基于EMD-LSTM模型的APU排气温度预测

王晓燕; 白贤明; 宋辞; 毛子荐

doi:10.13224/j.cnki.jasp.20220076

基于EMD-LSTM模型的APU排气温度预测

doi: 10.13224/j.cnki.jasp.20220076

王晓燕^{1, 2},
白贤明^{2, 3},
宋辞^{1, 2},
毛子荐^{1, 2}

1.
沈阳航空航天大学经济与管理学院，沈阳 110136
2.
辽宁省飞机火爆防控及可靠性适航技术重点实验室，沈阳 110136
3.
沈阳航空航天大学安全工程学院，沈阳 110136

详细信息

作者简介:
王晓燕（1975-），女，副教授，博士，主要从事机械可靠性工程及精益管理方面的研究

中图分类号: V267
计量
- 文章访问数: 18
- HTML浏览量: 7
- PDF量: 0
- 被引次数: 0
出版历程
- 收稿日期: 2022-02-21
- 网络出版日期: 2024-03-20

APU exhaust temperature prediction based on EMD-LSTM model

WANG Xiaoyan^{1, 2},
BAI Xianming^{2, 3},
SONG Ci^{1, 2},
MAO Zijian^{1, 2}

1.
College of Economics and Management，Shenyang Aerospace University，Shenyang 110136，China
2.
Liaoning Provincial Key Laboratory of Aircraft Fire Prevention and Control and Reliability Airworthiness Technology，Shenyang 110136，China
3.
College of Safety Engineering，Shenyang Aerospace University，Shenyang 110136，China

摘要

摘要:
为了提高排气温度（EGT）的预测精度需要减少数据的复杂性。提出一种经验模态分解（EMD）和长短期记忆神经网络（LSTM）组合方法来预测EGT。将具有时间序列特征的EGT数据，利用EMD分解成含有相同特征的本征模态函数（IMF）和残差（RES）；利用LSTM模型对分量进行预测；将所有分量预测出来的结果进行叠加得到EGT的预测值。并对EMD-LSTM模型与单一的LSTM模型的预测结果进行对比分析。结果表明：前者比后者的方均根误差和平均相对误差分别降低了35%和42%。说明此模型在预测APU的EGT值上具有更好的预测精度。
- 排气温度 /
- 预测精度 /
- 经验模态分解 /
- 长短期记忆神经网络 /
- 本征模态函数
Abstract:
To improve the prediction accuracy of exhaust gas temperature (EGT), the complexity of the data should be reduced. A combined empirical modal decomposition (EMD) and long short-term memory neural network (LSTM) method was proposed to predict EGT. First, EGT data with time series characteristics were decomposed into intrinsic mode function (IMF) and residual (RES) containing the same characteristics using EMD; the components were predicted using LSTM model; and the results predicted from all components were superimposed to obtain the predicted values of EGT. The prediction results of EMD-LSTM model and single LSTM model were compared and analyzed. The results showed that the former had 35% and 42% lower root mean square error and average relative error than the latter. It indicated that this model has better prediction accuracy in predicting the EGT value of APU.
- exhaust temperature /
- prediction accuracy /
- empirical modal decomposition /
- long and short-term memory neural network /
- intrinsic mode function

HTML

图 1 L_STM结构图

Figure 1. L_STM structure diagram

下载: 全尺寸图片幻灯片

图 2 EGT预测流程图

Figure 2. EGT prediction flow chart

下载: 全尺寸图片幻灯片

图 3 EGT数据序列

Figure 3. EGT data sequence

下载: 全尺寸图片幻灯片

图 4 EMD分解结果

Figure 4. EMD decomposition results

下载: 全尺寸图片幻灯片

图 5 各个分量L_STM预测结果

Figure 5. L_STM prediction results of each component

下载: 全尺寸图片幻灯片

图 6 EGT预测结果对比

Figure 6. Comparison of EGT prediction effect

下载: 全尺寸图片幻灯片

表 1 两种模型的评价结果

Table 1. Evaluation results of two models

预测模型 RMSE MAPE/%

LSTM 5.291 0.7

EMD-L_STM 3.414 0.4

下载: 导出CSV

参考文献(28)

