Risk identification of civil aviation engine control system based on particle swarm optimization-mean impact value-support vector machine

Abstract

The actual risk of the engine control system in operation is often higher than expected risk level, which brings hidden dangers to the safe operation of aircraft. Therefore, a PSO-MIV-SVM (particle swarm optimization-mean impact value-support vector machine) model is proposed to identify the risk of engine control system. Firstly, seven characteristic variables are extracted through the analysis of engine unsafe information, and 810 typical engine event samples were selected and normalized. Secondly, the SVM-based engine control system risk identification model is established and optimal kernel function of the SVM model is selected. Thirdly, the SVM-MIV method is used to sort the importance of the seven characteristic variables, and the identification accuracies of different characteristic variable groups are calculated to obtain the optimal combination of characteristic variables. Finally, the parameters of the SVM model are optimized by using the PSO algorithm and the accuracy of the PSO-MIV-SVM model for the risk identification of the engine control system reaches 93.58%.

Keywords

risk identification civil engine control system support vector machine particle swarm optimization particle swarm optimization-mean impact value-support vector machine

Get full access to this article

View all access options for this article.

References

Decision. NO/1/RM . AMC and GM to Part 21. European: The European Authority for aviation safety, 2003.

Advisory Circular . AC-39-8, Continued Airworthiness Assessment of Powerplant and Auxiliary Power Unit Installations of Transport Category Airplanes. Washington, DC: Federal Aviation Administration, 2014.

Airworthiness Handbook. PS-ANM-25-05, Transport Airplane Risk Assessment Methodology Handbook. Washington, DC: Federal Aviation Administration, 2011.

Violette

Safarian

Han

, et al. Transport Airplane Risk Analysis. J Aircraft 2015; 52(2): 395–402.

Guo

Sun

. Failure Risk Assessment Method of Civil Aircraft Based on Monto Carlo Method. Acta Aeronautica ET Astronautica Sinica 2017; 10: 155–163.

Report. DOT/FAA/TC-17/6, Analysis of Three Approaches for Estimation of Uncorrected Fleet Risk Due to Wear-out Failures. Washington, DC: Federal Aviation Administration, 2018.

SAE International Group . ARP5107B, Guidelines for time-limited-dispatch(TLD) analysis for electronic engine control systems. Washington, DC: Society of Automotive Engineer, 2006.

Rong

Zhou

. Multi-fault TLD analysis method of FADEC system based on Monte Carlo simulation. Acta Aeronautica ET Astronautica Sinica 2015; 36(12): 3970–3979.

Zhang

. Research on Safety Analysis and Assessment Techniques for Digital Control System of Civil Turbofan EngineMaster's thesis. Nanjing University of Aeronautics and Astronautics, 2012.

10.

Cai

. Accuracy analysis of a single-fault Markov model for FADEC system. J Syst Eng Electronics 2019; 30(5): 1044–1052.

11.

Aircraft Certification Service . Order 8110.107A, Monitor safety/analyze data. Washington, DC: Federal Aviation Administration, 2012.

12.

García Nieto

García-Gonzalo

Sánchez Lasheras

, et al. Hybrid PSO-SVM-based method for forecasting of the remaining useful life for aircraft engines and evaluation of its reliability. Reliability Eng Syst Saf 2015; 138: 219–231.

13.

Jiang

Xue

, et al. IEEE Control and Decision Conference. Qingdao, ChinaPiscataway, NJ: IEEE, 2015, pp. 4625–4630. 23-25 May 2015.Research recognition of aircraft engine abnormal state

14.

LiQiu

Shi

Nian

, et al. Research on Pattern Recognition of Gas Explosion Disaster Risk in Coal Mines Based on PSO-SVM. China Saf Sci J 2013; 23(5): 38–43.

15.

Tharwat

Hassanien

Elnaghi

. A BA-based algorithm for parameter optimization of support vector machine. Pattern Recognition Lett 2017; 93: 13–22.

16.

Sun

Liu

Wang

, et al. Weight analysis of cast blasting effective factors based on MIV method. J China Univ Mining Technology 2012; 41(06): 993–998.

17.

Angeline

. Using selection to improve particle swarm optimization. IEEE International Conference on Evolutionary Computation Proceedings, IEEE World Congress on Computational Intelligenc 1998. Piscataway, NJ: IEEE, 1998, pp. 84–89.

18.

Zhou

Zhuang

Zuo

, et al. Deep Learning-Based Approach for Civil Aircraft Hazard Identification and Prediction. IEEE Access 2020; 8: 103665–103683.

19.

Qiao

. Enterprise financial risk early warning method based on hybrid PSO-SVM model. J Appl Sci Eng 2019; 2(1): 71–178.

20.

Zhou

Zhuang

Zuo

, et al. Hazard identification and prediction system for aircraft electrical system based on SRA and SVM. Proc Inst Mech Eng G: J Aerospace Eng 2020; 234(4): 1014–1026.