基于气路参数融合的涡扇发动机性能退化预测

郭庆; 李印龙

doi:10.13224/j.cnki.jasp.20200420

基于气路参数融合的涡扇发动机性能退化预测

doi: 10.13224/j.cnki.jasp.20200420

郭庆,
李印龙

中国民航大学航空工程学院，天津 300300

基金项目: 中国民航大学研究生科研创新资助项目（10502730）

详细信息

通讯作者:
郭庆（1976-），男，副教授，硕士，研究领域为航空装备综合保障。

中图分类号: V267
计量
- 文章访问数: 163
- HTML浏览量: 4
- PDF量: 148
- 被引次数: 0
出版历程
- 收稿日期: 2020-10-09
- 刊出日期: 2021-11-28

Turbofan engine performance degradation prediction based on gas path parameter fusion

College of Aeronautical Engineering，Civil Aviation University of China，Tianjin 300300，China

摘要

摘要: 针对单参数驱动的涡扇发动机性能退化预测精度不高的问题，提出了一种基于气路参数融合的涡扇发动机性能退化预测的方法。通过监测发动机性能退化过程中多源参数，采用专家经验和核主成分分析相结合的方法，进行发动机性能参数的选择和融合，从而构建健康参数。基于非线性Wiener过程构建涡扇发动机退化模型，采用极大似然方法求得发动机退化模型的离线参数估计值；由于不同发动机性能退化的差异性，基于贝叶斯更新理念对随机参数进行实时更新，可以实现对单台发动机的性能退化实时预测。通过实例验证，采用此方法在预测末端方均根误差为0.028 3，整体预测精度提升了54.5%，可以辅助指导维修决策。
- 性能退化预测 /
- 涡扇发动机 /
- 多参数融合 /
- 核主成分分析 /
- 非线性Wiener
Abstract: In view of the problem of low accuracy in predicting performance degradation of turbofan engine driven by a single parameter，a turbofan engine performance degradation prediction method based on gas path parameter fusion was proposed.By monitoring multi-source parameters in the process of engine performance degradation，a combination of expert experience and nuclear principal component analysis was used to select and integrate engine performance indicators to construct health parameters.The turbofan engine degradation model was constructed based on the nonlinear Wiener process，and the maximum likelihood method was used to obtain the offline parameter estimates of the engine degradation model secondly，due to the difference of performance degradation of different engines，real-time updating of random parameters based on Bayesian updating concept can realize real-time prediction of performance degradation of single engine.Finally，through the verification of examples，the root mean square error at the end of prediction using this method was 0.028 3，and the overall prediction accuracy was improved by 54.5%，which can assist in guiding maintenance decision-making.
- performance degradation prediction /
- turbofan engine /
- multi-parameter fusion /
- nuclear principal component analysis /
- nonlinear Wiener

HTML

参考文献(28)

