下载量: 520
- 被引次数: 0
