Prediction of the Particle Size Distribution Parameters in a High Shear Granulation Process Using a Key Parameter Definition Combined Artificial Neural Network Model

Yu, Huiman; Fu, Jinsheng; Dang, Leping; Yuensin, Cheong; Tan, Hongsing; Wei, Hongyuan

doi:10.1021/acs.iecr.5b02679

Cited by 16 publications

(14 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Aggregation of NP, in spite of being the focus of ongoing studies in aqueous media [45,95,322,[326][327][328] [134,204,205,288,333], ZnO [75,137,206,207,224], and AlO NP [329,330] ( Table 2). The results of batch experiments may not be a real indicator of the particle conditions in porous media because aggregation in batch experiment in absence of flow can lack at least one of the main driving mechanisms of aggregation; that is orthokinetic aggregation [21,45,206,249,315].…”

Section: Definitions and Observationsmentioning

confidence: 99%

Continuum-based models and concepts for the transport of nanoparticles in saturated porous media: A state-of-the-science review

Babakhani¹,

Bridge

Doong³

et al. 2017

Advances in Colloid and Interface Science

143

View full text Add to dashboard Cite

Environmental applications of nanoparticles (NP) increasingly result in widespread NP distribution within porous media where they are subject to various concurrent transport mechanisms including irreversible deposition, attachment/detachment (equilibrium or kinetic), agglomeration, physical straining, site-blocking, ripening, and size exclusion. Fundamental research in NP transport is typically conducted at small scale, and theoretical mechanistic modeling of particle transport in porous media faces challenges when considering the simultaneous effects of transport mechanisms. Continuum modeling approaches, in contrast, are scalable across various scales ranging from column experiments to aquifer. They have also been able to successfully describe the simultaneous occurrence of various transport mechanisms of NP in porous media such as blocking/straining or agglomeration/deposition/detachment. However, the diversity of model equations developed by different authors and the lack of effective approaches for their validation present obstacles to the successful robust application of these models for describing or predicting NP transport phenomena. This review aims to describe consistently all the important NP transport mechanisms along with their representative mathematical continuum models as found in the current scientific literature. Detailed characterizations of each transport phenomenon in regards to their manifestation in the column experiment outcomes, i.e., breakthrough curve (BTC) and residual concentration profile (RCP), are presented to facilitate future interpretations of BTCs and RCPs. The review highlights two NP transport mechanisms, agglomeration and size exclusion, which are potentially of great importance in controlling the fate and transport of NP in the subsurface media yet have been widely neglected in many existing modeling studies. A critical limitation of the continuum modeling approach is the number of parameters used upon application to larger scales and when a series of transport mechanisms are involved. We investigate the use of simplifying assumptions, such as the equilibrium assumption, in modeling the attachment/detachment mechanisms within a continuum modelling framework. While acknowledging criticisms about the use of this assumption for NP deposition on a mechanistic (process) basis, we found that its use as a description of dynamic deposition behavior in a continuum model yields broadly similar results to those arising from a kinetic model. Furthermore, we show that in two dimensional (2-D) continuum models the modeling efficiency based on the Akaike information criterion (AIC) is enhanced for equilibrium vs kinetic with no significant reduction in model performance. This is because fewer parameters are needed for the equilibrium model compared to the kinetic model. Two major transport regimes are identified in the transport of NP within porous media. The first regime is characterized by higher particle-surface attachment affinity than particle-particle attachment affinity, and operat...

show abstract

Section: Definitions and Observationsmentioning

confidence: 99%

Continuum-based models and concepts for the transport of nanoparticles in saturated porous media: A state-of-the-science review

Babakhani¹,

Bridge

Doong³

et al. 2017

Advances in Colloid and Interface Science

143

View full text Add to dashboard Cite

show abstract

“…We adopted a three-layer configuration for the ANN model as commonly used in the literature [Gevrey et al, 2006;Nourani and Sayyah-Fard, 2012;Yu et al, 2015a]. These layers comprise an input layer, a hidden layer, and an output layer.…”

Section: Artificial Neural Network Modeling Proceduresmentioning

confidence: 99%

“…This procedure is called training of the network. Once these weights and biases are estimated, the network can be used for prediction of unknown outputs of a new data set [ Yu et al ., ].…”

