期刊文献+

人工神经网络结合遗传算法对CFWRP固化制度的优化 被引量:2

OPTIMIZATION OF CURING CYCLE OF CFWRP WITH COMBINATION OF ARTIFICIAL NEURAL NETWORK AND GENETIC ALGORITHM
下载PDF
导出
摘要 聚合物基复合材料的固化制度是影响其性能经济指标的重要因素。它们之间的关系既无先验公式表征,又为非线性,一般是采用“试凑法”探索试验,但耗时长也未必达到优化目的。神经网络法具有超强非线性映射能力,可自动总结出数据之间的函数关系,遗传算法可多点群体搜索,并可不陷入局部最优点。本文以碳纤维缠绕聚合物基复合材料(CFWRP)制成NOL环试件,在试验基础上采用人工神经网络结合遗传算法对固化制度进行优化,得到较好的结果。 The curing cycle of polymeric composites has significant effect on its performance and economic indices. Their relationships can not be described by empirical equations and shown to be nonlinear. "Trial-and-error method" was conventionally performed in the experiments, which cost too much time and still can not achieve the optimization. Neural network approach has good capability of nonlinear mapping and can summarize the function relationships of data automatically. Genetic algorithm can realize the multipoint population search and not be lost in the local optimized point. This study uses NOL rings made of carbon fiber wound reinforced plastics (CFWRP) as specimens. Based on the experiments, the optimization of curing cycle of NOL rings is performed with the combination of artificial neural network and genetic algorithm. The results are satisfactory.
出处 《玻璃钢/复合材料》 CAS CSCD 北大核心 2007年第2期3-6,共4页 Fiber Reinforced Plastics/Composites
基金 国家自然科学基金(50475034)
关键词 碳纤维缠绕复合材料 固化制度 优化 BP神经网络 遗传算法 carbon fiber wound reinforced plastics (CFWRP) curing cycle optimization BP neural network genetic algorithm
  • 相关文献

参考文献3

二级参考文献9

共引文献110

同被引文献21

  • 1焦俊婷,于霖冲.基于ANN的复合材料变厚度壳体固化变形预测[J].玻璃钢/复合材料,2006(5):3-5. 被引量:6
  • 2王海龙,李叶斌.人工神经网络结合遗传算法对FWRP张力制度的优化[J].玻璃钢/复合材料,2007(4):3-5. 被引量:3
  • 3A.Jacob.Globalisation of the pultrusiou industry[J].Reinforced Plastics,2006,50(5):38-41.
  • 4J.Martin.Pultruded composites compete with traditional construction materials[J].Reinforced Plastics,2006,50(5):20-27.
  • 5R.Stewart.Pultrusion industry grows steadily in US[J].Reinforced Plastics,2002,46(6):36-39.
  • 6H.Kurtaran,B.Ozcelik,T.Erzurunlu.Warpnge optimizatiou of a bus ceiling lamp base using neural network model and genetic algorithm[J].Journal of Materials Processing Technology,2005,(169):314-319.
  • 7K.Deb,S.Agarwal,T.Meyarivan.A fast and elitist multiobjective genetic algorithm:NSGA-Ⅱ[J].Evolutionary Computation,2002,6(2):182-197.
  • 8P.Murugan,S.Kannan,S.Baskar.NSGA-Ⅱ algorithm for multi-objective generation expansion planning problem[J].Electric Power systems Research,2009,79:600-628.
  • 9S.Majumdar,K.Mitra,S.Raha.Optimized species growth in epoxy polymerization with real-coded NSGA-Ⅱ[J].Polymer,2005,(46):11858-11869.
  • 10Elias G.Bekele,John W.Nicklow,Multi-objective automatic calibratiou of SWAT using NSGA-Ⅱ[J].Journal of Hydrology,2007,(341):165-176.

引证文献2

二级引证文献1

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部