Neural network models for biological waste-gas treatment systems

This paper outlines the procedure for developing artificial neural network (ANN) based models for three bioreactor configurations used for waste-gas treatment. The three bioreactor configurations chosen for this modelling work were: biofilter (BF), continuous stirred tank bioreactor (CSTB) and monolith bioreactor (MB). Using styrene as the model pollutant, this paper also serves as a general database of information pertaining to the bioreactor operation and important factors affecting gas-phase styrene removal in these biological systems. Biological waste-gas treatment systems are considered to be both advantageous and economically effective in treating a stream of polluted air containing low to moderate concentrations of the target contaminant, over a rather wide range of gas-flow rates. The bioreactors were inoculated with the fungus Sporothrix variecibatus, and their performances were evaluated at different empty bed residence times (EBRT), and at different inlet styrene concentrations (C(i)). The experimental data from these bioreactors were modelled to predict the bioreactors performance in terms of their removal efficiency (RE, %), by adequate training and testing of a three-layered back propagation neural network (input layer-hidden layer-output layer). Two models (BIOF1 and BIOF2) were developed for the BF with different combinations of easily measurable BF parameters as the inputs, that is concentration (gm(-3)), unit flow (h(-1)) and pressure drop (cm of H(2)O). The model developed for the CSTB used two inputs (concentration and unit flow), while the model for the MB had three inputs (concentration, G/L (gas/liquid) ratio, and pressure drop). Sensitivity analysis in the form of absolute average sensitivity (AAS) was performed for all the developed ANN models to ascertain the importance of the different input parameters, and to assess their direct effect on the bioreactors performance. The performance of the models was estimated by the regression coefficient values (R(2)) for the test data set. The results obtained from this modelling work can be useful for obtaining important relationships between different bioreactor parameters and for estimating their safe operating regimes.     

Neural network modeling of the light profile in a novel photobioreactor

An artificial neural network (ANN) was implemented to model the light profile pattern inside a photobioreactor (PBR) that uses a toroidal light arrangement. The PBR uses Tequila vinasses as culture medium and purple non-sulfur bacteria Rhodopseudomonas palustris as biocatalyzer. The performance of the ANN was tested for a number of conditions and compared to those obtained by using deterministic models. Both ANN and deterministic models were validated experimentally. In all cases, at low biomass concentration, model predictions yielded determination coefficients greater than 0.9. Nevertheless, ANN yielded the more accurate predictions of the light pattern, at both low and high biomass concentration, when the bioreactor radius, the depth, the rotational speed of the stirrer and the biomass concentration were incorporated in the ANN structure. In comparison, most of the deterministic models failed to correlate the empirical data at high biomass concentration. These results show the usefulness of ANNs in the modeling of the light profile pattern in photobioreactors.     

Closed loop identification of transfer function model for unstable bioreactors for tuning PID controllers

Closed loop identification of transfer function model for an unstable bioreactor is proposed based on an optimization method using either a step or a pulse response of PI/PID controlled bioreactor. A simple method is proposed for the initial guesses of the parameters of the first order plus time delay (FOPTD) transfer function model. A PID controller is designed for the identified model. Simulation study on the nonlinear model equations of an unstable bioreactor exhibiting multiple steady-states shows that the PID controller designed on the identified FOPTD model gives a good closed loop response similar to the one designed based on the linearized model from the nonlinear model equations.     

Fuzzy logic control of a fed-batch fermentor

A rule-based fuzzy logic control is developed for control of penicillin concentration in a fed-batch bioreactor. The membership functions, fuzzy ranges for the error and for the controller output are defined. A fuzzy rule base is constructed relating error to the control output based on operators' knowledge. The performance of the fuzzy-logic controller is evaluated by simulating a mathematical model of the fed-batch bioreactor.     

Hybrid modeling of xanthan gum bioproduction in batch bioreactor

This work is focused on hybrid modeling of xanthan gum bioproduction process by Xanthomonas campestris pv. mangiferaeindicae. Experiments were carried out to evaluate the effects of stirred speed and superficial gas velocity on the kinetics of cell growth, lactose consumption and xanthan gum production in a batch bioreactor using cheese whey as substrate. A hybrid model was employed to simulate the bio-process making use of an artificial neural network (ANN) as a kinetic parameter estimator for the phenomenological model. The hybrid modeling of the process provided a satisfactory fitting quality of the experimental data, since this approach makes possible the incorporation of the effects of operational variables on model parameters. The applicability of the validated model was investigated, using the model as a process simulator to evaluate the effects of initial cell and lactose concentration in the xanthan gum production.     

Control of unstable bioreactor using fuzzy tuned PI controller

A fuzzy tuning scheme for conventional PI controller is developed for controlling an unstable continuous bioreactor. The performance is compared with that of a fixed setting conventional PI controller. The performance of the tuning scheme is studied by simulating the non-linear model equations of the bioreactor. The robustness of the controller is also studied for uncertainties in the process parameters such as yield factor and measurement delay. Simulation results show that the fuzzy tuning improves the overall performance and particularly it is more robust to parameter uncertainties.     

