共查询到17条相似文献,搜索用时 125 毫秒
1.
2.
一种基于BP算法学习的小波神经网络 总被引:2,自引:1,他引:2
为发展 Szu的基于信号表示的小波神经网络 ,提出一种多输入多输出的小波网络模型 ,网络隐层采用框架小波函数、输出层采用 Sigmoid激励函数 ,并选用“熵误差函数”以加速网络的学习速度。奇偶判别和混沌时间序列预测例子的实验结果表明了它具有良好的函数逼近能力和推广能力 ,收敛速度和均方误差均优于相同结构的多层感知器模型。 相似文献
3.
基于多种神经网络的风暴潮增水预测方法的比较分析 总被引:1,自引:0,他引:1
简要介绍了利用BP神经网络、小波神经网络、递归神经网络进行风暴潮增水值预测的原理。选取广东省珠江口以南的阳江站2017年风暴潮增水数据进行测试。结果表明,三种神经网络方法针对阳江地区风暴潮增水的预测均具有可靠性和实用性。以当前增水值为输入量的单因子模型更能反映真实风暴潮增水趋势,而从增水极值预测的准确性来看,以台风风力、气压、风向等相关参数为输入量的多因子模型优于单因子模型。BP神经网络更适用于多因子长时间预测,小波神经网络在单因子短时间预测上准确性更高,递归神经网络预测值与实测值相关性更强。在工程运用中,需根据地域时空特点、数据资料的丰富度与预测值评估指标选择合适的方法。 相似文献
4.
5.
针对水下机器人操纵性优化设计中水动力系数预报问题,在水下机器人水动力预报中引入艇体肥瘦指数概念,确定了水下机器人艇体几何描述的五参数模型。提出采用小波神经网络方法预报水下机器人水动力,确定了神经网络的结构,利用均匀试验设计方法,设计了神经网络的学习样本。研究结果表明,只要确定适当的输入参数,选择适当的学习样本和网络结构,利用小波神经网络方法对水下机器人水动力进行预报可以达到较好的精度。 相似文献
6.
海冰管理是抵御寒区海洋资源开发海冰威胁的有效手段,海冰风险的准确、快速预测是海冰管理系统的关键组成部分。文中面向海冰管理中的冰情短时预测需求,明确了基于现场监测的海冰风险预测模式,开展了应用机械学习理论的海冰风险短时预测方法研究,并以渤海辽东湾海冰管理为例,讨论了神经网络与小波分解等非线性预测方法在冰情短时预测中的适用性。结果表明,时间序列小波神经网络在短时(6 h)冰厚预测中的预测精度与Elman神经网络相仿,而在24~48 h预测中的精度偏差较大;Elman神经网络在6 h、24 h与48 h的冰厚预测中均能保持较好的预测精度,在冰流速与来冰方向预测中,模型预测精度达到80%左右。 相似文献
7.
8.
9.
针对目前存在的海水水质受多因素影响、评价难的现状,提出了一种基于粒子群算法(PSO)优化误差反向传播(BP)神经网络的海水水质评价模型。该模型通过PSO得到BP神经网络最优的权值和阈值,结合青岛东部海域10个监测站点的数据得到水质评价结果。实验证明,该模型和单因子评价、传统的BP神经网络评价相比较,具有训练时间短、预测精度高的特点,在海水水质评价中具有良好的应用价值。 相似文献
10.
11.
1 .Introduction Large civil engineering structures are exposed to various external loads such as earthquakes ,winds ,traffic and wave loads during their lifetime . The structures may become deteriorated and de-graded withtime in an unexpected way, which m… 相似文献
12.
本文以一种新型激光扫描3-D视觉传播系统中快速求解3-D坐标值等为例子,展示BP神经网络的并行分布处理在本质上具有高速度优势及硬件容错能力;以及如何实现基于模拟神经网络的二进制数字量映射的无误差操作:进而阐明用模拟VLSI技术实现训练后神经网络芯片的可行性和推广意义。 相似文献
13.
14.
15.
Rados?aw ?bikowski 《Estuarine, Coastal and Shelf Science》2011,94(2):138-143
This study demonstrates application of artificial neural networks (ANNs) for identifying the origin of green macroalgae (Enteromorpha sp. and Cladophora sp.) according to their concentrations of Cd, Cu, Ni, Zn, Mn, Pb, Na, Ca, K and Mg. Earlier studies confirmed that algae can be used for biomonitoring surveys of metal contaminants in coastal areas of the Southern Baltic. The same data sets were classified with the use of different structures of radial basis function (RBF) and multilayer perceptron (MLP) networks. The selected networks were able to classify the samples according to their geographical origin, i.e. Southern Baltic, Gulf of Gdańsk and Vistula Lagoon. Additionally in the case of macroalgae from the Gulf of Gdańsk, the networks enabled the discrimination of samples according to areas of contrasting levels of pollution. Hence this study shows that artificial neural networks can be a valuable tool in biomonitoring studies. 相似文献
16.
WEI Dong ZHANG Shengkun
Ph.D. Candidate School of Naval Architecture Ocean Engineering Shanghai Jiao Tong University Shanghai P. R. China
Professor School of Naval Architecture Ocean Engineering Shanghai Jiao Tong University Shanghai P. R. China 《中国海洋工程》1999,(3)
Stiffened Panels are important strength members in ship and offshore structures,A new methodbased on counterpropagation neural networks(CPN)is proposed in this paper to predict the ultimate compres-sive strength of stiffened panels.Compared with two-parametric polynomial,this method can take more pa-rameters into account and make more use of experimental data.Numerical study is carried out to verify thevalidation of this method.The new method may find wide application in practical design. 相似文献
17.
Wave parameters prediction is an important issue in coastal and offshore engineering. In this literature, several models and methods are introduced. In the recent years, the well-known soft computing approaches, such as artificial neural networks, fuzzy and adaptive neuro-fuzzy inference systems and etc., have been known as novel methods to form intelligent systems, these approaches has also been used to predict wave parameters, as well. It is not a long time that support vector machine (SVM) is introduced as a strong machine learning and data mining tool. In this paper, it is used to predict significant wave height (Hs). The data set used in this study comprises wave wind data gathered from deep water locations in Lake Michigan. Current wind speed (u) and those belonging up to six previous hours are given as input variables, while the significant wave height is the output parameter. The SVM results are compared with those of artificial neural networks, multi-layer perceptron (MLP) and radial basis function (RBF) models. The results show that SVM can be successfully used for prediction of Hs. Furthermore, comparisons indicate that the error statistics of SVM model marginally outperforms ANN even with much less computational time required. 相似文献