[1]	刘连胜,张晗星,刘晓磊,等. 面向飞机辅助动力装置在翼剩余寿命预测的性能参数扩增方法[J]. 仪器仪表学报,2020,41(7): 107-116. LIU Liansheng,ZHANG Hanxing,LIU Xiaolei,et al. Performance parameter augment method for on-wing remaining useful life prediction of aircraft auxiliary power unit[J]. Chinese Journal of Scientific Instrument,2020,41(7): 107-116. (in Chinese LIU Liansheng, ZHANG Hanxing, LIU Xiaolei, et al. Performance parameter augment method for on-wing remaining useful life prediction of aircraft auxiliary power unit[J]. Chinese Journal of Scientific Instrument, 2020, 41(7): 107-116. (in Chinese)
[2]	LIU Liansheng,WANG Lulu,WANG Shaonian,et al. Remaining useful life prediction of aircraft auxiliary power unit with on-wing sensing data[C]//2018 Prognostics and System Health Management Conference. Piscataway,US: IEEE,2018: 223-228.
[3]	ALASWAD S,XIANG Yisha. A review on condition-based maintenance optimization models for stochastically deteriorating system[J]. Reliability Engineering & System Safety,2017,157: 54-63.
[4]	吕永乐,郎荣玲,路辉,等. 航空发动机性能参数联合RBFPN和FAR预测[J]. 北京航空航天大学学报,2010,36(2): 131-134,149. LÜ Yongle,LANG Rongling,LU Hui,et al. Prediction of aeroengine’s performance parameter combining RBFPN and FAR[J]. Journal of Beijing University of Aeronautics and Astronautics,2010,36(2): 131-134,149. (in Chinese LÜ Yongle, LANG Rongling, LU Hui, et al. Prediction of aeroengine’s performance parameter combining RBFPN and FAR[J]. Journal of Beijing University of Aeronautics and Astronautics, 2010, 36(2): 131-134, 149. (in Chinese)
[5]	丁刚,徐敏强,侯立国. 基于过程神经网络的航空发动机排气温度预测[J]. 航空动力学报,2009,24(5): 1035-1039. DING Gang,XU Minqiang,HOU Liguo. Prediction of aeroengine exhaust gas temperature using process neural network[J]. Journal of Aerospace Power,2009,24(5): 1035-1039. (in Chinese DING Gang, XU Minqiang, HOU Liguo. Prediction of aeroengine exhaust gas temperature using process neural network[J]. Journal of Aerospace Power, 2009, 24(5): 1035-1039. (in Chinese)
[6]	YILMAZ. Evaluation of the relationship between exhaust gas temperature and operational parameters in CFM56-7B engines[J]. Proceedings of the Institution of Mechanical Engineers: Part G Journal of Aerospace Engineering,2009,223(4): 433-440.
[7]	皮骏,马圣,张奇奇,等. 基于改进果蝇算法优化的GRNN航空发动机排气温度预测模型[J]. 航空动力学报,2019,34(1): 8-17. PI Jun,MA Sheng,ZHANG Qiqi,et al. Aero-engine exhaust gas temperature prediction model based on IFOA-GRNN[J]. Journal of Aerospace Power,2019,34(1): 8-17. (in Chinese PI Jun, MA Sheng, ZHANG Qiqi, et al. Aero-engine exhaust gas temperature prediction model based on IFOA-GRNN[J]. Journal of Aerospace Power, 2019, 34(1): 8-17. (in Chinese)
[8]	崔建国,高波,蒋丽英,等. 基于GRVM的航空发动机状态预测技术研究[J]. 控制工程,2018,25(10): 1854-1858. CUI Jianguo,GAO Bo,JIANG Liying,et al. Research on the technology of aeroengine condition prediction based on GRVM[J]. Control Engineering of China,2018,25(10): 1854-1858. (in Chinese CUI Jianguo, GAO Bo, JIANG Liying, et al. Research on the technology of aeroengine condition prediction based on GRVM[J]. Control Engineering of China, 2018, 25(10): 1854-1858. (in Chinese)
[9]	XIE Chuan,ZHANG Peng,YAN Zhi. Correlation analysis of aeroengine operation monitoring using deep learning[J]. Soft Computing,2021,25(1): 551-562. doi: 10.1007/s00500-020-05166-2
