A Multi-Source Statistics Data-Driven Method for Remaining Useful Life Prediction of Aircraft Engine

doi:10.7652/xjtuxb201711021

您当前的位置：

首页 >

文章列表页 >

A Multi-Source Statistics Data-Driven Method for Remaining Useful Life Prediction of Aircraft Engine

更新时间：2025-07-09

- A Multi-Source Statistics Data-Driven Method for Remaining Useful Life Prediction of Aircraft Engine
- Vol. 51, Issue 11, Pages: 150-155+172(2017)
- 作者机构：
  
  1. 西安交通大学电子与信息工程学院,西安,710049
  2. 西安交通大学机械结构强度与振动国家重点实验室,西安,710049
  3. 西安交通大学陕西省先进飞行器服役环境与控制重点实验室,西安,710049
  4. 西安交通大学航天航空学院,西安,710049
- 作者简介：
- 基金信息：
- DOI：10.7652/xjtuxb201711021
  CLC： V263
- Online First：10 November 2017，
  
  Published：2017
- 稿件说明：
移动端阅览
A Multi-Source Statistics Data-Driven Method for Remaining Useful Life Prediction of Aircraft Engine[J]. 2017, 51(11): 150-155+172.
DOI：

A Multi-Source Statistics Data-Driven Method for Remaining Useful Life Prediction of Aircraft Engine[J]. 2017, 51(11): 150-155+172. DOI： 10.7652/xjtuxb201711021.

摘要

针对统计数据驱动方法中多变量无法建立退化模型的问题

提出了一种多源统计数据驱动的航空发动机剩余寿命(RUL)预测方法。建立了基于欧氏距离的航空发动机监测信息融合模型

综合多源监测数据以量化发动机健康状态退化过程; 构建了基于非线性漂移维纳过程的航空发动机退化模型

推导发动机剩余寿命概率密度函数解析式

实现对发动机剩余寿命的估计。选取C-MAPSS数据集进行仿真实验

结果表明

与已有研究结果相比

所提方法预测结果在确定系数和惩罚得分两项均有所改进。该方法可为其他非线性退化系统的RUL预测提供一定的参考。

Abstract

A multi-source statistical data-driven method for remaining useful life(RUL)prediction of aircraft engines is proposed to solve the difficulty that the multivariate degradation model cannot be constructed. To quantify the degradation process of aircraft engines with the multi-source monitoring data

an information fusion model based on Euclidean distance is established. To estimate the RUL of aircraft engines

the arithmetic model of aircraft engines consisting of Wiener process with nonlinear drift is considered to derive the probability density function of RUL. The performance of the proposed method is verified by C-MAPSS. The simulations show that the proposed method improves coefficient of determination and total score compared with the existing results. The proposed approach provides new insights to RUL prediction of the other nonlinear degradation systems.

关键词

Keywords

references

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.

AHMAZADEH F, LUNDBERG J. Remaining useful life estimation: review [J]. International Journal of System Assurance Engineering and Management, 2014, 5(4): 461-474.

AHMADZADEH F. Mean residual life estimation considering operating environment [EB/OL]. [2017-02-23]. https: ∥pdfs.semanticscholar.org/333d/178 0c52a97f865b08b77880cdbdcd37f0866.pdf.

SI X S, WANG W B, HU C H, et al. Remaining useful life estimation: a review on the statistical data driven approaches [J]. European Journal of Operational Research, 2011, 213(1): 1-14.

COX D R, MILLER H D, et al. The theory of stochastic processes [M]. New York, USA: Wiley, 1965: 81-83.

任淑红, 左洪福, 白芳. 基于带漂移的布朗运动的民用航空发动机实时性能可靠性预测 [J]. 航空动力学报, 2009, 24(12): 166-171.

REN Shuhong, ZUO Hongfu, BAI fang. Real-time performance reliability prediction for civil aviation engines based on Brownian motion with drift [J]. Journal of Aerospace Power, 2009, 24(12): 166-171.

朱磊, 左洪福, 蔡景. 基于Wiener过程的民用航空发动机性能可靠性预测 [J]. 航空动力学报, 2013, 28(5): 1006-1012.

ZHU Lei, ZUO Hongfu, CAI Jing. Performance relia-bility prediction for civil aircraft engine based on Wiener process [J]. Journal of Aerospace Power, 2013, 28(5): 1006-1012.

周经伦, 厉海涛, 刘学敏, 等. 维纳过程寿命预测的一种自助法 [J]. 系统工程理论与实践, 2011, 31(8): 1588-1592.

ZHOU Jinglun, LI Haitao, LIU Xuemin, et al. A boot-strap method of life prediction based on Wiener process [J]. Systems Engineering Theory Practice, 2011, 31(8): 1588-1592.

SAXENA A, KAI G, SIMON D, et al. Damage prop-agation modeling for aircraft engine run-to-failure simulation [C]∥International Conference on Prognostics and Health Management. Piscataway, NJ, USA: IEEE, 2008: 1-9.

CAPOCELLI R M, RICCIARDI L M. On the transformation of diffusion processes into the wiener process [J]. Journal of Mathematical Analysis Applications, 1980, 54(1): 185-199.

SI X S, WANG W, HU C H, et al. Remaining useful life estimation based on a nonlinear diffusion degradation process [J]. IEEE Transactions on Reliability, 2012, 61(1): 50-67.

RAMASSO E, ROMBAUT M, ZERHOUNI N. Joint prediction of continuous and discrete states in time-series based on belief functions [J]. IEEE Transactions on Cybernetics, 2012, 43(1): 37-50.

JAVED K, GOURIVEAU R, ZERHOUNI N. A new multivariate approach for prognostics based on extreme learning machine and fuzzy clustering [J]. IEEE Transactions on Cybernetics, 2015, 45(12): 2626-2639.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Prediction Method for Remaining Useful Life of Standby Systems Considering Degradation of Spare Parts

Blind Vibration Sources Separation Method Based on Signal Feature of Aircraft Engine

Effects of Expansion Angle Crater Film Hole on the Film Cooling Characteristics of a Double-Wall Structure

Research on the Electrohydrodynamic Effects of Ionic Liquid-Modified Fuels

A Fast Calculation Method for Thermal Flow Fields in Transformer Windings Based on PI-DeepONet

Related Author

ZHANG Jialing

ZHANG Jianxun

DU Dangbo

ZHANG Zhengxin

SI Xiaosheng

杨广振 1

荆建平 1

明阳 2

Related Institution

(Zhijian Laboratory, Rocket Force University of Engineering,,)

School of Mechanical and Power Engineering, Shanghai Jiao Tong University

⁰