|Table of Contents|

Prediction of engine performance degradation based on adaptive change points(PDF)

《交通运输工程学报》[ISSN:1671-1637/CN:61-1369/U]

Issue:
2023年05期
Page:
143-151
Research Field:
载运工具运用工程
Publishing date:
2023-11-10

Info

Title:
Prediction of engine performance degradation based on adaptive change points
Author(s):
LI Yao-hua;  ZHANG Cheng
(School of Transportation Science and Engineering, Civil Aviation University of China, Tianjin 300300, China)
Keywords:
aeroengine;  reliability assessment;  Bayesian information criterion;  uncertain Liu process;  adaptive change point;  stage degradation
PACS:
V235.13
DOI:
10.19818/j.cnki.1671-1637.2023.05.009
Abstract:
To effectively utilize the monitoring big data to accurately identify the performance status and predict the performance degradation process of civil aircraft engines, a reliability evaluation model considering the uncertain degradation characteristics of civil aircraft engine performance parameters in different stages was proposed, so as to address the lack of fault data and the multi-stage degradation characteristics of civil aircraft engines during the performance degradation process. The change point detection model based on the Bayesian information criterion(BIC)was improved by the dynamic adaptive window width, and the adaptive change point was identified by the improved BIC with adaptive window width. Based on the identified adaptive change points, a distribution function model of the uncertain Liu process was established in stages. The reliability evaluation was conducted according to the mathematical properties of the first threshold of the performance degradation process of civil aircraft engines. In addition, the accuracy and superiority of the model were verified by comparing the sample data of performance degradation of civil aircraft engines. Analysis results indicate that the mean square error of degradation process in stages described by the change points is 5.8×10-28 after identifying the change points of performance degradation process of civil aircraft engines by using the BIC change point detection model with the improved adaptive window width. Under the conditions that the adaptive window width has different changing rules, the identified change points have no obvious change. Therefore, the model can accurately identify the adaptive change points of performance degradation process of civil aircraft engines and has strong robustness. When the uncertain Liu process in stages is used to analyze the dynamic degradation law of performance parameters of civil aircraft engines, the average evaluation error reduces by about 23.69% compared with the original Liu process model, and the reliability evaluation results are more accurate. Due to the Lipschitz continuity, the improved model can accurately predict the reliability level of performance degradation process of civil aircraft engines in a certain period of time in the future. It can be seen that the established improved reliability evaluation model can provide theoretical methods for the performance status monitoring and health management application of civil aircraft engines in practical engineering. 7 figs, 30 refs.

References:

