共查询到20条相似文献，搜索用时 236 毫秒
1.
用均匀设计进行实验方案的设计，并用分区间优化方法进行实验结果的优化。将重油催化裂化各种产物的产率与原料油的组成、反应条件进行关联，利用人工神经网络的方法建立重油催化裂化产品产率数学模型。用均匀设计的样本对建立的模型进行训练使该模型能很好地拟合试验数据。准确反映强化添加剂在不同反应条件下对催化裂化的产品产率影响，进而得出最优配方。 相似文献
2.
用均匀设计进行实验方案的设计,并用分区间优化方法进行实验结果的优化。将重油催化裂化各种产物的产率与原料油的组成、反应条件进行关联,利用人工神经网络的方法建立重油催化裂化产品产率数学模型。用均匀设计的样本对建立的模型进行训练使该模型能很好地拟合试验数据,准确反映强化添加剂在不同反应条件下对催化裂化的产品产率影响,进而得出最优配方。 相似文献
3.
高新技术项目投资风险的人工神经网络综合评价模型 总被引：2，自引：0，他引：2
高新技术项目投资具有高风险、高收益等特点，科学准确的风险评价对项目投资至关重要。在分析高新技术项目投资风险影响因素的基础上，并根据投资风险分级标准，建立了高新技术项目投资风险进行综合评价的人工神经网络模型，能有效地避免层次分析等传统评价过程中的人为影响。仿真实验表明，采用该方法能获得令人满意的结果。 相似文献
4.
提出了一种将人工神经网络理论应用于单相自适应重合闸中的方法,建立了一个3层的BP网络模型。利用MATLAB进行了大量仿真实验,验证了该方法在瞬时性故障与永久性故障识别中的可行性。 相似文献
5.
6.
BP神经网络在千岛湖水体富营养化变化预测中的应用 总被引：2，自引：0，他引：2
将人工神经网络模型引入水质预测中,并据此建立了千岛湖水体富营养化预测的BP神经网络模型。该模型选取了Chla作为网络的输出变量,通过主因子分析,得到温度Tw、pH、Chla、SD、TN 5个水质因子作为网络的输入变量,构建了5个网络模型。本研究表明,以上周的Tw、pH、Chla、SD为输入变量,下周Chla为输出变量的网络方案能够对千岛湖的水质变化进行很好的短期预测,从而能够使管理部门根据此模型掌握千岛湖水质变化趋势,为其制定千岛湖水质管理方案提供理论依据。 相似文献
7.
运用人工神经网络方法,建立药剂配方、原材料粒度与药剂爆热的三层BP网络模型,通过10组数据对网络进行智能驯化,利用驯化后的网络对另5组数据进行预测,并对这5组数据进行实际测量,结果表明该BP网络能够反映药剂配方、原材料粒度与药剂爆热之间的关系,预测精度较好,相对误差较小。 相似文献
8.
运用前馈式人工神经网络,通过建立网络模型并进行训练、测试,对华北地区某水厂的混凝投药量进行了预测,达到了较好的预测效果。 相似文献
9.
本文利用ＢＰ人工神经网络建立了出生率、死亡率及人口总数三元素动态网络模型，并对出生率，死亡率和人口总数动态进行仿真和预测。在此基础上建立了人口构成仿真网络并对中国人口构成动态进行了预测。 相似文献
10.
管理干部综合素质模糊评价体系的神经网络模型 总被引：6，自引：0，他引：6
本文根据人工神经网络的理论，利用高泛化性能的BP神经网络建立了企业管理人员综合素质的模糊评价模型，通过仿真和实例表明了模型的有效性，给管理干部综合素质的测评提供了一种简便、有效的方法。 相似文献
11.
