共查询到20条相似文献,搜索用时 46 毫秒
1.
可拓神经网络是基于可拓理论和神经网络而设计的一种新的方法,它即充分利用了可拓学定性描述和定量描述的优点,又考虑了神经网络并行结构的特点.它由输入和输出两层可拓神经元构成,在每个输入神经元和输出神经元之间有两个连接权值.然后利用遗传算法全局搜索能力,对建立的可拓神经网络的权值进行优化,在优化过程中利用可拓神经网络输出的正确次数与可拓神经网络输入的样本总数的比值作为适应度函数,染色体根据物元的节域进行实数编码,计算出的可拓距离的最大值对应的物元与样本一致时,输出正确次数累加一次.算法终止条件为误差值达到要求.最后利用该方法开发了励磁系统的故障诊断系统.并对可控硅的缺相故障进行了成功的诊断.试验结果证明,该方法比传统的神经网络具有速度快,准确度高的特点. 相似文献
2.
可拓神经网络是一类新的神经网络,它结合了可拓学理论和人工神经网络技术。可拓神经网络已经在模式识别、故障诊断、分类聚类等领域有了成功的应用。针对变压器故障诊断的特点,提出一种基于可拓神经网络的电力变压器故障诊断方法。介绍了可拓神经网络;构造了基于可拓神经网络的故障诊断模型和算法设计,并将其应用到电力变压器的诊断识别;通过仿真实验验证了该方法简单易行、训练误差小、收敛时间快等优点。该方法具有一定的应用及推广能力。 相似文献
3.
专家神经网络的构造研究 总被引:1,自引:1,他引:0
专家神经网络是由专家系统产生出的事件驱动无环路神经对象网络。这些神经对象处理信息的非线性复合函数比正常的神经网络结点处理器更复杂。本文研究了无环路网络的BP学习算法,这一算法将传统BP算法与专家神经网络特征结合起来,提供了一种获取知识的方法。 相似文献
4.
Ensemble neural networks (ENNs) are commonly used neural networks in many engineering applications due to their better generalization properties. An ENN usually includes several component networks in its structure, and each component network commonly uses a single feed-forward network trained with the back-propagation learning rule. As the neural network architecture has a significant influence on its generalization ability, it is crucial to develop a proper algorithm to determine the ENN architecture. In this paper, an ENN, which combines the component networks using the entropy theory, is proposed. The entropy-based ENN searches the best structure of each component network first, and employs entropy as an automating design tool to determine the best combining weights. Two analytical functions - the peak function and the Friedman function are used to assess the accuracy of the proposed ensemble approach. Then, the entropy-based ENN is applied to the modeling of peak particle velocity (PPV) damage criterion for rock mass. These computational experiments have verified that the proposed entropy-based ENN outperforms the simple averaging ENN and the single NN. 相似文献
5.
针对软件缺陷预测时缺陷数据集中存在的类别分布不平衡问题,结合上采样算法SMOTE与Edited Nearest Neighbor (ENN) 数据清洗策略,提出了一种基于启发式BP神经网络算法的软件缺陷预测模型。模型中采用上采样算法SMOTE增加少数类样本以改善项目中的数据不平衡状况,并针对采样后数据噪声问题进行ENN数据清洗,结合基于启发式学习的模拟退火算法改进四层BP神经网络后建立分类预测模型,在AEEEM数据库上使用交叉验证对提出的方案进行性能评估,结果表明所提出的算法能够有效提高模型在预测类不平衡数据时的分类准确度。 相似文献
6.
神经网络BP学习算法动力学分析 总被引:2,自引:0,他引:2
研究神经网络BP学习算法与微分动力系统的关系.指出BP学习算法的迭代式与相
应的微分动力系统数值解Euler方法在一定条件下等价,且二者在解的渐近性方面是一致的.
给出了神经网络BP学习算法与相应的微分动力系统解的存在性、唯一性定理和微分动力系统
的零解稳定性定理.从理论上证明了神经网络的学习在一定条件下与微分动力系统的数值方法
所得的数值解在渐近意义下是等价的,从而借助于微分动力系统的数值方法可以解决神经网络
的学习问题.最后给出了用改进Euler方法训练BP网的例子. 相似文献
7.
8.
