Hybrid neural network model of an industrial ethanol fermentation process considering the effect of temperature

In this work a procedure for the development of a robust mathematical model for an industrial alcoholic fermentation process was evaluated. The proposed model is a hybrid neural model, which combines mass and energy balance equations with functional link networks to describe the kinetics. These networks have been shown to have a good nonlinear approximation capability, although the estimation of its weights is linear. The proposed model considers the effect of temperature on the kinetics and has the neural network weights reestimated always so that a change in operational conditions occurs. This allow to follow the system behavior when changes in operating conditions occur.     

Adaptive optimal control of fed-batch alcoholic fermentation

An adaptive control scheme is developed for the optimization of a fed-batch ethanol production process. The fermentation process is modeled by an hybrid neural model combining mass balance equations and neural networks, used to represent the kinetic rates. The networks used, the functional link networks (FLN), allow the linear estimation of their parameters; this enables the re-estimation of the parameters at each sampling time, and thus the development of an adaptive optimal control scheme.     

A hybrid neural model of ethanol production by Zymomonas mobilis

A hybrid neural model was developed for the alcoholic fermentation by Zymomonas mobilis. This model is composed by the mass-balance equations of the process and neural networks, which describe the kinetic rates. Strategies that combines scarce experimental data with approximate models of the process were used to generate new data for the training of the networks, minimizing the number of experiments required. The proposed hybrid neural methodology uses all the information avail able about the process to deal with the difficulties in the development of the model.     

Model Reduction in Emulsion Polymerization Using Hybrid First Principles/Artificial Neural Networks Models, 2

Summary: A “series” hybrid model based on material balances and artificial neural networks to predict the evolution of weight average molecular weight, , in semicontinuous emulsion polymerization with long chain branching kinetics is presented. The core of the model is composed by two artificial neural networks (ANNs) that calculate polymerization rate, R_p, and instantaneous weight‐average molecular weight, from reactor process variables. The subsequent integration of the material balances allowed to obtain the time evolution of conversion and , along the polymerization process. The accuracy of the proposed model under a wide range of conditions was assessed. The low computer‐time load makes the hybrid model suitable for optimization strategies.

Effect of the monomer feed rate on .     

Characterization of in vitro neural functional connectivity on a neurofluidic device

Understanding the mechanism of functional connectivity in neural system is of great benefit to lot of researches and applications. Microfluidics and microelectrode arrays (MEAs) have been frequently utilized for in vitro neural cultures study. However, there are few studies on the functional connectivity of neural cultures grown on a microfluidic chip. It is intriguing to unveil the influences of microfluidic structures on in vitro neuronal networks from the perspective of functional connectivity. Hence, in the present study, a device was established, which comprised a microfluidic chamber for cell growth and a MEA substrate for recording the electrophysiological response of the neuronal networks. The network topology, neural firing rate, neural bursting rate and network burst frequency were adopted as representative characteristics for neuronal networks analysis. Functional connectivity was estimated by means of cross‐covariance analysis and graph theory. The results demonstrated that the functional connectivity of the in vitro neuronal networks formed in the microchannel has been apparently reinforced, corresponding to improve neuronal network density and increased small‐worldness.     

Simulation of aerated lagoon using artificial neural networks and multivariate regression techniques

The aim of this study was to develop an empirical model that provides accurate predictions of the biochemical oxygen demand of the output stream from the aerated lagoon at International Paper of Brazil, one of the major pulp and paper plants in Brazil. Predictive models were calculated from functional link neural networks (FLNNs), multiple linear regression, principal components regression, and partial least-squares regression (PLSR). Improvement in FLNN modeling capability was observed when the data were preprocessed using the PLSR technique. PLSR also proved to be a powerful linear regression technique for this problem, which presents operational data limitations.     

Generic schemes for single-molecule kinetics. 1: Self-consistent pathway solutions for renewal processes

In this paper, we discuss a strategy for reducing a complex single molecule kinetic process to a set of generic structures (motifs) that are building blocks for a general kinetic scheme. In general, these motifs have complex kinetics (i.e., waiting time distribution functions) which are composed of fundamental kinetic steps. (1) First, we treat four different experimental single molecule measurements within both the usual kinetic framework (i.e., using the rate matrix) and the waiting time distribution function framework. The two frameworks are then shown to be equivalent and can be formulated on the basis of the first passage time distribution function of monitored single molecule events. (2) Second, to calculate this basic quantity, we decompose a complex kinetic scheme with the help of two kinetic motifs, sequential and branching, and derive self-consistent equations by convoluting waiting time distributions and first passage time distribution(s) along the reaction pathway(s). (3) As examples, two experimental systems, a chain reaction model with a special case of enzymatic reactions and a general kinetic model for fluorescence emission, are analyzed on the basis of a generic scheme composed of a monitored link, controlled link, and unknown link, each representing a possible subscheme associated with a complex waiting time distribution function. As a result, single molecule measurements of the generic scheme retain the same functional form when a kinetic link is altered within a subscheme, and different measurements can be classified and analyzed within the same framework. (4) Finally, to explore the physical reasons for nonexponential waiting time distribution, we use the example of blinking phenomena to discuss several scenarios of dynamic and static disorder and their implications for observed memory effects. The self-consistent pathway formalism is presented in this paper for renewal processes and will be generalized to nonrenewal processes with memory effects in a future publication.     

