混合神经网络匹配响应面的多学科设计方法

doi:10.3969/j.issn.1001-2400.2012.05.027

Abstract

Abstract:

In order to improve the solving performance of Multi-disciplinary design optimization (MDO), a multi-disciplinary design method for the matched response surface based on the hybrid neural network is proposed. By combining the advantages of the back-propagation (BP) network with the adaptive resonance theory (ART) network and making full use of the target results sample through discipline-level optimization to adaptively change the traditional response surface structure, the proposed method improves the accuracy of the response surface and reduces the number of times of iteration of the discipline-level optimization, which leads to a better solving efficiency for the multi-disciplinary optimization methods. The optimization method is validated by a specific example. Comparison studies in terms of solving accuracy, discipline optimization times, average number of times of iteration and iterative occupancy hours of obtaining the optimization solution indicate that the method for the multi-disciplinary design of the matched response surface based on the hybrid neural network has a few advantages such as higher solution accuracy and higher computational efficiency.

Key words: back-propagation network, adaptive resonance theory network, multi-disciplinary design, response surface

CLC Number:

TP301

LIU Daohua;WANG Shuli;XUE Rui. Multi-disciplinary design method for the matched response surface based on the hybrid neural network[J].J4, 2012, 39(5): 161-167.

References

［1］ Tosserams S, Etman L F P, Rooda J E. A Micro-accelerometer MDO Benchmark Problem［J］. Structural and Multidisciplinary Optimization, 2010, 41(2): 255-275.
［2］王义民, 高军波. 论人地关系研究学科之间的辩诘与融合［J］. 信阳师范学院学报, 2011, 24(2): 1-4.
Wang Yimin, Gao Junbo. On the Debate and Fusion Among the Disciplines of Human-environment Relationship Research［J］. Journal of Xinyang Normal University, 2011, 24(2): 1-4.
［3］陈建江, 孙建勋, 常伯浚, 等. 基于人工神经网络的多学科优化设计研究［J］. 计算机集成制造系统, 2005, 11(10): 1351-1356.
Chen Jianjiang, Sun Jianxun, Chang Bojun, et al. Multidisciplinary Design Optimization Based on Artificial Neural Network［J］. Computer Integrated Manufacturing System, 2005, 11(10): 1351-1356.
［4］邢小楠, 徐元铭, 李烁, 等. 神经网络响应面逼近在飞机总体优化设计中的应用［J］. 机械设计与研究, 2004, 20(1): 68-71.
Xing Xiaonan, Xu Yuanming, Li Suo, et al. Application of the Neural Network Response Surface to Aircraft Preliminary Optimization Design［J］. Machine Design and Research, 2004, 20(1): 68-71.
［5］何麟书, 王书河, 张玉珠. 飞行器多学科综合设计新算法［J］. 航空学报, 2004, 25(5): 465-469.
He Linshu, Wang Shuhe, Zhang Yuzhu. The New Algorithm for Aircraft Multidisciplinary Integrated Design［J］. Acta Aeronautica et Astronautica Sinica, 2004, 25(5): 465-469.
［6］ Liu Jun, Yi Hong. Re-analysis of MDO for CGX Example［J］. Journal of Ship Mechanics, 2009,13(6): 895-904.
［7］唐璐, 黄俊, 武哲. 基于神经网络的协作优化方法在飞机总体设计中的应用［J］. 飞机设计, 2009, 29(2): 1-7.
Tang Lu, Huang Jun, Wu Zhe. Application of Collaborative Optimization Based on Neural Network to Aircraft Preliminary Design［J］. Aircraft Design, 2009, 29(2): 1-7.
［8］张梅, 潘大仁, 周以飞, 等. BP神经网络结合正交试验法优选锦锈杜鹃黄酮的提取工艺［J］. 信阳师范学院学报, 2011, 24(2): 261-264.
Zhang Mei, Pan Daren, Zhou Yifei, et al. Optimization of Extraction Process of Flavonoids in Rhododendron Pulchrum Sweet Based on Artifical Neural Network Combined with Orthogonal Experiment［J］. Journal of Xinyang Normal University, 2011, 24(2): 261-264.
［9］邵军虎, 白宝明, 林伟, 等. 多元量子LDPC码的构造与译码［J］. 西安电子科技大学学报, 2010, 37(6): 1005-1010.
Shao Junhu, Bai Baoming, Lin Wei, et al. Construction and Decoding of Nonbinary Quantum LDPC Codes ［J］. Journal of Xidian University, 2010, 37(6): 1005-1010.
［10］徐玮. 一种基于复形调优遗传算法的多学科优化方法［J］. 系统工程与电子技术, 2010, 32(4): 869-872.
Xu Wei. Multidisciplinary Optimization Method Based on Complex Optimization Genetic Algorithm［J］. System Engineering and Electronics, 2010, 32(4): 869-872.
［11］ Liu Bo, Wang Ling, Jin Yihui, et al. Directing Orbits of Chaotic Systems by Particle Swarm Optimization ［J］. Chaos, Solitons ＆ Fractals, 2006, 29(2): 454-461.
［12］ Hulme K F, Bloebaum C L. A Comparison of Solution Strategies for Simulation-based Multidisciplinary Design Optimization［C］//Symposium on Multidisciplinary Analysis and Optimization. St Louis: AIAA, 1998: 1-11.

[1]	JIN Hongling;GUO Chengyang;CHEN Jun;CHEN Jianjun. Dynamic reliability analysis of spacial flexible beam [J]. Journal of Xidian University, 2017, 44(6): 138-143.
[2]	ZHAO Kuan;CHEN Jianjun;CAO Hongjun;YUN Yonghu. Motion function reliability analysis of a rotating flexible beam with random parameters [J]. J4, 2013, 40(5): 141-147.
[3]	YOU Hai-long;JIA Xin-zhang. IC robust optimization design using RSM [J]. J4, 2009, 36(3): 458-462.

Multi-disciplinary design method for the matched response surface based on the hybrid neural network

PDF (PC)

Like

Knowledge

Cited

Abstract

Cite this article

share this article

References

Related Articles 3

Metrics

Comments

Recommended 0