Magnetic field-induced particle manipulation is a promising technique for biomicrofluidics applications. It is simple, cheap, and also free of fluid heating issues that accompany other common electric, acoustic, and optical methods. This work presents a fundamental study of diamagnetic particle motion in ferrofluid flows through a rectangular microchannel with a nearby permanent magnet. Due to their negligible magnetization relative to the ferrofluid, diamagnetic particles experience negative magnetophoresis and are repelled away from the magnet. The result is a three-dimensionally focused particle stream flowing near the bottom outer corner of the microchannel that is the farthest to the center of the magnet and hence has the smallest magnetic field. The effects of the particle's relative position to the magnet, particle size, ferrofluid flow rate, and concentration on this three-dimensional diamagnetic particle deflection are systematically studied. The obtained experimental results agree quantitatively with the predictions of a three-dimensional analytical model. 相似文献
12.
We present dual-mode, on-demand droplet routing in a multiple-outlet microfluidic device using an oil-based magnetic fluid. Magnetite (Fe3O4) nanoparticle-contained oleic acid (MNOA) was used as a carrier phase for droplet generation and manipulation. The water-in-MNOA droplets were selectively distributed in a curved microchannel with three branches by utilizing both a hydrodynamic laminar flow pattern and an external magnetic field. Without the applied magnetic field, the droplets travelled along a hydrodynamic centerline that was displaced at each bifurcating junction. However, in the presence of a permanent magnet, they were repelled from the centerline and diverted into the desired channel when the repelled distance exceeded the minimum offset allocated to the channel. The repelled distance, which is proportional to the magnetic field gradient, was manipulated by controlling the magnet''s distance from the device. To evaluate routing performance, three different sizes of droplets with diameters of 63, 88, and 102 μm were directed into designated outlets with the magnet positioned at varying distances. The result demonstrated that the 102-μm droplets were sorted with an accuracy of ∼93%. Our technique enables on-demand droplet routing in multiple outlet channels by simply manipulating magnet positions (active mode) as well as size-based droplet separation with a fixed magnet position (passive mode). 相似文献
13.
We present the conformal coating of non-spherical magnetic particles in a co-laminar flow
microfluidic system. Whereas in the previous reports spherical particles had been coated with thin
films that formed spheres around the particles; in this article, we show the coating of
non-spherical particles with coating layers that are approximately uniform in thickness. The novelty
of our work is that while liquid-liquid interfacial tension tends to minimize the surface area of
interfaces—for example, to form spherical droplets that encapsulate spherical particles—in our
experiments, the thin film that coats non-spherical particles has a non-minimal interfacial area. We
first make bullet-shaped magnetic microparticles using a stop-flow lithography method that was
previously demonstrated. We then suspend the bullet-shaped microparticles in an aqueous solution and
flow the particle suspension with a co-flow of a non-aqueous mixture. A magnetic field gradient from
a permanent magnet pulls the microparticles in the transverse direction to the fluid flow, until the
particles reach the interface between the immiscible fluids. We observe that upon crossing the
oil-water interface, the microparticles become coated by a thin film of the aqueous fluid. When we
increase the two-fluid interfacial tension by reducing surfactant concentration, we observe that the
particles become trapped at the interface, and we use this observation to extract an approximate
magnetic susceptibility of the manufactured non-spherical microparticles. Finally, using
fluorescence imaging, we confirm the uniformity of the thin film coating along the entire curved
surface of the bullet-shaped particles. To the best of our knowledge, this is the first
demonstration of conformal coating of non-spherical particles using microfluidics. 相似文献
14.
房地产销售价格指数是指导业界活动和市场研究的有效工具,但是预测的准确程度一直是人们倍加关注的。人工神经网络是一门新兴交叉学科,近年来被越来越多的应用到了实际问题的预测中,显示出其广阔的应用前景,特别是人工神经网络具有预测非线性系统未来行为的巨大潜力。因此,本文提出了用人工神经网络对房地产销售价格指数进行预测的方法,首先将输入数据进行预处理,再利用多层前馈神经网络BP算法来研究人工神经网络在房地产销售价格指数预测中的应用问题,最后得出神经网络方法预测精度较高的结论。 相似文献
15.
