基于综合指标多阶段相似的发动机寿命预测

doi:10.12305/j.issn.1001-506X.2021.05.33

摘要/Abstract

摘要：

针对航空发动机全寿命周期数据对性能衰退不够敏感的问题, 提出一种基于综合指标多阶段相似的寿命预测方法。首先, 使用参数变化幅度、参数起始值差异和参数失效值差异对多个传感器参数进行筛选, 将符合综合标准的参数融合成综合指标。然后, 采用移动相似性匹配的方法分别对整阶段和半阶段进行最优多模型选取, 将两个阶段的最优多模型寿命预测结果进行融合完成最终寿命预测。最后, 利用美国国家航空航天局数据集验证该综合指标和该方法的有效性, 其寿命预测精度高于单阶段多模型相似性寿命预测。

关键词: 综合指标, 多阶段, 相似性, 寿命预测

Abstract:

Aiming at the problem that the life cycle data of aeroengine is not sensitive to performance degradation, a multi-stage similarity life prediction method based on a comprehensive index is proposed. Firstly, the parameter variation scale, the parameter initial value difference, and the parameter value difference at failure are utilized to screen the multiple sensor parameters, and the parameters which meeting the comprehensive standards are merged into a comprehensive index. Then, the moving similarity matching method is used to select the optimal multi-model for the whole and half stage, respectively. And the results from the two-stage optimal multi-model life prediction are fused to complete the final life prediction. Finally, the data set of National Aeronautics and Space Administration(NASA) is used to verify the validity of the comprehensive index and the method, and the prediction accuracy is higher than the single-stage multi-model similarity life prediction.

Key words: comprehensive index, multi-stage, similarity, life prediction

中图分类号:

V239

赵洪利, 陈天铭, 郑涅. 基于综合指标多阶段相似的发动机寿命预测[J]. 系统工程与电子技术, 2021, 43(5): 1430-1436.

Hongli ZHAO, Tianming CHEN, Nie ZHENG. Engine life prediction based on multi-stage similarity of comprehensive index[J]. Systems Engineering and Electronics, 2021, 43(5): 1430-1436.

