Computer-aided tools for molecular systems engineering and wavelet-morphometric analysis of the texture of nanomaterials

An analysis of present-day computer-aided tools for molecular systems engineering and the possibility of their use for developing the texture of new nanomaterials is performed. A wavelet-morphometric algorithm for a computer-aided analysis of the texture of nanomaterials using the original photomicrographs is proposed that includes the following main stages: the decomposition of the original photomicrographs into low-frequency and high-frequency components using a discrete wavelet transform, the calculation of energymechanical characteristics for the identified images of the texture elements of the high-frequency component, and further binary decomposition and calculation of morphometric parameters for the created images of energy-mechanical characteristics (parameters of texture elements). A system of energy-mechanical and morphometric parameters of the elements of the texture of nanocomposites is proposed that is based on the use of binary decomposition filtration of textural photomicrographs and the morphometric parameters of the identified images of clusters in the binarization sections.     

Computation of the integral parameters of turbulent structures for the transient gas flows in pipes using wavelet transforms

Turbulent structures of simulated two-dimensional gas flows in a convergent-tube assembly of a complex pipe are analyzed by computing the morphometric parameters for the texture of two-dimensional energy fields using wavelet transforms. A new computer-aided procedure based on the decomposition of the original image of a gas flow into low-and high-frequency components using a discrete wavelet transform, calculation of the textural parameters for the high-frequency component, binary decomposition, and calculation of the morphometric parameters for the textured images is developed to analyze the flow pattern of the turbulence of transient gas flows in the assemblies of complex pipes. A new system of integral parameters computed on the basis of the binary decomposition of the textured images of gas-flow characteristics and the morphometric measurements of the parameters of flow objects in binarization sections is proposed to characterize the turbulent structure of transient gas flows in pipes.     

Influence of threshold variation on determining the properties of a polymer electrolyte fuel cell gas diffusion layer in X-ray nano-tomography

Morphological parameters of a 3D binary image of a porous carbon gas diffusion layer (GDL) for polymer electrolyte fuel cells (PEFC) reconstructed using X-ray nano-tomography scanning have been obtained, and influence of small alterations in the threshold value on the simulated flow properties of the reconstructed GDL has been determined. A range of threshold values with 0.4% increments on the greyscale map have been applied and the gas permeability of the binary images have been calculated using a single-phase lattice Botlzmann model (LBM), which is based on the treatment of nineteen velocities in the three dimensional domain (D3Q19). The porosity, degrees of anisotropy and the mean pore radius have been calculated directly from segmented voxel representation. A strong relationship between these parameters and threshold variation has been established. These findings suggest that threshold selection can significantly affect some of the flow properties and may strongly influence the computational simulation of micro and nano-scale flows in a porous structure.     

基于图像傅里叶变换纹理特征和概率神经网络的气固流化床流型识别

提出一种基于图像傅里叶变换纹理特征和概率神经网络相结合的气固流化床流型识别的新方法。该方法利用高速摄影系统获取流型图像。首先对流型图像进行组合滤波去噪,然后运用长方环傅里叶周向谱能量百分比法来计算图像频率分布特征,从而建立流型图像的纹理特征向量,并结合概率神经网络进行训练,实现流型的识别。实验结果表明,该方法能有效地识别气固流化床中鼓泡床、节涌床、湍动床、快速流化床、稀相输送五种典型流型,整体识别率达到98%,为流型识别开辟一条新途径。     

自适应算法在多孔介质气固相反应中的应用

在多孔介质气固相反应动力学实验模型的基础上,运用模糊神经网络技术确立自适应学习算法,然后通过VC实现算法,并将乙氧基化反应实验数据与计算结果进行数据拟合.通过系统的运行和测试的结果分析来看,该模型可以准确快速地确定实验过程中的反应参数,能够有效地缩短多孔介质气固相反应化工产品的开发周期.     

