A Synergetic Immune Clonal Selection Algorithm Based Multi-Objective Optimization Method for Carbon Fiber Drawing Process

被引:15
作者
Chen, Jiajia [1 ,4 ]
Ding, Yongsheng [1 ,2 ]
Jin, Yaochu [1 ,3 ]
Hao, Kuangrong [1 ,2 ]
机构
[1] Donghua Univ, Coll Informat Sci & Technol, Shanghai 201620, Peoples R China
[2] Donghua Univ, Engn Res Ctr Digitized Text & Fash Technol, Minist Educ, Shanghai 201620, Peoples R China
[3] Univ Surrey, Dept Comp, Guildford GU2 7XH, Surrey, England
[4] Shanghai Normal Univ, Coll Informat Mech & Elect Engn, Shanghai 200234, Peoples R China
关键词
Carbon fiber; Drawing process; Synergetic immunity clonal selection; Multi-objective optimization;
D O I
10.1007/s12221-013-1722-y
中图分类号
TB3 [工程材料学]; TS1 [纺织工业、染整工业];
学科分类号
082103 [纺织化学与染整工程]; 082905 [生物质能源与材料];
摘要
Carbon fiber production is a large-scale system which comprises a large number of production processes. Among the various complex production conditions, the drawing process is one of the most influential factors that affect the quality of carbon fiber. How to obtain the fittest process parameters of the drawing process is a typical multi-objective optimization problem. To address the drawbacks of mathematical programming techniques available for solving optimization problems, we propose a new synergetic immune clonal selection algorithm (SICSA) to obtain the optimal process parameters, such as the linear density, strength, and breaking elongation ratio. The main operators of the SICSA are synergetic evolution, clonal operation and non-uniform mutation. The synergetic evolution between populations adopts a "division-parallel-recombination" mode, the clonal operation searches for optimal solutions globally, and the non-uniform mutation explores optimal solutions locally and enhances the diversity of the solution's. As a result, optimal solutions which lead to reasonable distribution of the drawing ratio are obtained. We also compare the proposed SICSA with an immune algorithm and a genetic algorithm for optimizing the parameter in the drawing process. Our results show that the SICSA has the best performance in precision and convergence time. These results can serve as references and provide guidance for real production of carbon fiber.
引用
收藏
页码:1722 / 1730
页数:9
相关论文
共 32 条
[1]
Modelling and multi-objective optimization of a variable valve-timing spark-ignition engine using polynomial neural networks and evolutionary algorithms [J].
Atashkari, K. ;
Nariman-Zadeh, N. ;
Golcu, M. ;
Khalkhali, A. ;
Jamali, A. .
ENERGY CONVERSION AND MANAGEMENT, 2007, 48 (03) :1029-1041
[2]
A multi-objective artificial immune algorithm for parameter optimization in support vector machine [J].
Aydin, Ilhan ;
Karakose, Mehmet ;
Akin, Erhan .
APPLIED SOFT COMPUTING, 2011, 11 (01) :120-129
[3]
Modeling of a two-stage draw process [J].
Bechtel, SE ;
Vohra, S ;
Jacob, KI .
POLYMER, 2001, 42 (05) :2045-2059
[4]
Boor C. D., 2001, APPL MATH SCI, V27, P1
[5]
An efficient multi-objective optimization method for black-box functions using sequential approximate technique [J].
Chen, Guodong ;
Han, Xu ;
Liu, Guiping ;
Jiang, Chao ;
Zhao, Ziheng .
APPLIED SOFT COMPUTING, 2012, 12 (01) :14-27
[6]
System engineering and configuration management in ITER [J].
Chiocchio, S. ;
Martin, E. ;
Barabaschi, P. ;
Bartels, Hans Werner ;
How, J. ;
Spears, W. .
FUSION ENGINEERING AND DESIGN, 2007, 82 (5-14) :548-554
[7]
Multistage Modified Fiber Drawing Process and Related Diameter Measuring System [J].
Chuo, Shih-Min ;
Wan, Meng-Hsun ;
Wang, Lon A. ;
Wang, Jau-Sheng .
JOURNAL OF LIGHTWAVE TECHNOLOGY, 2009, 27 (15) :2983-2988
[8]
An immune-inspired multi-objective approach to the reconstruction of phylogenetic trees [J].
Coelho, Guilherme P. ;
da Silva, Ana Estela A. ;
Von Zuben, Fernando J. .
NEURAL COMPUTING & APPLICATIONS, 2010, 19 (08) :1103-1132
[9]
A coevolutionary multi-objective evolutionary algorithm [J].
Coello, CAC ;
Sierra, MR .
CEC: 2003 CONGRESS ON EVOLUTIONARY COMPUTATION, VOLS 1-4, PROCEEDINGS, 2003, :482-489
[10]
Solving multiobjective optimization problems using an artificial immune system [J].
Coello C.A.C. ;
Cortés N.C. .
Genetic Programming and Evolvable Machines, 2005, 6 (2) :163-190