图/表 13

图1

图2

表1

图3

图4

图5

图6

表2

图7

表3

表4

图8

表5

参考文献 31

1	尉询楷, 杨立, 刘芳, 等. 航空发动机预测与健康管理[M]. 北京: 国防工业出版社, 2014: 132- 133.
	WEI X K , YANG L , LIU F , et al. Aer engine prediction and health management[M]. Beijing: National Defense Industry Press, 2014: 132- 133.
2	ELSHEIKH A , YACOUT S , OUALI M S . Bidirectional handshaking LSTM for remaining useful life prediction[J]. Neurocomputing, 2019, 323, 148- 156. doi: 10.1016/j.neucom.2018.09.076
3	PENG Y Z , WANG Y , ZI Y Y . Switching state-space degradation model with recursive filter/smoother for prognostics of remaining useful life[J]. IEEE Trans.on Industrial Informatics, 2018, 15 (2): 822- 832.
4	LEI Y G , LI N P , GONTARZ S , et al. A model-based method for remaining useful life prediction of machinery[J]. IEEE Trans.on Reliability, 2016, 65 (3): 1314- 1326. doi: 10.1109/TR.2016.2570568
5	LI N , LEI Y , LIN J , et al. An improved exponential model for predicting remaining useful life of rolling element bearings[J]. IEEE Trans.on Industrial Electronics, 2015, 62 (12): 7762- 7773. doi: 10.1109/TIE.2015.2455055
6	PECHT M . Prognostics and health management of slsctronics[M]. New Jersey: Wiley Online Library, 2008.
7	ELLEFSEN A L , BJORLYKHAUG E , ESOY V , et al. Remaining useful life predictions for turbofan engine degradation using semi-supervised deep architecture[J]. Reliability Engineering & System Safety, 2019, 183, 240- 251.
8	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.
	ZHAO G S , WU S S , RONG H J . A multi-source statics data-driven method for remaining useful life prediction of aircraft engine[J]. Journal of Xi'an Jiaotong University, 2017, 51 (11): 150- 155.
9	黄亮, 刘君强, 贡英杰. 基于一致性检验的航空发动机剩余寿命预测[J]. 系统工程与电子技术, 2018, 40 (12): 2736- 2742.
	HUANG L , LIU J Q , GONG Y J . Residual lifetime prediction of aeroengines based on the consistency test[J]. Systems Engi-neering and Electronics, 2018, 40 (12): 2736- 2742.
10	车畅畅, 王华伟, 倪晓梅, 等. 基于改进GRU的航空发动机剩余寿命预测[J]. 航空计算技术, 2020, 50 (1): 13- 16.
	CHE C C , WANG H W , NI X M , et al. Residual life prediction of aeroengine based on improved GRU[J]. Aeronautical Computing Technique, 2020, 50 (1): 13- 16.
11	宋亚, 夏唐斌, 郑宇, 等. 基于Autoencoder-BLSTM的涡扇发动机剩余寿命预测[J]. 计算机集成制造系统, 2019, 25 (7): 1611- 1619.
	SONG Y , XIA T B , ZHENG Y , et al. Remaining useful life prediction of turbofan engine based on autoencoder-BLSTM[J]. Computer Integrated Manufacturing Systems, 2019, 25 (7): 1611- 1619.
12	WANG T Y. Trajectory similarity based prediction for remaining useful life estimation[D]. Cincinnati: University of Cincinnati, 2010.
13	SHI J M , LI Y X , WANG G , et al. Health index synthetization and remaining useful life estimation for turbofan engines based on run-to-failure datasets[J]. Maintenance and Reliability, 2016, 18 (4): 621- 631. doi: 10.17531/ein.2016.4.18
14	张妍, 王村松, 陆宁云, 等. 基于退化特征相似性的航空发动机寿命预测[J]. 系统工程与电子技术, 2019, 41 (6): 1414- 1421.
	ZANG Y , WANG C S , LU N Y , et al. Remaining useful life prediction for aero-engine based on the similarity of degradation characteristics[J]. Systems Engineering and Electronics, 2019, 41 (6): 1414- 1421.
15	曹惠玲, 崔科璐, 梁佳旺. 基于多参数融合相似的民航发动机寿命预测[J]. 中国机械工程, 2020, 31 (7): 781- 787.
	CAO H L , CUI K L , LIANG J W . Multi-parameter fusion similarity-based method for remaining useful life prediction of civil aviation engine[J]. China Mechanical Engineering, 2020, 31 (7): 781- 787.
16	YU W M , KIM Y , MECHEFSKE C . An improved similarity-based prognostic algorithm for RUL estimation using an RNN autoencoder scheme[J]. Reliability Engineering and System Safety, 2020, 199, 106926. doi: 10.1016/j.ress.2020.106926
17	GUO L, LEI Y G, LI N P, et al. Deep convolution feature learning for health indicator construction of bearings[C]//Proc. of the Prognostics and System Health Management Conference, 2017.
18	LIAO L X , JIN W J , PAVEL R . Enhanced restricted boltzmann machine with prognosability regularization for prognostics and health assessment[J]. IEEE Trans.on Industrial Electro-nics, 2016, 63 (11): 7076- 7083. doi: 10.1109/TIE.2016.2586442
19	HOU M R , PI D C , LI B R . Similarity-based deep learning approach for remaining useful life prediction[J]. Measurement, 2020, 159, 107788. doi: 10.1016/j.measurement.2020.107788
20	赵洪利, 张猛. 基于随机维纳过程的航空发动机性能衰退研究[J]. 推进技术, 2021, 42 (3): 488- 494.
	ZHAO H L , ZHANG M . Research on performance degradation of aeroengines baesd on stochastic wiener process[J]. Journal of Propulsion Technology, 2021, 42 (3): 488- 494.
21	Department of Denfense. MIL-HDBK-516C ariworthiness certification criteria[S]. Washington: Department of Defense, 2014.
22	BENZAKEIN M. Propulsion strategy for the 21st century-a vision into the future[C]//Proc. of the ISABE, 2001.
23	Department of Denfense. JSSG 2007B Joint service specification guide: engines, aircraft, turbine[S]. Washington: Department of defense, 2008: 1-575.
24	Federal Aviation Administration. FAR 33 airworthiness standards: aircraft engine[S]. Washington: Federal Aviation Administration, 1984.
25	YU W , KIM I Y , MECHEFSKE C K . Remaining useful life estimation using a bidirectional recurrent neural network based autoencoder scheme[J]. Mechanical Systems and Signal Processing, 2019, 129, 764- 780. doi: 10.1016/j.ymssp.2019.05.005
26	ZHANG Q , TSE W T , WAN X , et al. Remaining useful life estimation for mechanical systems based on similarity of phase space trajectory[J]. Expert Systems with Applications, 2015, 42 (5): 2353- 2360. doi: 10.1016/j.eswa.2014.10.041
27	KHELIF R, MALINOWSKI S, CHEBEL-MORELLO B, et al. RUL prediction based on a new similarity-instance based approach[C]//Proc. of the IEEE 23rd International Symposium on Industrial Electronics, 2014: 2463-2468.
28	WANG T Y, YU J B, SIEGEL D, et al. A similarity-based prognostics approach for remaining useful life estimation of engineered systems[C]//Proc. of the IEEE International Confe-rence on Prognostics and Health Management, 2008: 4-9.
29	EMMANUEL R. Investigating computational geometry for failure prognostics in presence of imprecise health indicator: results and comparisons on C-MAPSS datasets[C]//Proc. of the 2nd European Conference of the Prognostics and Health Management Society, 2014.
30	SEXENA A, KAI G, SIMO N, et al. Damage propagation modeling for aircraft engine run-to-failure simulation[C]//Proc. of the IEEE International Conference on Prognostics and Health Management, 2008.
31	HANZ R . Advanced control of turbofan engines[M]. Germany: Springer, 2012.