[1]	ZHANG Z,SI X,HU C,et al.Degradation data analysis and remaining useful life estimation:a review on wiener-process-based methods[J].European Journal of Operational Research,2018,271（3）:775-796.
[2]	周东华,魏慕恒,司小胜.工业过程异常检测、寿命预测与维修决策的研究进展[J].自动化学报,2013,39（6）:711-722.
[3]	HUANG Z,XU Z,WANG W,et al.Remaining useful life prediction for a nonlinear heterogeneous wiener process model with an adaptive drift[J].IEEE Transactions on Reliability,2015,64（2）:687-700.
[4]	李业波,李秋红,黄向华,等.航空发动机性能退化缓解控制技术[J].航空动力学报,2012,27（4）:930-936.
[5]	CHEN Z,CAO S,MAO Z.Remaining useful life estimation of aircraft engines using a modified similarity and supporting vector machine （SVM） approach[J].Energies,2017,11（1）:1-14.
[6]	WU Y,YUAN M,DONG S.Remaining useful life estimation of engineered systems using vanilla LSTM neural networks[J].Neurocomputing,2018,275（3）:167-179.
[7]	王玺,胡昌华,任子强,等.基于非线性Wiener过程的航空发动机性能衰减建模与剩余寿命预测[J].航空学报,2020,41（2）:195-205.
[8]	赵申坤,姜潮,龙湘云.一种基于数据驱动和贝叶斯理论的机械系统剩余寿命预测方法[J].机械工程学报,2018,54（12）:115-124.
[9]	王华伟,高军,吴海桥.基于贝叶斯模型平均的航空发动机可靠性分析[J].航空动力学报,2014,29（2）:305-313.
[10]	周俊.数据驱动的航空发动机剩余使用寿命预测方法研究[D].南京：南京航空航天大学,2017.
[11]	ZHOU Shenghan,XU Xingxing,XIAO Yiyong,et al.Remaining useful life prediction with similarity fusion of multi-parameter and multi-sample based on the vibration signals of diesel generator gearbox[J].Entropy,2019,21（9）：861-889.
[12]	赵广社,吴思思,荣海军.多源统计数据驱动的航空发动机剩余寿命预测方法[J].西安交通大学学报,2017,51（11）:150-155，172.
[13]	YAN H,LIU K,ZHANG X,et al.Multiple sensor data fusion for degradation modeling and prognostics under multiple operational conditions[J].IEEE Transactions on Reliability,2016,65（3）:1416-1426.
[14]	FANG X,PAYNABAR K,GEBRAEEL N.Multistream sensor fusion-based prognostics model for systems with single failure modes[J].Reliability Engineering and System Safety,2017,159:322-331.
[15]	任子强,司小胜,胡昌华,等.融合多传感器数据的发动机剩余寿命预测方法[J].航空学报,2019,40（12）:134-145.
[16]	TKACZ E，KOZANECKA D，KOZANECKI Z.Investigations of oil-free support systems to improve the reliability of ORC hermetic high-speed turbomachinery[J].Mechanics and Mechanical Engineering，2011，15（3）：355-365.
[17]	者娜,杨剑锋,刘文彬.KPCA和改进SVM在滚动轴承剩余寿命预测中的应用研究[J].机械设计与制造,2019（11）:1-4，8.
[18]	LIU K,GEBRAEEL N Z,SHI J.A data-level fusion model for developing composite health indices for degradation modeling and prognostic analysis[J].IEEE Transactions on Automation Science and Engineering,2013,10（3）:652-664.
[19]	林震,姜同敏,程永生,等.阿伦尼斯模型研究[J].电子产品可靠性与环境试验,2005,17（6）:12-14.
[20]	WANG Yudong,TANG Yincai.Statistical analysis of accelerated temperature cycling test based on Coffin-Manson model[J].Communications in Statistics-Theory and Methods,2020,49（15）:3663-3680.
[21]	王浩伟,徐廷学,米巧丽,等.加速应力下基于Gamma过程的寿命预测方法[J].科学技术与工程,2013,13（35）:10455-10459.
[22]	高惠璇.应用多元统计分析[M].北京:北京大学出版社,2005.
[23]	李宏.求解几类复杂优化问题的进化算法及其应用[D].西安:西安电子科技大学,2009.
[24]	ZIO E,PELONI G.Particle filtering prognostic estimation of the remaining useful life of nonlinear components[J].Reliability Engineering and System Safety,2011,96（3）:403-409.
[25]	CHEHADE A,SONG C,LIU K,et al.A data-level fusion approach for degradation modeling and prognostic analysis under multiple failure modes[J].Journal of Quality Technology,2018,50（2）:150-165.
[26]	SI X,WANG W,HU C,et al.Remaining useful life estimation based on a nonlinear diffusion degradation process[J].IEEE Transactions on Reliability,2012,61（1）:50-67.
[27]	SAXENA A,GOEBEL K,SIMON D,et al.Damage propagation modeling for aircraft engine run-to-failure simulation[C]∥Proceedings of International Conference on Prognostics and Health Management.Denver,USA:International Conference on Prognostics and Health Management,2008:1-9.
[28]	CARR M,WANG W.An approximate algorithm for prognostic modelling using condition monitoring information[J].Europen Journal of Operational Research,2011,211（1）:90-96.