基于多方法集成的复杂工艺优化设计研究

• 论文 •

基于多方法集成的复杂工艺优化设计研究

蒋伟进，许宇胜

1.湖南工业大学计算机学院,湖南株洲 412008;2.中国地质大学计算机学院，湖北武汉 430074；3.北京工业大学机械与电子工程学院,北京 100022

收稿日期:2005-04-24 修回日期:2005-09-08 出版日期:2006-04-15 发布日期:2006-04-25
基金资助:
国家自然科学基金资助项目（60473037）；中国包装总公司技术创新资助项目（05ZBKJA011）；湖南省自然科学基金资助项目（04JJ3052）。

Research on optimal design of complex process based on multi-method integration

JIANG Wei-jin，XU Yu-sheng

1.Sch. of Computer Sci., Hunan Univ. of Industry, Zhuzhou 412008, China;2.Sch.of Computer Sci.,China Univ. of Geosciences,Wuhan 430074，China;3.Sch. of Mechanical Eng. & Applied Electronics, Beijing Univ. of Tech., Beijing 100022, China

Received:2005-04-24 Revised:2005-09-08 Online:2006-04-15 Published:2006-04-25
Supported by:
Project supported by the National Science Foundation,China(No.60473037)，the Plan of New Technology Projects in China National Packaging Corporation 2005,China(No.05ZBKJA011)and the National Science Foundation of Hunan Province,China(No.04JJ3052).

摘要/Abstract

摘要： 针对流程工业复杂的连续生产工艺的特点，提出了基于模式识别、神经网络、遗传算法、非线性回归等多种智能技术集成的复杂工艺过程优化系统的设计思想、体系结构、关键技术和实现方法，主要解决多因子、高噪声、非线性、非高斯分布和非均匀的复杂工艺系统难题。采用代理技术设计系统的体系结构，用偏最小二乘法和Chelyshev多项式建立领域模型，通过演化计算进行最优问题求解，并用正交实验取得模型学习的样本数。实际应用证明，利用这些方法可以在很少的实验情况下，使所建立的模型能在较大误差范围内指导生产实践。

关键词: 复杂工艺过程, 动态建模, 偏最小二乘法

Abstract: Aiming at characteristics of complex production process in process industries, an intelligent software system on optimal formula of production processing with multivariate factors based on pattern recognition, artificial neural network, genetic algorithm and nonlinear regression methods was introduced. Design philosophy, architecture, key technologies and implementation methods of the proposed system were narrated. The proposed system was designed to solve problems on multi-factor ,high noise, nonlinear, non-Gaussian distribution and non-uniform distribution in optimal industrial complicated craft process.　The architecture of the system was designed by using agent technology, and the domain model was constructed by the least square method and Chebyshev polynomial. Then the optimal solution of model was solved by the evolution algorithm, and learning sample data was gained by the orthogonal test.　Applications indicated that these methods could provide guidelines for the industrial production with allowable error even though a few experiments were made.

Key words: complex process, dynamic modeling, partial lest square method, multi-agent system

中图分类号:

蒋伟进，,许宇胜. 基于多方法集成的复杂工艺优化设计研究[J]. .

JIANG Wei-jin,，XU Yu-sheng. Research on optimal design of complex process based on multi-method integration[J]. .

参考文献

［1］ XIE Shengli,HUANG Qiang,LIN Lanfen,et al.Case-based intelligent process planning system［J］.Research on Computer Application,2002,22(9):97-103.

[2] YANG Zhigang,MA Ziqin,LIU Chengying,et al.Process plan cases retrieval approach based on part characteristic list and key machine tools［J］.Computer Integrated Manufacturing Systems,2003,9(7):556-560(in Chinese).［杨志刚，马自勤，刘成颖，等.基于零件特性表和关键机床的工艺实例检索［J］.计算机集成制造系统，2003，9(7)：556-560.］

[3] MARIFAT M,BRITANIK J.Case-based process planning with hierarchical process merging［J］.IEEE International Conference on Humans,Information and Technology,1994,1(2):165-170.

[4] LIU Xiaobing,LIU Caiyan,MA Yue,et al.Research on process planning system based on HCBR for hybrid production industries［J］.Computer Integrated Manufacturing Systems,2005,11(7):941-946(in Chinese).［刘晓冰，刘彩燕，马跃，等.基于分层实例推理的混合型行业工艺设计系统研究［J］.计算机集成制造系统，2005，11(7)：941-946.］

[5] JIANG Weijin.Research on ceramic materials control mold and its arithmetic based on neural network［A］.Proceedings of the 6th European Conference on Information Systems［C］.Cork,Ireland:Addison-Wesley Press，2003.89-93.

[6] JIANG Weijin,XU Yuhui,XU Yusheng.Optimization of injection parameters based on hybrid neural network and genetic algorithm［A］.Proceedings of the 2005 National Joint Conference on Fuzzy Logic and Computational Intelligence［C］.Shenzhen,China:Shenzhen University Press,2005.241-246.

[7] SADIQ S,SADIQ W,ORLOWSKA M.Pockets of flexibility in workflow specifications［A］.Proceedings of the 20th International Conference on Conceptual Modeling［C］.Yokohama,Japan:2001.43-46.

[8] HEINL P,HORN S,JABLONSKIS,et al.A comprehensive approach to flexibility in workflow management systems［A］.Proceedings of the International Joint Conference on Work Activities Coordination and Collaboration［C］.San Francisco,CA,USA:IEEE Concurrency,1999.79-89.

[9] JIANG Weijin.Research on diagnosis model distributed intelligence and key technique based on MAS［J］.Control Theory and Applications,2004,28(5):82-88(in Chinese).［蒋伟进.基于MAS的分布式智能诊断方法与应用研究［J］.控制理论与应用,2004,28(5):82-88.］

[10] JIANG Weijin.Research on key technologies of virtual enterprise and dynamic modeling based on MA & BP［J］.Information and Control,2002，31(4):329-335(in Chinese).［蒋伟进.基于MA和BP的虚拟企业动态建模及关键技术研究［J］.信息与控制,2002,31(4):329-335.］

[11] JIANG Weijin.Research and implementation of distributed MSP algorithm based on GA & MAS［J］.Computer Science,2002,29(9):443-447(in Chinese).［蒋伟进.基于GA和MAS的分布式任务调度算法研究与实现［J］.计算机科学，2002,29(9):443-447.］

[12] JIANG Weijin.Research on the optimization of the equipment funds assignment model based on HGA［J］.Journal of the Control and Instruments in Chemical Industry,2004,31(2):10-14(in Chinese).［蒋伟进.基于HGA的经费分配多目标优化模型求解［J］.化工自动化及仪表,2004,31(2):10-14.］

[1]	郭银章，曾建潮. 基于元模型调用的机械产品协同设计过程建模[J]. , 2011, 17(05): 0-0.
[2]	郭银章，曾建潮. 基于元模型调用的机械产品协同设计过程建模[J]. , 2011, 17(05): 0-0.
[3]	赵良才，景旭文. 产品全寿命动态建模方法研究[J]. , 2003, 9(7): 0-0.