Data-driven IMA degradation modeling and health assessment

被引：0

作者：

Fan J. ^{[1
]}

Chen J. ^{[1
]}

Guo Y. ^{[1
]}

Xue X. ^{[1
]}

Liu Z. ^{[2
]}

机构：

[1] Northwestern Polytechnical University, Xi’an

[2] Xi‘an Aerospace Propulsion Institute, Xi’an

来源：

Aerospace Systems | 2023年 / 6卷 / 01期

基金：

中国国家自然科学基金;

关键词：

Data preprocessing; Health assessment; Integrated modular avionics; Long Short-Term Memory; Random forest;

D O I：

10.1007/s42401-022-00170-w

中图分类号：

学科分类号：

摘要：

With the improvement of aircraft informatization, integrated modular avionics (IMA) system has become an important part of modern aircraft airborne systems, and its operation status has great significance to ensure flight safety; therefore, it is necessary to study its degradation process and health assessment. To preprocess the original data obtained in the actual engineering environment, the Lagrange interpolation and Pauta criterion are used to make up the missing data and remove the abnormal data, random forest algorithm is adopted to reduce the redundant data, and the representative IMA data are screen out finally. And then, based on the IMA system analysis and health state classification, the Long Short-Term Memory (LSTM) network is introduced in this paper to model the IMA system’s degradation process and assess system health status, and the effectiveness of the proposed method for degradation modeling and health assessment is verified by the experimental simulation in the end. © 2022, Shanghai Jiao Tong University.

引用

页码：15 / 23

页数：8

共 16 条

[1]

Wolfig R., A distributed platform for integrated modular avionics, (2015)

[2]

Tuan H.D., Nam Q.H., Nghia M.D., Research on building of power characteristics of the main diesel engines under pressure in high-pressure pipelines and end-of-stroke compression pressure by Lagrange interpolation, International Conference on System Science and Engineering (ICSSE). IEEE, pp. 23-26, (2021)

[3]

Xu C.H., Ma M.H., Optimization method for gross error processing of traffic data based on Pauta criterion, J Shanghai Univ Eng Sci, 32, 1, pp. 64-67, (2018)

[4]

Ishwaran H., Kogalur U.B., Gorodeski E.Z., Et al., High-dimensional variable selection for survival data, J Am Stat Assoc, 105, 489, pp. 205-217, (2010)

[5]

Svetnik V., Liaw A., Tong C., Et al., Application of Breiman’s random forest to modeling structure-activity relationships of pharmaceutical molecules. International workshop on multiple Classifier systems, pp. 334-343, (2004)

[6]

Athey S., Wager S., Tibshirani J., Generalized random forests, Ann Stat, 47, 2, pp. 1148-1178, (2019)

[7]

Huang L., Liu J., Gong Y., Multi-phase residual life prediction of engines based on Wiener process, J Beijing Univ Aeronaut Astronaut, 44, 5, pp. 1081-1087, (2018)

[8]

Chen J., Shen C., Jing Z., Et al., Remaining useful life prediction of aircraft flap control system with mode transition, AIAA J, 60, 2, pp. 1104-1115, (2022)

[9]

Fang S., Gou B., Wang Y., Et al., Optimal hierarchical management of shipboard multibattery energy storage system using a data-driven degradation model, IEEE Trans Transport Electrific, 5, 4, pp. 1306-1318, (2019)

[10]

Chen J., Zhao Y., Xue X., Et al., Data-Driven Health Assessment in a Flight Control System under Uncertain Conditions, Appl Sci, 11, 21, (2021)

← 1 2 →