Cotton dust particle size distribution in oil mills

Analytical procedures have been developed for characterizing the size and shape of cotton dust particulates collected by the vertical elutriator (VE) sampler. Data are reported for dust distributions on VE filters collected from different processing areas (cleaning, delintering, hulling, and baling) in cottonseed oil mills. Results of particle volume distributions obtained with a Coulter counter are compared with data obtained from an image-analysis system designed to classify cotton dust into fibrous and nonfibrous (particulate) components. The image-analysis data include distributions of the lengths and widths of fibers and the areas and diameters of particles present on the VE filters. In many of the locations studied, a considerable amount of the total dust sampled can be attributed to lint, lint fragments, and also to particles significantly larger than 15 μm diameter. Southern Region, SEA, USDA.     

Discoloration process modeling by neural network

The photo-oxidation of acid orange 52 dye was performed in the presence of H₂O₂, utilizing UV light, aiming the discoloration process modeling and the process variable influence characterization. The discoloration process was modeled by the use of feedforward neural network. Each sample was characterized by five independent variables (dye concentration, pH, hydrogen peroxide volume, temperature and time of operation) and a dependent variable (absorbance). The neural model has also provided, through Garson Partition coefficients and the Pertubation method, the independent variable influence order determination. The results indicated that the time of operation was the predominant variable and reaction mean temperature was the lesser influent variable. The neural model obtained presented coefficients of correlation on the order 0.98, for sets of trainability, validation and testing, indicating the power of prediction of the model and its character of generalization.     

基于BP神经网络的旋风分离器分割粒径模化与预测

为精确建立分割粒径与旋风分离器结构参数和操作参数之间的复杂映射关系,发展了基于数据驱动的BP神经网络（BPNN）的分割粒径模型。使用全局量纲分析,提出环形空间雷诺数、表征旋风分离器本体尺寸影响的量纲为1数和排气芯管插入深度尺寸比作为网络输入参数,表征空气动力等效分割粒径大小的量纲为1尺寸作为网络输出参数,分别确定了训练算法和隐含层神经元个数对BPNN分割粒径模型预测精度的影响。结果表明：贝叶斯正则化算法优于L-M算法和拟牛顿算法,并在隐含层神经元个数为7时达到最优预测性能。与理论模型、半经验模型和多元回归模型进行比较,结果表明,贝叶斯正则化BPNN分割粒径模型展现出了较好的预测能力和泛化性能,模型预测的均方误差为0.136、决定系数为0.975。     

Dynamic neural network modeling for hydrochloric acid recovery process

This paper describes neural network models for the prediction of the concentration profile of a hydrochloric acid recovery process consisting of double fixed-bed ion exchange columns. The process is used to remove the Fe²⁺ and Fe³⁺ ion from the pickling liquor, resulting in increasing the acid concentration for reusing in the pickling process. Due to the complexity and highly nonlinearity of the process, the modeling of the process based on the first principle is difficult and involve too many unknown parameters. Therefore, an attractive alternative technique, neural network modeling, has been applied to model this system because of its ability to model a complex nonlinear process, even when process understanding is limited. The process data sets are gathered from a real hydrochloric acid recovery pilot plant and used for neural network training and validation. Backpropagation and Lenvenberg-Marquardt techniques are used to train various neural network architectures, and the accuracy of the obtained models have been examined by using test data set. The optimal neural network architectures of this process can be determined by MSE minimization technique. The simulation results have shown that multilayer feedforward neural network models with two hidden layers provide sufficiently accurate prediction of the concentration profile of the process.     

Artificial neural network modeling for predicting melt blowing processing

An artificial neural network model is established for predicting the fiber diameter of melt blown nonwoven fabrics from the processing parameters. An attempt is made to study the effect of the number of hidden layers and hidden layer neurons to minimize the prediction error. The artificial neural network with three hidden layers (5, 2, and 3 neurons in the first, second, and third hidden layer, respectively) yields the minimum prediction error and thus is determined as the preferred network. The square of the correlation coefficient of measured and predicted fiber diameters shows the good performance of the model. Using the established ANN model, computer simulations of the effects of the processing parameters on the fiber diameter are carried out. The results show great promise for this research in the field of computer assisted design of melt blowing technology. © 2005 Wiley Periodicals, Inc. J Appl Polym Sci 99: 424–429, 2006     

Evolutionary polymorphic neural network in chemical process modeling

Evolutionary polymorphic neural network (EPNN) is a novel approach to modeling dynamic process systems. This approach has its basis in artificial neural networks and evolutionary computing. As demonstrated in the studied dynamic CSTR system, EPNN produces less error than a traditional recurrent neural network with a less number of neurons. Furthermore, EPNN performs networked symbolic regressions for input–output data, while it performs multiple step ahead prediction through adaptable feedback structures formed during evolution. In addition, the extracted symbolic formulae from EPNN can be used for further theoretical analysis and process optimization.     

