An estimation method for direct maintenance cost of aircraft components based on particle swarm optimization with immunity algorithm

Abstract

A particle swarm optimization (PSO) algorithm improved by immunity algorithm (IA) was presented. Memory and self-regulation mechanisms of IA were used to avoid PSO plunging into local optima. Vaccination and immune selection mechanisms were used to prevent the undulate phenomenon during the evolutionary process. The algorithm was introduced through an application in the direct maintenance cost (DMC) estimation of aircraft components. Experiments results show that the algorithm can compute simply and run quickly. It resolves the combinatorial optimization problem of component DMC estimation with simple and available parameters. And it has higher accuracy than individual methods, such as PLS, BP and v-SVM, and also has better performance than other combined methods, such as basic PSO and BP neural network.

Keywords

aircraft design / maintenance cost / particle swarm optimization / immunity algorithm / predict

References

[1] ChenJu-hua, ZhangLi-li, ZhangHong-cai. The study on the whole-life design of complex electromechanical system [J]. Journal of Jiamusi University (Natural Science Edition), 2004, 22(4): 459-464(in Chinese)

[2] HayesS. Reduced maintenance costs for the 737-600/-700/-800/-900 family of airplanes [J]. AERO Magazine, 2001, 3: 25-31

[3] AFAM. Understanding maintenance costs for new and existing aircraft [J]. Airline Fleet & Asset Management, 2001, 5: 56-62

[4] PoubeauJDirect maintenance costs-art or science? [R], 1989, France, Airbus Industric

[5] CutlerRMaintenance Engineering [R], 2003, Blagnac Cedex, France, Airbus Industric

[6] ThomasA MAnalysis of F/A-18 engine maintenance costs using the Boeing dependability cost model[R], 1994, Montcroy CA, Naval Postgraduate School

[7] EberhartR C, ShiY HKimJ H. Particle swarm optimization: developments, applications and resources [A]. Proc of the IEEE Congress on Evolutionary Computation 2001 (CEC’ 01) [C], 2001, Korea, IEEE Press: 81-86

[8] FukuyamaYLeeK Y, El-SharkawiM A. Fundamentals of particle swarm techniques [A]. Modern Heuristic Optimization Techniques with Applications to Power Systems [C], 2002, NJ, IEEE Press: 45-51

[9] de CastroL N, TimmisJArtificial Immune Systems: A New Computational Intelligence Approach [M], 2002, London, Springer

[10] BatesJ M, GrangerC W J. Combination Forecasts [J]. Operations Research Quarterly, 1969, 20(4): 451-468

[11] KennedyJ, EberhartR C. Particle swarm optimization [A]. Proceedings of IEEE International Conference on Neural Networks [C], 1995, Perth, IEEE Press: 1942-1948

[12] TreleaI C. The particle swarm optimization algorithm: Convergence analysis and parameter selection [J]. Information Processing Letters, 2003, 85: 317-325

[13] van den BerghFAnalysis of particle swarm optimizers [D], 2002, South Africa, Department of Computer Science, University of Pretoria

[14] ClercM. The swarm and the queen: towards a deterministic and adaptive particle swarm optimization [A]. Evolutionary Programming Society, Institution of Electrical Engineers. Proc of the IEEE Congress on Evolutionary Computation 1999 (CEC’ 99) [C], 1999, Washington DC, IEEE Press: 1951-1957

[15] LuGang, TanDe-jian, et al.WangLi-po, RajapakseJ C, FukushimaK, et al.. Improvement on regulating definition of antibody density of immune algorithm [A]. Proceedings of the 9th International Conference on Neural Information Processing (ICONIP’ 02) [C], 2002, Singapore, Nanyang Technological University: 2669-2672

[16] ZhangJiang-she, XuZong-ben, LiangYi. The whole annealing genetic algorithms and their sufficient and necessary conditions of convergence [J]. Science in China (Series E), 1997, 27(2): 154-164(in Chinese)