Subset ARMA Model Identification Using Genetic Algorithms

Subset models are often useful in the analysis of stationary time series. Although subset autoregressive models have received a lot of attention, the same attention has not been given to subset autoregressive moving-average (ARMA) models, as their identification can be computationally cumbersome. In this paper we propose to overcome this disadvantage by employing a genetic algorithm. After encoding each ARMA model as a binary string, the iterative algorithm attempts to mimic the natural evolution of the population of such strings by allowing strings to reproduce, creating new models that compete for survival in the next population. The success of the proposed procedure is illustrated by showing its efficiency in identifying the true model for simulated data. An application to real data is also considered.     

Determining phase diagrams of tetrahydrofuran+methane,carbon dioxide or nitrogen clathrate hydrates using an artificial neural network algorithm

In this communication, we have developed a feed-forward artificial neural network algorithm for estimating dissociation pressures of the binary clathrate hydrates of tetrahydrofuran+methane, carbon dioxide or nitrogen as a function of temperature and concentration of tetrahydrofuran in the aqueous solution below/equal its stoichiometric concentration (i.e., 0.056 mole fraction). In order to develop this algorithm, the most reliable experimental data reported in the literature on the dissociation pressures of the aforementioned binary hydrates have been used. Moreover, we report few experimental data on the dissociation pressures of the binary hydrates of tetrahydrofuran+carbon dioxide or nitrogen at 0.011 mole fraction of tetrahydrofuran in aqueous solution, which were measured using an isochoric pressure-search method. The latter experimental data are used to verify the reliability of the corresponding experimental data reported in the literature.     

一类化工过程多变量系统的自适应非线性预测控制

针对化工过程的一类多变量非线性系统,提出了一种自适应非线性预测控制(ANMPC)算法。在采用递归最小二乘法进行预测模型参数在线辨识的基础上,将系统的静态非线性关系用一个反向传播(BP)神经网络稳态模型来表示,通过稳态模型求得的动态增益来进一步校正预测模型的参数。详述了ANMPC控制器设计步骤,通过在一个多变量pH中和过程中的仿真验证了本算法的可行性和有效性。     

Bed expansion of binary mixtures of irregular particles in solid–liquid fluidization: Experimental,empirical correlation,and GA-ANN modelling

Expansion behaviour for a bed of binary mixture of the irregularly shaped particle in Newtonian liquid was measured in two different circular columns. Variations in the physical parameters on the expansion behaviour have been reported. Bed expansion increases with an increase in liquid velocity and a decrease in particle diameter. Static bed height and expansion of the bed are low for higher diameter columns. An empirical correlation has been developed for predicting the ratio of bed height at the fluidized condition to the initial bed height as a function of the physical and dynamic variables related to the system for the binary particle mixtures. The correlation coefficient and variance of the estimate are 0.9299 and 0.0013, respectively, which is acceptable statistical accuracy. A hybrid of the genetic algorithm and neural network modelling for the prediction of the same has also been attempted where the input parameters are optimized using the Levenberg–Marquardt algorithm. With a relative error of 1.46%, the genetic algorithm performed well. So, the modelling has successfully predicted the bed height ratio at fluidized conditions to the initial bed height.     

基于非线性PLS小波基神经网络的动态过程监测

引言对于化工动态过程,当某些过程参数,由于人为的误操作、设备性能的下降、仪表故障以及外部环境的干扰等因素的影响,而偏离最优操作区域较远时,则认为是发生了故障．如果在过程刚偏离正常操作区域时,能够有效地监测出过程异常,就能最大限度地保证过程在优良状态下运行．动态过程监测可以理解为对数据窗内采集到的数据x（t）进行实时分类．本文利用小波变换以及非线性PLS（PartialLeastSquares）算法,提出一种新的基于非线性PLS小波基神经网络的动态过程监测方法,并将其用于动态过程监测．1基于非线性PLS小波基神经网络的动态…     

Combining neural network and genetic algorithms to optimize low NOx pulverized coal combustion

The present work introduces a way of optimizing the low NO_x combustion using the neural network and genetic algorithms for pulverized coal burned utility boiler. The NO_x emission characteristic of a 600 MW capacity boiler operated under different conditions is experimentally investigated and on the basis of experimental results, the artificial neural network is used to describe its NO_x emission property to develop a neural network based model. A genetic algorithm is employed to perform a search to determine the optimum solution of the neural network model, identifying appropriate setpoints for the current operating conditions and the low NO_x emission of the pulverized coal burned boiler is achieved.     