序号	符号	具体含义
1	T2	风扇进口总温
2	T24	低压压气机出口总温
3	T30	高压压气机出口总温
4	T50	低压涡轮出口总温
5	P2	风扇进口压力
6	P15	外涵道道总压
7	P30	高压压气机出口总压
8	Nf	未修正的风扇转速
9	Nc	未修正的核心机转速
10	epr	发动机压力比
11	Ps30	高压压气机出口静压
12	Phi	燃油流量和P30比值
13	NRf	风扇修正转速
14	NRc	核心机修正转速
15	BPR	涵道比
16	farB	燃烧室油气比
17	htBleed	引气焓值
18	Nf_dmd	风扇转速设定值
19	PCNfR_dmd	风扇修正转速设定值
20	W31	高压涡轮引气量
21	W32	低压涡轮引气量

参数序号	参数名称	权重值
3	低压涡轮出口总温	0.617 8
7	高压压气机出口静压	0.229 8
13	高压涡轮引气量	0.067 5
14	低压涡轮引气量	0.084 9

运行循环	综合指标	低压涡轮出口总温
40运行循环	0.218 186	0.228 588
80运行循环	0.199 913	0.279 911
120运行循环	0.232 731	0.275 942

运行循环	RMSE	MAE
40运行循环	0.214 844	0.218 186
80运行循环	0.217 335	0.199 913
120运行循环	0.246 365	0.232 731

预测结果	多阶段多模型	多模型	单模型
MAPE/%	0.146 578	0.177 883	0.232 731
预测误差范围	[-55, 37]	[-66, 55]	[-89, 82]