The recognition of supersonic inlet flow pattern has become a research hotspot in recent years. In this paper, the dual external pressure supersonic inlet is taken as the research object. To explore the flow characteristics of the inlet, time-mean processing on the inlet pressure signal collected by sensors is conducted first, and the features of the inlet pressure data in time domain and frequency domain are extracted, respectively. As feature selection (FS) plays an important role in classification tasks and has been recently studied as a multi-objective optimization problem, two objectives of FS are considered and an improved non-dominated sorting genetic algorithm NSGA2 with hybrid mutation operators using support vector machines (SVM) as classifiers is proposed, aiming to simultaneously select feature subsets and optimize SVMs hyper-parameters. In addition, a way to deal with variation transgression is proposed to make the mutation operator of the single-objective evolution fit well in the multi-objective evolution algorithm. Experimental results on 31 sensor datasets demonstrate that our proposed algorithm can achieve competitive classification accuracy while obtaining a smaller size of feature subset compared with particle swarm optimization algorithm and some multi-objective optimization algorithms using single-objective evolution mutation operators.
HankJMurphyJMutzmanR. The X-51A Scramjet Engine Flight Demonstration Program. In: 15th AIAA International Space Planes and Hypersonic Systems and Technologies Conference, Dayton, OH, 28 April–01 May 2008.
2.
CurranE. T.MurthyS.Scramjet propulsion, progress in astronautics and aeronautics. Lawrence, KS: ARC, 2000.
3.
HypersonicAMcclintonCRHuntJL, et al.Airbreathing hypersonic technology vision vehicles and development dreams. Aiaa Paper, 2000.
4.
LijoV.KimH. D.MatsuoS., et al. A study of the supersonic ejector–diffuser system with an inlet orifice. Aerospace Sci Technology2012; 23(1): 321–329.
5.
NanL.ChangJJiangC, et al.Unstart/restart hysteresis characteristics analysis of an over-under TBCC inlet caused by backpressure and splitter. Aerospace Sci Technology2017; 72: 418–425.
6.
RostamiMBerahmandKNasiriE, et al.Review of swarm intelligence-based feature selection methods. Eng Appl Artif Intelligence2021; 100(1): 104210.
7.
JohnGHKohaviRPflegerK. Irrelevant Features and the Subset Selection Problem. Burlington, MA: Morgan Kaufmann Publishers Inc., 1994, pp. 121–129.
8.
WhitneyAW. A direct method of nonparametric measurement selection. IEEE Trans Comput1971; C-20(9): 1100–1103.
9.
MarillTGreenD. On the effectiveness of receptors in recognition systems. IEEE Trans Inf Theor2006; 9(1): 11–17.
10.
NarendraPMFukunagaK. A branch and bound algorithm for feature subset selection. IEEE Trans Comput1977; 26: 917–922.
11.
EngelbrechtAPGroblerJLangeveldJ. Set based particle swarm optimization for the feature selection problem. Eng Appl Artif Intelligence2019; 85: 324–336.
12.
HancerE. A new multi-objective differential evolution approach for simultaneous clustering and feature selection. Eng Appl Artif Intelligence2020; 87: 103307.
13.
ChatterjeeSBhattacherjeeA. Genetic algorithms for feature selection of image analysis-based quality monitoring model: An application to an iron mine. Eng Appl Artif Intelligence2011; 24(5): 786–795.
14.
TranB.ZhangM.BingX.A PSO based hybrid feature selection algorithm for high-dimensional classification. In: IEEE Congress on Evolutionary Computation (CEC), Vancouver, Canada, 24–29 July 2016.
15.
YongZGongDWJianC. Multi-objective particle swarm optimization approach for cost-based feature selection in classification. IEEE/ACM Trans Comput Biol Bioinformatics2017; 14(1): 64–75.
16.
KhushabaRNAl-AniAAl-JumailyA. Feature subset selection using differential evolution and a statistical repair mechanism - ScienceDirect. Expert Syst Appl2011; 38(9): 11515–11526.
17.