[1] 潘 刚,尚朝轩,梁玉英,等.考虑认知不确定的雷达功率放大系统可靠性评估[J].北京航空航天大学,2016,42(6):1185-1194.
PAN Gang, SHANG Chao-xuan, LIANG Yu-ying, et al. Reliability evaluation of radar power amplification system considering epistemic uncertainty[J]. Journal of Beijing University of Aeronautics and Astronautics, 2016, 42(6): 1185-1194.(in Chinese)
[2] LIU Bao-ding. Why is there a need for uncertainty theory[J]. Journal of Uncertain Systems, 2011, 6(1): 3-10.
[3] 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.
MA 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)
[4] QIU Qing-an, CUI Li-rong. Reliability evaluation based on a dependent two-stage failure process with competing failures[J]. Applied Mathematical Modelling, 2018, 64: 699-712.
[5] LIU Le, LI Xiao-yang, SUN Fu-qiang, et al. A general accelerated degradation model based on the Wiener process[J]. Materials, 2016, 9(12): 981.
[6] LIU Bao-ding. Uncertainty distribution and independence of uncertain processes[J]. Fuzzy Optimization and Decision Making, 2014, 13(3): 259-271.
[7] LIU Bao-ding. Fuzzy process, hybrid process and uncertain process[J]. Journal of Uncertain System, 2008, 2(1): 3-16.
[8] LIU Bao-ding. Some research problems in uncertainty theory[J]. Journal of Uncertain System, 2009, 3(1): 3-10.
[9] GAO Jin-wu, YAO Kai, ZHOU Jian, et al. Reliability analysis of uncertain weighted k-out-of-n systems[J]. IEEE Transactions on Fuzzy Systems, 2018, 26(5): 2663-2671.
[10] ZHANG Qing-yang, KANG Rui, WEN Mei-lin. Belief reliability for uncertain random systems[J]. IEEE Transactions on Fuzzy Systems, 2018, 26(6): 3605-3614.
[11] ZHANG Qing-yang, ZENG Zhi-guo, ZIO E, et al. Probability box as a tool to model and control the effect of epistemic uncertainty in multiple dependent competing failure processes[J]. Applied Soft Computing, 2017, 56: 570-579.
[12] YAO Kai. First hitting time of uncertain random renewal reward process and its application in insurance risk process[J]. Soft Computing, 2019, 23(11): 3687-3696.
[13] ZHANG Qing-yang, KANG Rui, WEN Mei-lin. A new method of level-2 uncertainty analysis in risk assessment based on uncertainty theory[J]. Soft Computing, 2018, 22(17): 5867-5877.
[14] YAO Kai, LIU Bao-ding. Parameter estimation in uncertain differential equations[J]. Fuzzy Optimization and Decision Making, 2020, 19(1): 1-12.
[15] YANG Xiang-feng, LIU Bao-ding. Uncertain time series analysis with imprecise observations[J]. Fuzzy Optimization and Decision Making, 2019, 18(3): 263-278.
[16] CAO Xue-rui, HU Lin-min, LI Zhen-zhen. Reliability analysis of discrete time series-parallel systems with uncertain parameters[J]. Journal of Ambient Intelligence and Humanized Computing, 2019, 10: 2657-2668.
[17] LIU Zhao-cai, HU Lin-min, LIU Si-jia, et al. Reliability analysis of general systems with bi-uncertain variables[J]. Soft Computing, 2020, 24: 6975-6986.
[18] LI Xiao-yang, WU Ji-peng, LIU Le, et al. Modeling accelerated degradation data based on the uncertain process[J]. IEEE Transactions on Fuzzy Systems, 2019, 27(8): 1532-1542.
[19] LIU Bao-liang, ZHANG Zhi-qiang, WEN Yan-qing. Reliability analysis for devices subject to competing failure processes based on chance theory[J]. Applied Mathematical Modelling, 2019, 75: 398-413.
[20] 刘宝亮,张志强,温艳清,等.具有变点的不确定竞争失效退化系统的可靠性建模[J].北京航空航天大学学报,2020,46(11):2039-2044.
LIU Bao-liang, ZHANG Zhi-qiang, WEN Yan-qing, et al. Reliability modeling of uncertain competitive failure degradation systems with change points[J]. Journal of Beijing University of Aeronautics and Astronautics, 2020, 46(11): 2039-2044.(in Chinese)
[21] 车畅畅,王华伟,倪晓梅,等.基于多尺度排列熵和长短时记忆神经网络的航空发动机剩余寿命预测[J].交通运输工程学报,2019,19(5):106-115.
CHE Chang-chang, WANG Hua-wei, NI Xiao-mei, et al.Residual life prediction of aeroengine based on multi-scale permutation entropy and LSTM neural network[J]. Journal of Traffic and Transportation Engineering, 2019, 19(5): 106-115.(in Chinese)
[22] KORKAS K K, FRYZLEWICZ P. Multiple change-point detection for non-stationary time series using wild binary segmentation[J]. Statistica Sinica, 2017, 27(1): 287-311.
[23] FRICK K, MUNK A, SIELING H. Multiscale change point inference[J]. Journal of the Royal Statistical Society Series B: Statistical Methodology, 2014, 76(3): 495-580.
[24] MESSER M, ALBERT S, SCHNEIDER G. The multiple filter test for change point detection in time series[J]. Metrika, 2018, 81(6): 589-607.
[25] MESSER M, KIRCHNER M, SCHIEMANN J, et al. A multiple filter test for the detection of rate changes in renewal processes with varying variance[J]. The Annals of Applied Statistics, 2014, 8(4): 2027-2067.
[26] 夏正敏.基于分形的网络流量分析及异常检测技术研究[D].上海:上海交通大学,2012.
XIA Zheng-min. Research on network traffic analysis and anomaly detection based on fractal theory[D]. Shanghai: Shanghai Jiao Tong University, 2012.(in Chinese)
[27] LIU Bao-ding. Extreme value theorems of uncertain process with application to insurance risk model[J]. Soft Computing, 2013, 17: 549-556.
[28] ZHANG Chong, LIM P, QIN A K, et al. Multiobjective deep belief networks ensemble for remaining useful life estimation in prognostics[J]. Transactions on Neural Networks and Learning Systems, 2017, 28(10): 2306-2318.
[29] KHANH L S, MITRA F, ANNE B, et al. Remaining useful life estimation based on stochastic deterioration models: a comparative study[J]. Reliability Engineering and System Safety, 2013, 112(5): 165-175.
[30] LI Shu-min, CHEN Yin. Reliably evaluation method considering FM dependency via uncertainty theory[C]∥IEEE. 2020 11th International Conference on Prognostics and System Health Management(PHM-2020 Jinan). New York: IEEE, 2020: 91-96.

Memo

Memo:
-
Last Update: 2023-11-10