[10]	GAO You,SHEN Yuli. Prediction of aero-engine exhaust gas temperature based on chaotic neural network model[C]//Advances in Mechanical and Electronic Engineering. Berlin,Heidelberg: Springer,2012: 145-150.
[11]	ZHANG Chunxiao,YUE Junjie. Application of an improved adaptive chaos prediction model in aero-engine performance parameters[J]. WSEAS Transactions on Mathematics,2012,11(2): 114-124.
[12]	KUMAR A,SRIVASTAVA A,GOEL N,et al. Exhaust gas temperature data prediction by autoregressive models[C]//2015 IEEE 28th Canadian Conference on Electrical and Computer Engineering. Piscataway,US: IEEE,2015: 976-981.
[13]	付旭云,陕振勇,李臻,等. 时变模糊神经网络及其在航空发动机排气温度预测中的应用[J]. 计算机集成制造系统,2014,20(4): 919-925. FU Xuyun,SHAN Zhenyong,LI Zhen,et al. Time-varying fuzzy neural network and its application in prediction of exhaust gas temperature[J]. Computer Integrated Manufacturing Systems,2014,20(4): 919-925. (in Chinese FU Xuyun, SHAN Zhenyong, LI Zhen, et al. Time-varying fuzzy neural network and its application in prediction of exhaust gas temperature[J]. Computer Integrated Manufacturing Systems, 2014, 20(4): 919-925. (in Chinese)
[14]	车畅畅,王华伟,倪晓梅,等. 基于1D-CNN和Bi-LSTM的航空发动机剩余寿命预测[J]. 机械工程学报,2021,57(14): 304-312. CHE Changchang,WANG Huawei,NI Xiaomei,et al. Residual life prediction of aeroengine based on 1D-CNN and Bi-LSTM[J]. Journal of Mechanical Engineering,2021,57(14): 304-312. (in Chinese doi: 10.3901/JME.2021.14.304 CHE Changchang, WANG Huawei, NI Xiaomei, et al. Residual life prediction of aeroengine based on 1D-CNN and Bi-LSTM[J]. Journal of Mechanical Engineering, 2021, 57(14): 304-312. (in Chinese) doi: 10.3901/JME.2021.14.304
[15]	王坤,侯树贤. 基于深度学习的辅助动力装置性能参数预测方法研究[J]. 推进技术,2022,43(1): 290-299. WANG Kun,HOU Shuxian. Prediction method of auxiliary power unit performance parameter based on deep learning[J]. Journal of Propulsion Technology,2022,43(1): 290-299. (in Chinese WANG Kun, HOU Shuxian. Prediction method of auxiliary power unit performance parameter based on deep learning[J]. Journal of Propulsion Technology, 2022, 43(1): 290-299. (in Chinese)
[16]	FU Xuyun,DING Gang,ZHONG Shisheng. Aeroengine turbine exhaust gas temperature prediction using support vector machines[C]//International Symposium on Neural Networks. Berlin,Heidelberg: Springer,2009: 235-241.
[17]	WANG Lulu,LI Ming,LIU Liansheng,et al. Exhaust gas temperature sensing data anomaly detection for aircraft auxiliary power unit condition monitoring[C]//2018 International Conference on Sensing,Diagnostics,Prognostics,and Control. Piscataway,US: IEEE,2018: 426-430.
[18]	ZHENG Jinde,PAN Haiyang. Mean-optimized mode decomposition: an improved EMD approach for non-stationary signal processing[J]. ISA Transactions,2020,106: 392-401. doi: 10.1016/j.isatra.2020.06.011
[19]	BOUDRAA A O,KHALDI K,CHONAVEL T,et al. Audio coding via EMD[J]. Digital Signal Processing,2020,104: 102770. doi: 10.1016/j.dsp.2020.102770
[20]	袁浩,刘紫燕,梁静,等. 融合LSTM的深度强化学习视觉导航[J]. 无线电工程,2022,52(1): 161-167. YUAN Hao,LIU Ziyan,LIANG Jing,et al. Visual navigation based on LSTM and deep reinforcement learning[J]. Radio Engineering,2022,52(1): 161-167. (in Chinese doi: 10.3969/j.issn.1003-3106.2022.01.024 YUAN Hao, LIU Ziyan, LIANG Jing, et al. Visual navigation based on LSTM and deep reinforcement learning[J]. Radio Engineering, 2022, 52(1): 161-167. (in Chinese) doi: 10.3969/j.issn.1003-3106.2022.01.024