分形多孔介质传热传质过程的格子Boltzmann模拟

针对自然界中实际多孔介质具有的分形特性和随机性,利用中点替代算法和二值化处理构造统计上具有分形特性的随机多孔介质。分析了所构造的多孔介质盒维数与Hurst指数之间的关系。基于随机分形构造的原理,对二维实际多孔介质图像进行了重构。利用两点相关函数,分析了重构图像的结构相关性, 并与实际目标多孔介质的结构特征进行比较。在与解析解对比验证的基础上,将基于二元混合理论的格子Boltzmann模型（LBM）用于模拟多孔介质内流体扩散过程。通过计算不同分形特性的二维多孔介质的有效扩散系数,研究了重构多孔介质的分形维数与有效扩散系数的关系。利用热耦合LBM模型计算多孔介质内传热过程,分析了不同的分形特性对多孔介质蓄热过程的影响。     

基于Co(Ⅱ)配合物前驱体的微纳米Co_3O_4功能材料的研究进展

金属有机骨架化合物(MOFs)是由有机配体和金属节点通过自组装形成的一类具有周期性结构和较大比表面积的材料。目前,选择MOFs材料作为前驱体,经高温焙烧合成纳米金属氧化物或纳米复合金属氧化物材料是一大研究热点。综述了近年来以Co基配位聚合物为前驱体制备纳米Co_3O_4或Co_3O_4/碳纳米复合材料的方法,以及Co_3O_4纳米材料在锂离子电池负极材料、超级电容器、电催化析氧反应、气敏材料及催化剂材料等研究领域的应用,并对其今后的发展进行了展望。     

CORRELATION AND PREDICTION OF VLE OF WATER + CONGENER MIXTURES FOUND IN ALCOHOLIC BEVERAGES USING AN ARTIFICIAL NEURAL NETWORK

Artificial neural networks have been used for the correlation and prediction of vapor-liquid equilibrium data of binary water mixtures found in alcoholic beverage production. The main interest of the study is the accurate modeling of the bubble pressure and concentration of congeners in the vapor phase (substances different from ethanol and water), considered to be an important enological parameter in the alcoholic industry. Nine binary water + congener mixtures were considered for analysis. Vapor-liquid equilibrium data of these systems were taken from the literature (333 data points for training and 111 data points for testing), the artificial neural network results were compared with available literature data, and the accuracy of the modeling is discussed. The study shows that the neural network model is a good alternative method for the estimation of phase equilibrium properties for this type of mixture.

Supplemental materials are available for this article. Go to the publisher's online edition of Chemical Engineering Communications to view the free supplemental file. http://www.informaworld.com/smpp/title~db=all~content=t713454788     

基于改进BP神经网络陶瓷梭式窑火焰图像识别方法

在陶瓷产品生产过程中,不同烧制阶段陶瓷梭式窑烧结带温度发生相应的变化,其对应的火焰图像也随着变化。本文针对陶瓷梭式窑烧结带温度检测提出一种基于改进BP神经网络的火焰图像识别方法。首先对获取的火焰图像利用改进的小波阈值算法去除图像中的噪音进行预处理,其次基于改进的BP神经网络对得到的火焰图像三个分量值R、G、B和测得的火焰温度进行数据拟合,最后测试已训练的神经网络识别火焰图像的效果。实验结果表明,改进后的BP神经网络收敛速度更快、训练时间更短、误差更小,能够更好地检测陶瓷梭式窑火焰图像温度。     

基于复杂网络时空特性的泡沫图像动态纹理特征分析

基于机器视觉的浮选过程监控方法已经被广泛应用于浮选过程中,泡沫表面纹理特征是过程监控的关键视觉特征之一。当前静态纹理特征只能从空间维度描述图像特征,在时间维度上刻画图像序列的内在变化特性存在不足,不能准确反映浮选泡沫浮选过程动态特性。提出了基于复杂网络时空特性的泡沫图像序列动态纹理特征方法。通过将每帧图像的像素点映射到网络各节点,利用邻接矩阵建立复杂网络模型和网络权值动态演化反应不同时刻的图像特征,基于复杂网络时空特性提取泡沫图像序列的动态纹理特征。结合实际生产数据进行仿真验证,实验结果表明该方法可准确识别浮选动态状况,为浮选生产过程的实时调节提供重要的指导信息。     

