排序方式: 共有29条查询结果,搜索用时 875 毫秒
1.
基于遗传算法和BP神经网络的优化设计方法 总被引:5,自引:0,他引:5
随着生产规模的复杂化、多维化和非线性等复杂特性的增加,对生产中高效的优化技术要求也越来越迫切,利用并行遗传算法和BP网络的优点,提出采用遗传算法的并行搜索和解空间搜索的优点进行网络参数的选取,利用BP网络简单和可塑性强的优点来优化样本空间,以取得整体的优化效率。 相似文献
2.
3.
提出了基于硬限幅功能函数的前向神经网络的分类学习算法,并将其应用于可分凸集或不交集合的分类.仿真结果证明,同基于S功能函数的前向神经网络的BP算法相比,该算法具有较强的分类能力且收敛时间极短.此外,本算法易于硬件实现,且成本低,具有很大的应用潜力. 相似文献
4.
针对日长变化难以用精确模型进行预报的问题,将一种新型人工神经网络--极限学习机(extreme learning machine, ELM)用于日长变化预报中.首先针对时间序列预测问题中存在的嵌入维数选取和网络结构设计问题,提出一种基于灰色关联分析(grey relational analysis, GRA)的ELM算法(GRA-ELM),该算法将灰色关联分析输入节点选取嵌入到ELM网络的训练过程中,同时完成嵌入维数和隐层节点规模的确定.然后根据日长变化数据的特点对其进行预处理,建立一种能够高精度、近实时预报日长变化的GRA-ELM预报模型.最后将GRA-ELM模型的预报结果同标准ELM、反向传播神经网络、广义回归神经网络和地球定向参数预报比较竞赛的结果进行比较.结果表明,通过本方法得到的日长变化较其他方法在精度上有较大改善. 相似文献
5.
在盐酸介质中,碘酸钾与钙红反应褪色程度与碘酸根浓度在一定范围内呈线性关系,以此建立了碘的光度测定新方法。方法的最大吸收波长在510nm处,碘定量测定的线性范围为0.3mVL,摩尔吸光系数ε=1.3×10^4L/mol·cm。本法所得结果和国家标准(GB5009.24.85)中规定食盐中碘含量的测定方法相当。 相似文献
6.
7.
Too many sensors and data information in structural health monitoring system raise the problem of how to realize multi-sensor information fusion. An experiment on a three-story frame structure was conducted to obtain vibration test data in 36 damage cases. A coupling neural network (NN) based on multi-sensor information fusion is proposed to achieve identification of damage occurrence, damage localization and damage quantification, respectively. First, wavelet packet transform (WPT) is used to extract features of vibration test data from structure with different damage extent. Then, data fusion is conducted by assembling feature vectors of different type sensors. Finally, three sets of coupling NN are constructed to implement decision fusion and damage identification. The results of experimental study proved the validity and feasibility of the proposed methodology. 相似文献
8.
9.
Children of 3, 5, 7, 9, and 11 years of age were given simple, social-matching problems. Two conditions were employed: each involved verbal presentation but in one (Condition V) no concrete representation was involved while in the other (Condition M) models were also used. Within each condition, information was provided which was (a) sufficient, (b) superfluous, (c) irrelevant or which displayed a combination of these characteristics. For all age groups, the problems containing only irrelevant information were the most difficult, although Condition M enhanced the performance of younger children while depressing that of 7- and 9-year-olds. The results were interpreted as supporting the view that a major source of difficulty for the child may lie in selecting the appropriate referent. Some inferences are drawn regarding the abilities of children to cope with ambiguity. 相似文献
10.
聚类分析已成为数据挖掘研究中非常活跃的研究课题,在聚类分析方法中,基于模型的算法由于考虑到“噪声”或异常数据,可以自动确定聚类个数,可以产生鲁棒的聚类方法,而成为领域研究的一个重点。本文主要对神经网络中的竞争学习神经网络、SOFM 神经网络方法、统计学聚类方法研究。 相似文献