KiraKRendellLA. The feature selection problem: traditional methods and a new algorithm. In: Tenth National Conference on Artificial Intelligence, San Jose, CA, 12–16 July 1992.
18.
PengHLongFDingC. Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy. IEEE Trans Pattern Anal Machine Intell2005; 27(8): 1226–1238.
19.
JainAKDuinPWMaoJ. Statistical pattern recognition: a review. IEEE Trans Pattern Anal Machine Intell2000; 22: 4–37.
20.
XueXYaoMWuZ. A novel ensemble-based wrapper method for feature selection using extreme learning machine and genetic algorithm. Knowledge & Information Systems2017; 57: 389–412.
21.
PehlivanogluYV. Efficient accelerators for PSO in an inverse design of multi-element airfoils. Aerospace Sci Technol2019; 91: 110–121.
22.
YingyingZJunweiLJianyongC, et al.An improved NSGA-III algorithm for feature selection used in intrusion detection. Knowledge-Based Systems2017; 116: 74–85.
23.
SevincE.A Novel Evolutionary Algorithm for Data Classification Problem with Extreme Learning Machines. IEEE Access2019; 99: 1–1.
24.
ZaretalabAHajipourVSharifiM, et al.A knowledge-based archive multi-objective simulated annealing algorithm to optimize series–parallel system with choice of redundancy strategies. Comput Ind Eng2015; 80: 33–44.
25.
DebKPratapAAgarwalS, et al.A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Trans Evol Computat2002; 6(2): 182–197.
26.
SoyelHTekgucUDemirelH. Application of NSGA-II to feature selection for facial expression recognition. Comput Electr Eng2011; 37(6): 1232–1240.
27.
BrintrupA. Behaviour adaptation in the multi-agent, multi-objective and multi-role supply chain - ScienceDirect. Comput Industry2010; 61(7): 636–645.
28.
SiedleckiWSklanskyJ. A note on genetic algorithms for large-scale feature selection. Pattern Recognition Lett1989; 10(5): 335–347.
29.
OhI-SLeeJ-SMoonB-R. Hybrid genetic algorithms for feature selection. IEEE Trans Pattern Anal Mach Intell2004; 26: 1424–1437.
30.
BouraouiAJamoussiSBenayedY. A multi-objective genetic algorithm for simultaneous model and feature selection for support vector machines. Artif Intell Rev2017; 50: 261–281.
31.
LaumannsMRudolphGSchwefelHP. Mutation control and convergence in evolutionary multi-object optimization. Dortmund, Germany: Universität Dortmund, 2001.
32.
KapplerC. Are evolutionary algorithms improved by large mutations? In: Parallel Problem Solving from Nature - PPSN IV, International Conference on Evolutionary Computation. The 4th International Conference on Parallel Problem Solving from Nature, Berlin, Germany, 22–26 September1996.
33.
TanKCGohCKYangYJ, et al.Evolving better population distribution and exploration in evolutionary multi-objective optimization. Eur J Oper Res2006; 171(2): 463–495.
34.
BasseurMSeynhaeveFTalbiEG. Design of multi-objective evolutionary algorithms: application to the flow-shop scheduling problem. In: Proceedings of the 2002 Congress on Evolutionary Computation, 2002CEC ‘02, Honolulu, HI, 12–17 May 2002.
35.
HerrmannDSiebeFGülhanA. Pressure fluctuations (Buzzing) and inlet performance of an airbreathing missile. J Propulsion Power2013; 29(4): 839–848.
36.
HeK.ZhangX.RenS., et al. Deep Residual Learning for Image Recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, 27–30 June 2016.
37.
KizilozHE. Classifier ensemble methods in feature selection. Neurocomputing2020; 419: 97–107.
38.
LeiY.Signal processing and feature extraction - ScienceDirect. Intelligent fault diagnosis remaining useful life prediction of rotating machinery. Netherlands: Elsevier, 2017, pp. 17–66.
39.
JunweiLAiminCBo-YangZ, et al.Multiobjective evolutionary algorithms: a survey of the state of the art. Swarm Evol Comput2011; 1(1): 32–49.