[21]	WANG Jujie,ZHANG Wenyu,LI Yaning,et al. Forecasting wind speed using empirical mode decomposition and Elman neural network[J]. Applied Soft Computing,2014,23: 452-459. doi: 10.1016/j.asoc.2014.06.027
[22]	谷玉海,朱腾腾,饶文军,等. 基于EMD二值化图像和CNN的滚动轴承故障诊断[J]. 振动测试与诊断,2021,41(1): 105-113,203. GU Yuhai,ZHU Tengteng,RAO Wenjun,et al. Fault diagnosis for rolling bearing based on EMD binarization image and CNN[J]. Journal of Vibration,Measurement & Diagnosis,2021,41(1): 105-113,203. (in Chinese GU Yuhai, ZHU Tengteng, RAO Wenjun, et al. Fault diagnosis for rolling bearing based on EMD binarization image and CNN[J]. Journal of Vibration, Measurement & Diagnosis, 2021, 41(1): 105-113, 203. (in Chinese)
[23]	岳相臣. 经验模态分解算法应用研究[D]. 西安: 西安电子科技大学,2013. YUE Xiangchen. Research on empirical mode decomposition algorithm’s application[D]. Xi’an: Xidian University,2013. (in Chinese YUE Xiangchen. Research on empirical mode decomposition algorithm’s application[D]. Xi’an: Xidian University, 2013. (in Chinese)
[24]	吕鲜,戚湧,张伟斌. 基于长短期记忆模型的交通拥堵预测方法[J]. 南京理工大学学报,2020,44(1): 26-32,48. LV Xian,QI Yong,ZHANG Weibin. Traffic congestion prediction method based on long short-term memory model[J]. Journal of Nanjing University of Science and Technology,2020,44(1): 26-32,48. (in Chinese LV Xian, QI Yong, ZHANG Weibin. Traffic congestion prediction method based on long short-term memory model[J]. Journal of Nanjing University of Science and Technology, 2020, 44(1): 26-32, 48. (in Chinese)
[25]	明彤彤,王凯,田冬冬,等. 基于LSTM神经网络的锂离子电池荷电状态估算[J]. 广东电力,2020,33(3): 26-33. MING Tongtong,WANG Kai,TIAN Dongdong,et al. Estimation on state of charge of lithium battery based on LSTM neural network[J]. Guangdong Electric Power,2020,33(3): 26-33. (in Chinese MING Tongtong, WANG Kai, TIAN Dongdong, et al. Estimation on state of charge of lithium battery based on LSTM neural network[J]. Guangdong Electric Power, 2020, 33(3): 26-33. (in Chinese)
[26]	WU Jun,HU Kui,CHENG Yiwei,et al. Data-driven remaining useful life prediction via multiple sensor signals and deep long short-term memory neural network[J]. ISA Transactions,2020,97: 241-250. doi: 10.1016/j.isatra.2019.07.004
[27]	YE Shu,JIANG Jianguo,LI Junjie,et al. Fault diagnosis and tolerance control of five-level nested NPP converter using wavelet packet and LSTM[J]. IEEE Transactions on Power Electronics,2020,35(2): 1907-1921. doi: 10.1109/TPEL.2019.2921677
[28]	李鹏,何帅,韩鹏飞,等. 基于长短期记忆的实时电价条件下智能电网短期负荷预测[J]. 电网技术,2018,42(12): 4045-4052. LI Peng,HE Shuai,HAN Pengfei,et al. Short-term load forecasting of smart grid based on long-short-term memory recurrent neural networks in condition of real-time electricity price[J]. Power System Technology,2018,42(12): 4045-4052. (in Chinese LI Peng, HE Shuai, HAN Pengfei, et al. Short-term load forecasting of smart grid based on long-short-term memory recurrent neural networks in condition of real-time electricity price[J]. Power System Technology, 2018, 42(12): 4045-4052. (in Chinese)