Emission control in palm oil mills using artificial neural network and genetic algorithm

The present study utilized a combination of artificial neural network (ANN) and genetic algorithms (GA) to optimize the release of emission from the palm oil mill. A model based on ANN is developed from the actual data taken from the palm oil mill. The predicted data agree well with the actual data taken. GA is then employed to find the optimal operating conditions so that the overlimit release of emission is reduced to the allowable limit.     

A neural network-based soft sensor for particle size distribution using image analysis

Many industrial processes require on-line measurement of particle size and particle size distribution for process monitoring and control. The available techniques for reliable on-line measurement are, however, limited. In this paper, based on the captured surface images of randomly disarranged ore particles, the image uniformity was characterized. Particle size distribution was then investigated by applying a neural network-based modeling with the obtained image uniformity. The proposed soft sensor provides an improved prediction model and can be used for real time measurement of particle size distribution in the industrial operations.     

Artificial neural network modeling for predicting melt‐blowing processing

An artificial neural network (ANN) model is established for predicting the fiber diameter of melt‐blown nonwoven fabrics from the processing parameters. An attempt is made to study the effect of the number of the hidden layers and the hidden layer neurons to minimize the prediction error. The artificial neural network with three hidden layers (5, 2, and 3 neurons in the first, second, and third hidden layer, respectively) yields the minimum prediction error, and thus, is determined as the preferred network. The square of correlation coefficient of measured and predicted fiber diameters shows the good performance of the model. Using the established ANN model, computer simulations of the effects of the processing parameter on the fiber diameter are carried out. The results show great prospects for this research in the field of computer‐assisted design of melt‐blowing technology. © 2006 Wiley Periodicals, Inc. J Appl Polym Sci 101: 4275–4280, 2006     

多频率系统动态插值神经网络软测量建模

针对某些化工过程关键变量难以在线测量的问题,提出了一种基于多采样率系统的时间序列神经网络的软测量建模方法,建立了动态插值神经网络模型,并利用增强粒子群算法实现了网络参数的优化。将此方法用于实验室模拟建模,实现了变量的在线预估,并对网络的训练效果和泛化性能进行了分析,表明其建模效果明显优于普通静态神经网络。     

Pore‐network modeling of particle retention in porous media

Transport and filtration of micron and submicron particles in porous media is important in applications such as water purification, contaminants dispersion, and drilling mud invasion. Existing macroscopic models often fail to be predictive without empirical adjustments and a more fundamental approach may be required. We develop a physically‐representative, 3D pore network model based on a particle tracking method to simulate particle retention and permeability impairment in polydisperse particle systems. The model includes the effect of hydraulic drag, gravity, electrostatic and van der Waals forces, as well as Brownian motion. A converging‐diverging pore throat geometry is used to capture the mechanism of interception. With the analytical solution of fluid velocity within a pore throat, the trajectory of each particle is calculated explicitly. We also incorporate surface roughness and particle–surface interaction to determine particle attachment and detachment. Pore throat structure and conductivity are updated dynamically to account for the effect of deposited particles. Predictions of effluent concentration and macroscopic filtration coefficient are in good agreement with published experimental data. We find that the filtration coefficient is dependent on the relative angle between fluid flow and gravity. Particle deposition by interception is significant for large particle/grain size ratios. Brownian diffusion is the primary cause of retention at low Peclet numbers, especially for small gravity numbers. Particle size distribution is found to be a cause of hyperexponential deposition often observed in experiments. Permeability reduction was small for strong repulsive forces because particles only deposited in paths of slow velocity. © 2017 American Institute of Chemical Engineers AIChE J, 63: 3118–3131, 2017     

Empirical and scale-up modeling in stirred ball mills

Stirred ball mills are frequently used for ultrafine- and nanogrinding in food, pharmaceutical and chemical industry, but only few investigations have been published on empirical or scale-up modeling of stirred ball mills. Experiments have been carried out with a laboratory scale stirred ball mill. During the experiments the main technical parameters such as stirrer speed, grinding media, filling ratio, grinding time and the solid mass concentration have been systematically adjusted. The particle size distribution of mill products can be well estimated by empirical functions, so an empirical model has been prepared for the laboratory mill. The relation between the grinding fineness, grinding time and specific grinding work was represented for several materials such as pumice, andesite, limestone and tailings of ore mining industry. The power consumption of the stirred ball mill for scale-up was determined by a method based on the dimensional analysis. A new scale-up model has been presented as well by with industrial size stirred ball mills can be designed on the basis of the laboratory measurements.     

