Aviation Equipment Maintenance Support System Based on KELM Effectiveness Evaluation

被引：0

作者：

Bai, Yu ^{[1
,2
]}

Liu, Xing ^{[1
,3
]}

Zhou, Lijian ^{[4
]}

Zhang, Jinpo ^{[3
]}

机构：

[1] Naval Aviat Univ, Yantai, Peoples R China

[2] PLA, Unit 61035, Beijing, Peoples R China

[3] PLA, Unit 91967, Xingtai, Peoples R China

[4] PLA, Unit 92635, Qingdao, Peoples R China

来源：

PROCEEDINGS OF 2021 2ND INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND INFORMATION SYSTEMS (ICAIIS '21) | 2021年

关键词：

Extreme learning machine; kernel function; Maintenance support; Effectiveness evaluation; FAULT-DIAGNOSIS; VECTOR MACHINES;

D O I：

10.1145/3469213.3470300

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Maintenance support work is an important link in maintaining and improving the combat effectiveness of aviation equipment, and is an important link in the comprehensive equipment support system. Accurate measurement and evaluation can provide a strong theoretical basis for the next maintenance system reform. This paper draws on the successful evaluation index system of aviation equipment maintenance support abroad, and establishes an index system suitable for the characteristics of our army. And using the nuclear over-limit learning machine as the modeling framework, an effectiveness evaluation model based on KELM is proposed. Simulation experiments show that under small sample conditions, the model can quickly learn evaluation indicators, and the variance between the output evaluation value and the true value is small, and it has good function approximation performance and generalization ability, which is a guarantee for aviation equipment maintenance Provide reference for system effectiveness evaluation.

引用

页数：5

共 14 条

[1] System-level operational diagnosability analysis in quasi real-time fault diagnosis: The probabilistic approach [J].

Cui, Yiqian ;

Shi, Junyou ;

Wang, Zili .

JOURNAL OF PROCESS CONTROL, 2014, 24 (09) :1444-1453

[2]

Gao ZW, 2015, IEEE T IND ELECTRON, V62, P3768, DOI [10.1109/TIE.2015.2417501, 10.1109/TIE.2015.2419013]

[3] Fault diagnosis of analog circuit based on a second map SVDD [J].

Jiang, Yuanyuan ;

Wang, Youren ;

Luo, Hui .

ANALOG INTEGRATED CIRCUITS AND SIGNAL PROCESSING, 2015, 85 (03) :395-404

[4] Double-model adaptive fault detection and diagnosis applied to real flight data [J].

Lu, Peng ;

Van Eykeren, Laurens ;

van Kampen, Erik-Jan ;

de Visser, Coen ;

Chu, Qiping .

CONTROL ENGINEERING PRACTICE, 2015, 36 :39-57

[5] A SVDD approach of fuzzy classification for analog circuit fault diagnosis with FWT as preprocessor [J].

Luo, Hui ;

Wang, Youren ;

Cui, Jiang .

EXPERT SYSTEMS WITH APPLICATIONS, 2011, 38 (08) :10554-10561

[6] Incipient fault diagnosis using support vector machines based on monitoring continuous decision functions [J].

Namdari, Mehdi ;

Jazayeri-Rad, Hooshang .

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2014, 28 :22-35

[7]

Ni J, 2010, J MANUF SCI E-T ASME, V132, P237

[8]

Smart E, 2013, IEEE SYMP INDUST EL, P132, DOI 10.1109/ISIEA.2013.6738982

[9] Prognostics of the Motor Coupling Based on the LS-SVM Regression using Features in Time Domain [J].

Susilo, Didik Djoko ;

Widodo, Achmad ;

Prahasto, Toni ;

Nizam, Muhammad .

4TH INTERNATIONAL CONFERENCE ON INDUSTRIAL, MECHANICAL, ELECTRICAL, AND CHEMICAL ENGINEERING, 2019, 2097

[10] Fault diagnosis and prognosis of wastewater processes with incomplete data by the auto-associative neural networks and ARMA model [J].

Xiao, Hongjun ;

Huang, Daoping ;

Pan, Yongping ;

Liu, Yiqi ;

Song, Kang .

CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS, 2017, 161 :96-107

← 1 2 →