高级检索

广义动态模糊神经网络焊接接头力学性能预测

张永志1,2,董俊慧1,侯继军1

张永志1,2,董俊慧1,侯继军1. 广义动态模糊神经网络焊接接头力学性能预测[J]. 焊接学报, 2017, 38(8): 37-40. DOI: 10.12073/j.hjxb.20150911002
引用本文: 张永志1,2,董俊慧1,侯继军1. 广义动态模糊神经网络焊接接头力学性能预测[J]. 焊接学报, 2017, 38(8): 37-40. DOI: 10.12073/j.hjxb.20150911002
ZHANG Yongzhi1,2, DONG Junhui1, HOU Jijun1. Predictive modeling of mechanical properties of welded joints based on generalized dynamic fuzzy RBF neural network[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2017, 38(8): 37-40. DOI: 10.12073/j.hjxb.20150911002
Citation: ZHANG Yongzhi1,2, DONG Junhui1, HOU Jijun1. Predictive modeling of mechanical properties of welded joints based on generalized dynamic fuzzy RBF neural network[J]. TRANSACTIONS OF THE CHINA WELDING INSTITUTION, 2017, 38(8): 37-40. DOI: 10.12073/j.hjxb.20150911002

广义动态模糊神经网络焊接接头力学性能预测

Predictive modeling of mechanical properties of welded joints based on generalized dynamic fuzzy RBF neural network

  • 摘要: 建立广义动态模糊神经网络模型,用来预测焊接接头力学性能. 模型结构不再是建模时预设,而是在对逐个样本的学习过程中动态自适应调整. 引入椭圆基函数扩大函数的接收域,利用系统误差和模糊规则ε完备性作为模糊规则增加的依据,并将模糊规则ε完备性作为径向基单元的宽度确定准则. 以误差减少率评价模糊规则的重要性,并以此为依据对模型的模糊规则进行修剪. 采用三种不同厚度、不同工艺TC4钛合金TIG焊接试验,获得17组训练样本和5组仿真样本数据,建模并仿真. 结果表明,该模型能够对焊接接头力学性能进行较为准确的预测.
    Abstract: Generalized dynamic fuzzy neural network model was established to predict the mechanical properties of welded joints. Structure of the model is no longer in default modeling, but on a sampleby dynamically adaptive learning process. By introducing elliptic basis functions to expand the receive domain to function , increased fuzzy rules was based on the systematic error and fuzzy rules ε completeness, and the RBF unit width determination criterion was based on fuzzy rules ε completeness. The fuzzy rule of model pruning was based on their importance which was evaluated by error reduction rate. By using three different thicknesses and different process TC4 titanium alloy TIG welding test group, 17 sets and 5 sets of training and simulation sample data were obtained for modeling and simulation. The results showed that the model can accurate prediction on the mechanical properties of welded joints.
  • [1] Koganti R, Karas C, Joaquin A,etal. Metal inert gas (MIG) welding process optimization for joining aluminum sheet material using OTC/DAIHEN equipment[J]. Proceedings of IMECE, 2003,10(3): 15-21.[2] Benyounis K Y, Olabi A G, Hashmim S J. Multi-response optimization of CO2laser-welding process of austenitic stainless steel[J]. Optics & Laser Technology, 2008, 40(3): 76-87.[3] Benyounis K Y, Olabi A G. Optimization of different welding processes using statistical and numerical approaches-A reference guide[J]. Advances in Engineering Software, 2008, 39(3): 483-496.[4] Pan L K, Wang C C, Hsiso Y C,etal. Optimization of Nd-YAG laser welding onto magnesium alloy via Taguchi analysis[J]. Optics and Laser Technology, 2005, 37(2): 33-42.[5] Peyre P, Sierra G,Deschaux B,etal. Generation of aluminum-steel joints with laser-induced reactive wetting[J]. Materials Science and Engineering, 2007, 444(1): 327-338.[6] Shojaeefard M H, Behnagh R A, Akbari M,etal. Modeling and pareto optimization of mechanical properties of friction stir welded AA7075/AA5083 butt joints using neural network and particle swarm algorithm[J]. Materials & Design, 2013, 44(2): 190-198.[7] 张永志, 董俊慧, 张艳飞. 基于径向基神经网络焊接接头力学性能预测[J]. 焊接学报, 2008, 29(7): 81-84. Zhang Yongzhi, Dong Junhui, Zhang Yanfei. Prediction of mechanical properties of titanium alloy welding joints based on RBF neural network[J]. Transactions of the China Welding Institution, 2008, 29(7): 81-84.[8] 张永志, 董俊慧. 两种预测焊接接头力学性能的模糊神经网络[J]. 焊接学报, 2011, 32(11): 104-107. Zhang Yongzhi, Dong Junhui. Research on two fuzzy neural networks to predict mechanical properties of welded joints[J]. Transactions of the China Welding Institution, 2011, 32(11): 104-107.[9] 张艳飞, 董俊慧, 张永志. 基于自适应模糊神经网络焊接接头力学性能预测[J]. 焊接学报, 2007, 28(9): 5-8. Zhang Yanfei, Dong Junhui, Zhang Yongzhi. Prediction mechanical properties of welded joints based on ANFIS[J]. Transactions of the China Welding Institution, 2007, 28(9): 5-8.[10] 罗 薇. 基于广义回归神经网络的广西农业机械需求预测[J]. 农机化研究, 2013, 35(1): 49-52. Luo Wei. Agricultural machinery demand forecasting in guangxi province based on generalized regression neural network[J]. Journal of Agricultural Mechanization Research, 2013, 35(1): 49-52.[11] 伍世虔, 徐 军. 动态模糊神经网络——设计与应用[M]. 北京: 清华大学出版社, 2008.[12] Chuen C L. Fuzzy logic in control systems: fuzzy logic controller part.I[J]. IEEE Transactions on Systems, Man and Cyberneties, 1990, 20(2): 404-418.[13] Daya R, Lai S, Manjaree P,etal. Corrective action planning using RBF neural network[J]. Applied Soft Computing, 2007(7): 1055-1063.[14] 唐正魁, 董俊慧, 张永志, 等. 混合聚类RBF神经网络焊接接头力学性能预测[J]. 焊接学报, 2014, 35(12): 105-108. Tang Zhengkui, Dong Junhui, Zhang Yongzhi,etal. Prediction of mechanical properties of welding joints by hy-brid cluster fuzzy RBF neural network[J]. Transactions of the China Welding Institution, 2014, 35(12): 105-108.
  • 期刊类型引用(1)

    1. 王兴磊,杨赫然,孙兴伟,赵泓荀,潘飞. 基于WOA-RBF的螺杆转子双砂带磨削表面粗糙度及材料去除率预测. 制造技术与机床. 2025(04): 172-179 . 百度学术

    其他类型引用(8)

计量
  • 文章访问数:  657
  • HTML全文浏览量:  35
  • PDF下载量:  491
  • 被引次数: 9
出版历程
  • 收稿日期:  2015-09-10

目录

    /

    返回文章
    返回