Funabiki N. Kitamichi J. Nishikawa S. 《IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics》1998,28(6):849-855
A novel neural network approach called “Evolutionary Neural Network (ENN)” is presented for the module orientation problem. The goal of this NP-complete problem is to minimize the total wire length by flipping circuit modules with respect to their vertical and/or horizontal axes of symmetry. In order to achieve high quality VLSI systems, it is strongly desired to solve the problem as quickly as possible in the design cycle. Based on the concept of the genetic algorithm, the evolutionary initialization scheme on neuron states is introduced so as to provide a high quality solution within a very short time. The performance of ENN is compared with three heuristic algorithms through simulations on 20 examples with up to 500 modules. The results show that ENN can find the best solutions in the shortest time 相似文献
9.
针对污水处理过程溶解氧(DO)浓度控制问题,提出了一种基于前馈神经网络的建模控制方法(FNNMC).本文构造了神经网络建模控制系统,通过对建模神经网络和控制神经网络隐含层学习率的分析,证明了学习算法的收敛性以及整个系统的稳定性.最后,本文基于国际基准的Benchmark Simulation Model No.1 (BSMl)进行了仿真实验,验证了合理选取学习率的重要性,并通过与PID和模型预测控制(MPC)等已有控制方法的比较,验证了神经网络建模控制方法针对污水处理过程溶解氧浓度控制具有良好的建模能力,更高的控制精度以及更好的动态响应能力. 相似文献
10.
基于改进ENN2 聚类算法的多故障诊断方法 总被引:1,自引:0,他引:1
针对可拓神经网络无法解决多故障诊断的问题,建立问题模型,将多故障诊断问题转化为多特征样本的聚类问题。从模型结构和学习算法两个方面对ENN2进行改进,提出基于改进ENN2聚类算法的多故障诊断方法,并对其参数和时间复杂度进行分析。采用工程实例对所提出的方法进行验证,结果表明,所提出的方法能够解决离线的多故障诊断问题,且得到的诊断模型可用于在线状态监控,具有较好的应用前景。 相似文献
11.
12.
In this paper, we propose a new recurrent fuzzy neural network, which has the standard state space form, we call it state-space
recurrent neural networks. Input-to-state stability is applied to access robust training algorithms for system identification.
Stable learning algorithms for the premise part and the consequence part of fuzzy rules are proved. 相似文献
13.
Because of the chaotic nature and intrinsic complexity of wind speed, it is difficult to describe the moving tendency of wind speed and accurately forecast it. In our study, a novel EMD–ENN approach, a hybrid of empirical mode decomposition (EMD) and Elman neural network (ENN), is proposed to forecast wind speed. First, the original wind speed datasets are decomposed into a collection of intrinsic mode functions (IMFs) and a residue by EMD, yielding relatively stationary sub-series that can be readily modeled by neural networks. Second, both IMF components and residue are applied to establish the corresponding ENN models. Then, each sub-series is predicted using the corresponding ENN. Finally, the prediction values of the original wind speed datasets are calculated by the sum of the forecasting values of every sub-series. Moreover, in the ENN modeling process, the neuron number of the input layer is determined by a partial autocorrelation function. Four prediction cases of wind speed are used to test the performance of the proposed hybrid approach. Compared with the persistent model, back-propagation neural network, and ENN, the simulation results show that the proposed EMD–ENN model consistently has the minimum statistical error of the mean absolute error, mean square error, and mean absolute percentage error. Thus, it is concluded that the proposed approach is suitable for wind speed prediction. 相似文献
14.
对一类未知的非线性的多变量系统,提出了用动态神经网络实现直接自适应控制的策略,基于Lyapunov理论,获得一个稳定并且连续的学习律,避免了递归训练过程,闭环系统被证明是鲁棒稳定的,跟踪误差收敛到一个小的残集,这种方法的特点是即不需要离线学习阶段也不要求初始的参数误差足够小,仿真结果验证了提出的动态网络的自适应控制算法的有效性。 相似文献
15.
进化神经网络研究进展 总被引:11,自引:0,他引:11
进化神经网络是将进化算法应用于神经网络的构造、学习而得到的神经网络,具有很强的鲁棒适应性。综述了进化神经网络方法及其应用研究新进展,对研究中出现的一些问题进行了讨论与展望。 相似文献
16.
17.
提出一种基于预测控制的神经网络控制方法,将模型未知时的混沌运动控制到不稳定的不动点(UFP)处,该控制系统不需要UFP的位置及其局性态等知识,它包括观测器、带反馈校正的神经网络在预测器和在线训练的神经网络控制器,其方法简便,收敛速度比现有同类方法快得多,同时还分析了控制系统的稳定性,并证明了神经网络控制器的收敛性,理论推导和仿真结果都表明了该方法的有效性。 相似文献
18.
19.