Determination of steel quality based on discriminating textural feature selection

Image data can be acquired from a product surface in real time by image sensor systems in chemical plants. For quality determination based on these image datasets, effective texture classification methodology is essential to handle highly dimensional images and to extract quality-related information from these product surface images.Wavelet texture analysis is useful for reducing the dimension and extracting textural information from images. Although wavelet texture analysis extracts only textural characteristics from images, the extracted features still contain unnecessary information for classification. The texture analysis method can be improved by retaining only class-dependent features and removing common features. In previous works, best basis and local discriminant basis are the most popular techniques for selecting an important basis from the wavelet packet basis. However, feature selection based on wavelet texture analysis has been studied for texture classification. Because previous methods are designed for wavelet coefficients with features for analysis, their performance is poor with wavelet texture analysis.We propose a novel texture classification methodology for quality determination based on feature selection using wavelet texture analysis. The proposed methodology applies the sequential forward floating selection (SFFS) algorithm as a feature selection strategy to select discriminating wavelet signatures using wavelet texture analysis. The proposed methodology is validated through quality determination for industrial steel surfaces. The results show that the proposed method has fewer classification errors with fewer number of features than previous methods.     

Strategies for Optimizing Feed Rate of Fed-Batch Yeast Fermentation by Fuzzy-Neural Network

In this paper,a novel fuzzy neural network model,in which an adjustable fuzzy sub-space was designed by uniform design,has been established and used in fed-batch yeast fermentationas an example.A brand-new optimization sub-network with special structure has been built andgenetic algorithm,guaranteeing the optimization in overall space,is introduced for the feed rateoptimization.On the basis of the model network,the optimal substrate concentration and theoptimal amount of fed-batch at different periods have been studied,aided with the optimizationnetwork and the genetic algorithm separately.The above results can be used as a basis for theestablishment of a fuzzy neural network controller.     

Evaluation of chloride penetration in high performance concrete using neural network algorithm and micro pore structure

Chloride attack is one of the major causes of deterioration of reinforced concrete structures. In order to evaluate the chloride behavior in concrete, a reasonable prediction for the diffusion coefficient of chloride ion, which governs mechanism of chloride diffusion inside concrete, is basically required. However, it is difficult to obtain chloride diffusion coefficients from experiments due to time and cost limitations.In this study, a numerical technique for chloride diffusion in high performance concrete (HPC) using a neural network algorithm is proposed. In order to collect comparative data on diffusion coefficients in concrete with various mineral admixtures such as ground granulated blast-furnace slag (GGBFS), fly ash (FA), and silica fume (SF), a series of electrically driven chloride penetration tests was performed. Seven material components in various mix designs and duration time are selected as neurons in a back-propagation algorithm, and associated learning of the neural network is carried out. An evaluation technique for chloride behavior in HPC using the obtained diffusion coefficients from the neural network algorithm is developed based on, so-called, Multi-Component Hydration Heat Model (MCHHM) and Micro Pore Structure Formation Model (MPSFM). The applicability of the developed technique is verified by comparing the analytical simulation results and the experimental results obtained in this study. Furthermore, this proposed technique using the neural network algorithm and micro modeling is applied to available experimental data for verification of its applicability.     

基于粒子群优化Hopfield网络匹配的稀相颗粒速度测量

提出了一种基于粒子群算法(PSO)和Hopfield神经网络相结合的粒子跟踪测速算法。该方法采用高速摄影系统拍摄气固两相流的稀相颗粒运动图像,经图像处理后,提取形心参数。将粒子匹配问题转化为优化问题,采用粒子群优化算法与Hopfield神经网络相结合的方法进行优化,求出最优解来实现颗粒的正确匹配,然后计算出颗粒的速度矢量,并与互相关法求出的速度进行对比,实验结果表明,该方法能准确地跟踪稀相颗粒,是一种有效的稀相流场速度测量方法。