Artificial neural network modeling for prediction of binary surface tension containing ionic liquid

In this study, a feed-forward multilayer perceptron neural network is applied to predict the surface tension of 32 binary ionic liquids (ILs)/non-ILs systems using melting point (Tm), molecular weight (Mw) and mole fraction of ILs as well as Tm and Mw of non-IL components. The data are divided into two different subsets, namely training and testing subsets, to obtain the optimum parameters of the used network and to evaluate the correlative capability of the trained network. The results of the test stage show excellent capability of the proposed network to predict/correlate the binary surface tension of ILs/non-ILs systems (AARD%: 0.93, MSE: 6.67 × 10^?7 and R²: 0.9950).     

Reinforcing the phenomenological consistency in artificial neural network modeling of multiphase reactors

Artificial neural networks (ANN) aided with dimensional analysis have been successfully applied in multiphase reactors modeling when considerable amount of experimental data (or database) is available. An important problem that stemmed from this approach was the ambiguity to select the fittest combination of dimensionless numbers to be used as ANN inputs to predict a variable of interest. A genetic algorithm (GA) based methodology was proposed to optimize the combination of inputs by taking into account the phenomenological consistency (PC) of the resulting ANN models along with their fitting capabilities. PC is a measure of the capability of an ANN model to simulate outputs with specified gradient conditions with respect to the process variables. These conditions are imposed based on a priori knowledge of the system's behavior. PC used to be evaluated in the vicinity of a particular point in the database space. The novelty of the approach was the extension of the PC test around all the points available in the training data set. This technique may be regarded as a robust method to prevent data overfitting when the function to be learned by ANN is characterized by a monotonic behavior with respect to some of the process variables. The new approach was illustrated using as a case study the correlation of two-phase pressure drop in randomly packed beds with countercurrent flow.     

Measurement based modeling and control of bimodal particle size distribution in batch emulsion polymerization

In this article, a novel modeling approach is proposed for bimodal Particle Size Distribution (PSD) control in batch emulsion polymerization. The modeling approach is based on a behavioral model structure that captures the dynamics of PSD. The parameters of the resulting model can be easily identified using a limited number of experiments. The resulting model can then be incorporated in a simple learning scheme to produce a desired bimodal PSD while compensating for model mismatch and/or physical parameters variations using very simple updating rules. © 2010 American Institute of Chemical Engineers AIChE J, 2010     

基于物理信息神经网络的传热过程物理场代理模型的构建

物理信息的神经网络（PINN）通过构建结构化的深度神经网络体系,可以有效地耦合基于物理定律的非线性偏微分方程组（如Navier-Stokes方程）,能够在较少量的边界数据条件下解决监督学习问题。但是,PINN训练效果与边界条件的设置方式密切相关。本工作以具有内热源的二维稳态导热方程和平板间二维稳态对流传热方程为案例,基于软边界和硬边界两种设定方法构建PINN。将训练所得到的代理模型预测温度场输出,并将其与软件模拟结果进行验证分析,结果表明硬边界PINN代理模型预测能力较优。     

Genetic optimization of neural network and fuzzy logic for oil bubble point pressure modeling

Bubble point pressure is a critical pressure-volume-temperature (PVT) property of reservoir fluid, which plays an important role in almost all tasks involved in reservoir and production engineering. We developed two sophisticated models to estimate bubble point pressure from gas specific gravity, oil gravity, solution gas oil ratio, and reservoir temperature. Neural network and adaptive neuro-fuzzy inference system are powerful tools for extracting the underlying dependency of a set of input/output data. However, the mentioned tools are in danger of sticking in local minima. The present study went further by optimizing fuzzy logic and neural network models using the genetic algorithm in charge of eliminating the risk of being exposed to local minima. This strategy is capable of significantly improving the accuracy of both neural network and fuzzy logic models. The proposed methodology was successfully applied to a dataset of 153 PVT data points. Results showed that the genetic algorithm can serve the neural network and neurofuzzy models from local minima trapping, which might occur through back-propagation algorithm.     

基于深层神经网络的多输出自适应软测量建模

在污水处理运行过程中,多个重要的难测过程变量的存在,不仅妨碍了生产过程的监控,而且阻碍了过程控制策略的调整或优化。即使软测量模型得到合理的构建,在投入运行后仍然遭受性能的退化和同时带来的高昂的维护成本。此外,合适辅助变量的选取直接影响后续建模的效果。因此,文中提出了一种基于深层神经网络的多输出自适应软测量模型,用于污水处理过程中多个目标变量的同步在线预测。其中,深层神经网络基于一种栈式自编码而构建,在极端复杂场景下具有优异的在线预测性能;并在建模中引入时差建模和变量重要性投影（VIP）这两种算法,以应对性能退化问题和实现辅助变量的精选。最后,通过一个实际案例对所提出模型进行验证。结果表明,所提出的软测量模型不仅具有较好的多输出预测性能,且在单目标预测结果上也有不错的表现。