Aerodynamic Optimization Design of Compressor Cascade Based on Parallel Multi-Objective Genetic Algorithm and Artificial Neural Network

Abstract:

Genetic algorithm (GA) is improved with fast non-dominated sort approach and crowded comparison operator. A new algorithm called parallel multi-objective genetic algorithm (PMGA) is developed with the support of Massage Passing Interface (MPI). Then, PMGA is combined with Artificial Neural Network (ANN) to improve the optimization efficiency. Training samples of the ANN are evaluated based on the two-dimensional Navier-Stokes equation solver of cascade. To demonstrate the feasibility of the hybrid algorithm, an optimization of a controllable diffusion cascade is performed. The optimization results show that the present method is efficient and trustiness.

• Periodical: Applied Mechanics and Materials (Volumes 138-139)
• Pages: 534-539
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.138-139.534
• Online since: November 2011
• Authors: Li Hai Chen, Qing Zhen Yang, Jin Hui Cui
• Keywords: Aerodynamic Optimization Design, Artificial Neural Network (ANN), Cascade, Compressor, Multi-Objective Genetic Algorithm (MGA)

References

[1] WangWeng-uang, Zhou Zheng-gui, Hu Jun. Automatic optimization design of compressor blade based on parallel genetic algorithm[J]. Aviation power transaction, 2006, 21(5): 924-929.

[2] Kalyanmoy Deb, Amrit Pratap, Sameer Agarwal, and T. Meyarivan A Fast and Elitist Multiobjective Genetic Algorithm: NSGA-II[J]. IEEE Transactions on Evolutionary Computation. 2002 6(2): 182~197.

DOI: 10.1109/4235.996017

[3] Du Zhi-hui, Parallel Programming Technology of high performance computation-Parallel program design of MPI[M]. BeiJing: Tsinghua University press. (2001).

[4] LI Song-bin. A Multiple-population Parallel Genetic Algorithm Based on Platform MPICH[J]. Journal of XiaMen University(Natural Science). 2006, 45（5）：646~651.

[5] Petty CC, Lenze M R. A Theorerical Investion of A Parallel Genetic Algorithm[C]. In: Proc. of 3rd Int. Conf, on Genetic Algorithms, Morgan Kaufmann，1989：398～405.

[6] LiuYong etc. Non-numerical Parallel Algirithm[M]. BeiJing: Electronic Industry Publishing Company, (2003).

[7] GuoJia, Wang Rui-min. The Learning Method of Neural Network Based on Genetic Algorithm[J]. Computer and Numeric Control. 2003, 32(5): 98-101.

[8] Fang Kai-tai, Wang Yuan. uniform design and uniform design table. BeiJing: China Sciences Press, (1994).

[9] Fei Qi, Liu Jing-xue. A Multi-attribute Decision Making Method Based on Fuzzy Preference Information[J]. Journal of Wuhan University of Technology. 2006, 28(9): 132-135.

[10] Qi Zhao-hui, Zhang wei-hua, Fan yu-zhu. A New Algorithm of Weight Coefficients of Multiple Attribute Decision Making[J]. Operations Research and Management Science. 2006, 15(3): 36-40.