字符识别是模式识别领域的一项传统课题,其内容是模式识别领域中很多课题的基本内容。人工神经网络的出现为字符识别的研究提供了一种新的手段,BP神经网络(Back Propagation Neural Network)作为人工神经网络的一个分支,现已成为其最广泛的应用。本文以三层BP网络作为模型,并将其应用于对金属角铁上的字符识别。由于角铁字符为数字与英文字母混合,文中在对传统的BP算法进行了改进的基础上,采用了分组神经网络的设计方法,取得了良好的识别效果。 相似文献
16.
基于粗糙集-神经网络的财务危机预警模型实证研究 总被引：2，自引：0，他引：2
本文提出了以粗糙集与神经网络相结合的技术方法,应用于我国上市公司财务危机预警研究中。在通过以中国上市公司财务数据为基础进行实证分析之后,结果表明粗糙集的引入减少了神经网络的输入维数,采用动量添加法和参数自适应算法修正的神经网络算法,在网络训练的准确性和精度上都优于传统的BP神经网络。 相似文献
17.
本文在分析工程图知识特点的基础上,提出采用人工神经网络的方法表示其知识,使用BP神经网络实现工程图形符号的知识表达,并设计了基于BP的工程图符识别方法,把识别过程转化为网络内部权值计算过程。 相似文献
18.
Artificial neural network (ANN) has been used in several engineering application areas including civil engineering. The use of ANN to predict the behavior of reinforced concrete (R/C) members, using the vast amount of experimental data as a test-bed for learning and verification of results, proved to be a viable method for carrying out parametric studies. This paper presents application of ANN for predicting the shear resistance of rectangular R/C beams. Six parameters that influence the shear resistance of beams, mainly shear-span-to-depth ratio, concrete strength, longitudinal reinforcement, shear reinforcement, beam depth and beam width, are used as input for the ANN. A back propagation neural network (BPNN) with different activation functions is used and their results are compared. The sigmoid function with variable threshold is adopted due to its accuracy of prediction. The ANN prediction and the measured experimental values are compared with the shear strength predictions of ACI318-02 and BS8110 codes. A sensitivity study of the parameters that affect shear strength of R/C beams is carried out and the underlying complex nonlinear relationships among these parameters were investigated. Shear response curves and surfaces based on these parameters were generated. It is concluded that ANN can predict, to a great degree of accuracy, the shear resistance of rectangular R/C beams and it is a viable tool for carrying out parametric study of shear behavior of R/C beams. 相似文献
19.
This study presents a model for predicting the low-cycle fatigue life of steel reinforcing bars using Artificial Neural Network (ANN). A Radial Basis Function (RBF) artificial neural network topology with two additional hidden layers and four neurons (processing elements) in each of these layers is used. The input parameters for the network are the maximum tensile strain (εs,max) and the strain ratio (R) and the output of the ANN is the number of cycles to fatigue failure (Nf). Low-cycle fatigue tests were conducted by the authors in a previous study for different types of steel reinforcing bars subjected to different strain amplitudes and at different strain ratios. The data resulted from these tests were used to train and test the ANN. It is observed that the ANN prediction of low-cycle fatigue life of steel reinforcing bars is within ±2 cycles of the experimental results for the majority of the test data. A parametric study had been carried out to investigate the effect of maximum strain and strain ratio on the fatigue life of steel reinforcing bars. It is concluded that both the strain ratio and the maximum strain have significant effect on the low-cycle fatigue life of such bars, especially at low values of maximum strain and their effect should be considered in both analysis and design. Other observations and conclusions were also drawn. 相似文献
20.
小波神经网络(Wavelet Neural Network)结合了小波变换及神经网络的优点,是一种基于知识的故障诊断方法,它不需要精确的数学模型,既具有良好的时频局部性质,又有较好的自学习能力和容错能力。本文介绍了小波网络及其在电力系统故障检测中的应用,通过EMTP仿真实验表明,小波网络与传统的人工神经网络相比,具有收敛速度快,鲁棒性强的特点,可以将小波网络应用于电力系统的故障检测。 相似文献