【作者】 马铭； 孟庆锴； 张利彪；

【Author】 MA Ming 1,MENG Qingkai1,ZHANG Libiao2 (1.Information Manage Center,Beihua University,Jilin 132013,China; 2. College of Computer Science and Technology,Jilin University,Changchun 130012,China)

【机构】 北华大学信息管理中心； 吉林大学计算机科学与技术学院；

【摘要】 为了解决模糊系统优化问题,提高全局优化能力,在模糊加权神经网络和微粒群算法的基础上,提出了一种基于微粒群算法的模糊神经网络优化算法。该算法可以同时对模糊加权神经网络的网络结构和权值参数进行优化,对实际问题可以自动生成较好的模糊神经网络模型。经过实验分析和计算,证明这种算法在解决模糊系统优化问题上表现了良好的性能,应用该算法可以有效地解决软测量问题。该结果对工业过程中的软测量建模提供了良好的参考价值。更多还原

【Abstract】 In order to solve the problem associated with fuzzy system optimization and improve the overall optimization capability,a new algorithm has been proposed to optimize the weighted neural network based on particle swarm optimization. The proposed algorithm can optimize both the fuzzy neural network’s topology and weighting parameters at the same time to obtain a near-optimal structure of fuzzy neural network. An experimental analysis and calculation shows that the algorithm is very effective in solving fuzzy system optimization,and can also effectively solve the problem of soft sensor. The result provides a good reference for the soft sensor modeling in industrial process.更多还原