Phenomenological and neural-network modeling of cephalosporin C production bioprocess

Cephalosporin C production process withCephalosporium acremonium ATCC 48272 in synthetic medium was investigated and the experimental results allowed the development of a mathematical model describing the process behavior. The model was able to explain fairly well the diauxic phenomenon, higher growth rate during the glucose-consumption phase, and the production occurring only in the sucrose-consumption phase. Moreover, the process was simulated utilizing the neural-networks technique. Two feed-forward neural-networks with one hidden layer were employed. Both models, phenomenological and neural-networks based, satisfactorily describe the bioprocess. The difficulties in determining kinetic parameters are avoided when neural networks are utilized.     

The acid-catalyzed polycondensation of furfuryl alcohol: Old puzzles unravelled

This paper describes mechanistic studies aimed at understanding the origin of two important side events accompanying the linear polycondensation of furfuryl alcohol in acidic media. The first process concerns the formation of conjugated sequences along the polymeric chains. The use of model monomers and compounds simulating the structure of the linear polymer provided for the first time a full understanding of the reactions leading to multiple unsaturations. The main culprits for this process are the labile hydrogen atoms on the methylene moiteties bridging the furan rings. The second anomaly in these systems concerns the formation of networks following a complex branching mechanism. Again, model structures helped to pinpoint the origin of this process and to propose plausible reactions to describe it.     

Reactions ofOrtho-quinones and the model compound 4-t-butyl-1,2-benzo-quinone in alkaline peroxide

The literature on the occurence and reactions of quinone structures in mechanical pulps has been reviewed. A study on the reactions of a quinone model compound (4-t-butyl-1,2-benzoquinone) in alkaline hydrogen peroxide has been reported, with detailed analysis of reaction products and kinetic phenomena. The study reveals that the diversity of products formed is much more complex than that obtained using an α,β-unsaturated aldehyde as a model, a simple second-order expression can be used to describe the kinetics. The kinetics representing chromophore removal for the two classes of model compound are compared with previously reported studies of kinetic phenomena during bleaching of mechanical pulps.     

Efficient chemical kinetic modeling through neural network maps

An approach to modeling nonlinear chemical kinetics using neural networks is introduced. It is found that neural networks based on a simple multivariate polynomial architecture are useful in approximating a wide variety of chemical kinetic systems. The accuracy and efficiency of these ridge polynomial networks (RPNs) are demonstrated by modeling the kinetics of H(2) bromination, formaldehyde oxidation, and H(2)+O(2) combustion. RPN kinetic modeling has a broad range of applications, including kinetic parameter inversion, simulation of reactor dynamics, and atmospheric modeling.     

Software sensors for monitoring of a solid waste composting process

Process identification for composting of tobacco solid waste in an aerobic, adiabatic batch reactor was carried out using neural network-based models which utilized the nonlinear finite impulse response and nonlinear autoregressive model with exogenous inputs identification methods. Two soft sensors were developed for the estimation of conversion. The neural networks were trained by the adaptive gradient method using cascade learning. The developed models showed that the neural networks could be applied as intelligent software sensors giving a possibility of continuous process monitoring. The models have a potential to be used for inferential control of composting process in batch reactors. Presented at the 33rd International Conference of the Slovak Society of Chemical Engineering, Tatranské Matliare, 22–26 May 2006.     

Neural networks for prediction of ultrafiltration transmembrane pressure – application to drinking water production

Modelling of ultrafiltration plants for drinking water production appears as a necessary step before plants control and supervisory. It first requires a better knowledge about membrane fouling by natural waters. The phenomena involved are very complex, because of the nature of the fluid concerned: water. Thus up to now phenomenological model cannot be applied for resource waters. Because of their properties, new modelling tools called neural networks seem to be a promising way to model complex phenomena and therefore to be applied to water treatment. In the present study a neural network is used to model the time evolution of transmembrane pressures for ultrafiltration membranes applied to drinking water production. Different network structures and architectures have been elaborated and evaluated with the aim of computing the pressure at the end of a filtration cycle and after the next backwash. For some of these networks a very good accuracy is obtained for both pressures predictions. The inlets are permeate flow rate, turbidity during the cycle and pressure measurements at the cycle start and at the end of the previous cycle. These networks are able to model the effect of both reversible and irreversible fouling on pressures even if no inlet parameter concerning organic matters is considered.