Section: Artificial Neural Network Modeling Proceduresmentioning

confidence: 99%

“…Although the outcomes of their paper provide very useful insights into the retention behavior of NP in porous media, they are limited to regression analysis of retained fraction and retained mass profiles of NP in porous media. The artificial neural network (ANN) is a powerful algorithm which emulates the processing system of the human brain in terms of the structure and interactions of neurons with the information signals [ Lu et al ., ; Maier and Dandy , ; Morshed and Kaluarachchi , ; Nourani and Sayyah‐Fard , ; Yu et al ., ]. This concept, which was originally proposed in 1940s by McCulloch and Pitts [], has been introduced as a versatile and universal tool for function approximation problems, especially in nonlinear systems, where other mathematical/mechanistic techniques are difficult to implement [ Morshed and Kaluarachchi , ; Nourani et al ., ; Yerramareddy et al ., ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Parameterization and prediction of nanoparticle transport in porous media: A reanalysis using artificial neural network

Babakhani

Bridge

Doong

et al. 2017

Water Resources Research

View full text Add to dashboard Cite

The continuing rapid expansion of industrial and consumer processes based on nanoparticles (NP) necessitates a robust model for delineating their fate and transport in groundwater. An ability to reliably specify the full parameter set for prediction of NP transport using continuum models is crucial. In this paper we report the reanalysis of a data set of 493 published column experiment outcomes together with their continuum modeling results. Experimental properties were parameterized into 20 factors which are commonly available. They were then used to predict five key continuum model parameters as well as the effluent concentration via artificial neural network (ANN)-based correlations. The Partial Derivatives (PaD) technique and Monte Carlo method were used for the analysis of sensitivities and model-produced uncertainties, respectively. The outcomes shed light on several controversial relationships between the parameters, e.g., it was revealed that the trend of K att with average pore water velocity was positive. The resulting correlations, despite being developed based on a ''black-box'' technique (ANN), were able to explain the effects of theoretical parameters such as critical deposition concentration (CDC), even though these parameters were not explicitly considered in the model. Porous media heterogeneity was considered as a parameter for the first time and showed sensitivities higher than those of dispersivity. The model performance was validated well against subsets of the experimental data and was compared with current models. The robustness of the correlation matrices was not completely satisfactory, since they failed to predict the experimental breakthrough curves (BTCs) at extreme values of ionic strengths. Plain Language Summary Models based on advection-dispersion-equation (ADE), have succeeded in describing a variety of nanoparticle (NP) transport mechanisms within subsurface porous media. These models are usually fitted against known observation data to obtain the unknown parameters. Nevertheless, the parameters determined in this way cannot be used for a new problem of the same type and again there exists the need for the data to calibrate the model parameters for a new problem. Black box models, such as artificial neural network (ANN), have been mostly, if not all the times, used in the same way of ADE models, i.e., single problem solver. In this paper we use the ability of ANN to develop a series of simple correlation matrices that can be easily used for the prediction of ADE parameters in the new problem without the need for additional calibration. Although comparisons between ANN model predictions and experimental data show that there is still further work to be done, our approach out-performs other comparable models and offers new insight into the complex interactions among the factors determining NP transport and fate in the environment.

show abstract

“…Such modelling paradigms are, in fact, incapable of accounting for the sophisticated nonlinear relationships or even the complex interactions among the inputs parameters that control the granulation process [10]. Artificial Neural Networks (ANN) and Fuzzy Systems have been investigated previously to predict the properties of granules and to scale-up the granulation processes [13][14][15][16]. However, because these so-called soft-computing techniques represent powerful interpolators there exist no guarantees that they will perform well beyond the training range [10].…”

Section: Introductionmentioning

confidence: 99%

Predictive modelling of the granulation process using a systems-engineering approach

2016

View full text Add to dashboard Cite

Prediction of the Particle Size Distribution Parameters in a High Shear Granulation Process Using a Key Parameter Definition Combined Artificial Neural Network Model

Cited by 16 publications

References 39 publications

Continuum-based models and concepts for the transport of nanoparticles in saturated porous media: A state-of-the-science review

Continuum-based models and concepts for the transport of nanoparticles in saturated porous media: A state-of-the-science review

Parameterization and prediction of nanoparticle transport in porous media: A reanalysis using artificial neural network

Predictive modelling of the granulation process using a systems-engineering approach

Contact Info

Product

Resources

About