Adaptive dissolved oxygen control through the glycerol feeding in a recombinant Pichia pastoris cultivation in conditions of oxygen transfer limitation

In high cell density cultivation processes the productivity is frequently constrained by the bioreactor maximum oxygen transfer capacity. The productivity can often be increased by operating the process at low dissolved oxygen concentrations close to the limitation level. This may be accomplished with a closed-loop controller that regulates the dissolved oxygen concentration by manipulating the dominant carbon source feeding rate. In this work we study this control problem in a pilot 50l bioreactor with a high cell density recombinant P. pastoris cultivation in complex media. The study focuses on the design of accurate stable adaptive controllers, with guaranteed exponential convergence and its relation with the calibration of controller parameters. Two adaptive control strategies were tested in the pilot bioreactor: a model reference adaptive controller with a linear reference model and an integral feedback controller with adaptive gain. The latter alternative proved to be more robust to errors in the measurements of the off-gas composition. Concerning the instrumentation, algorithms were derived assuming that both the dissolved oxygen tension and off-gas composition are measured on-line, but also the case of only dissolved oxygen being measured is addressed. It was verified that the measurement of off-gas composition might not improve the controller performance due to measurement and process time delays.     

Predictive modelling of Fe(III) precipitation in iron removal process for bioleaching circuits

In this study, the applicability of three modelling approaches was determined in an effort to describe complex relationships between process parameters and to predict the performance of an integrated process, which consisted of a fluidized bed bioreactor for Fe³⁺ regeneration and a gravity settler for precipitative iron removal. Self-organizing maps were used to visually evaluate the associations between variables prior to the comparison of two different modelling methods, the multiple regression modelling and artificial neural network (ANN) modelling, for predicting Fe(III) precipitation. With the ANN model, an excellent match between the predicted and measured data was obtained (R ² = 0.97). The best-fitting regression model also gave a good fit (R ² = 0.87). This study demonstrates that ANNs and regression models are robust tools for predicting iron precipitation in the integrated process and can thus be used in the management of such systems.     

Adapting a Feedforward Heteroassociative Network to Hodgkin-Huxley Dynamics

Using the original McCulloch-Pitts notion of simple on and off spike coding in lieu of rate coding, an Anderson-Kohonen artificial neural network (ANN) associative memory model was ported to a neuronal network with Hodgkin-Huxley dynamics. In the ANN, the use of 0/1 (no-spike/spike) units introduced a cross-talk term that had to be compensated by introducing balanced feedforward inhibition. The resulting ANN showed good capacity and fair selectivity (rejection of unknown input vectors). Translation to the Hodgkin-Huxley model resulted in a network that was functional but not at all robust. Evaluation of the weaknesses of this network revealed that it functioned far better using spike timing, rather than spike occurrence, as the code. The algorithm requires a novel learning algorithm for feedforward inhibition that could be sought physiologically.     

Modeling force-velocity relation in skeletal muscle isotonic contraction using an artificial neural network

The aim of this study is to design an artificial neural network (ANN) to model force-velocity relation in skeletal muscle isotonic contraction. We obtained the data set, including physiological and morphometric parameters, by myography and morphometric measurements on frog gastrocnemius muscle. Then, we designed a multilayer perceptron ANN, the inputs of which are muscle volume, muscle optimum length, tendon length, preload, and afterload. The output of the ANN is contraction velocity. The experimental data were divided randomly into two parts. The first part was used to train the ANN. In order to validate the model, the second part of experimental data, which was not used in training, was employed to the ANN and then, its output was compared with Hill model and the experimental data. The behavior of ANN in high forces was more similar to experimental data, but in low forces the Hill model had better results. Furthermore, extrapolation of ANN performance showed that our model is more or less able to simulate eccentric contraction. Our results indicate that ANNs represent a powerful tool to capture some essential features of muscle isotonic contraction.     

Inulinase production in a batch bioreactor using agroindustrial residues as the substrate: experimental data and modeling

The production of inulinase employing agroindustrial residues as the substrate is a good alternative to reduce production costs and to minimize the environmental impact of disposing these residues in the environment. This study focused on the use of a phenomenological model and an artificial neural network (ANN) to simulate the inulinase production during the batch cultivation of the yeast Kluyveromyces marxianus NRRL Y-7571, employing a medium containing agroindustrial residues such as molasses, corn steep liquor and yeast extract. It was concluded that due to the complexity of the medium composition it was rather difficult to use a phenomenological model with sufficient accuracy. For this reason, an alternative and more cost-effective methodology based on ANN was adopted. The predictive capacity of the ANN was superior to that of the phenomenological model, indicating that the neural network approach could be used as an alternative in the predictive modeling of complex batch cultivations.     

An ensemble simulation approach for artificial neural network: An example from chlorophyll a simulation in Lake Poyang,China

Artificial neural network (ANN) models have been widely used in environmental modeling with considerable success. To improve the reliability of ANN models, ensemble simulations were applied in this study to develop four ANN ensemble models for chlorophyll a simulation in the largest freshwater lake (Lake Poyang) in China. Reliability (evaluated by model fit and stability) of these ANN ensemble models was compared with that of single ANN models from ensemble members. The model fit of these single ANN models varied significantly over repeated runs, indicating the unstable performance of the single ANN models. Comparing with the single ANN models, the ANN ensemble models showed a better model fit and stability, implying the potential of ensemble simulation in achieving a more reliable model. An ensemble size of 30 was adequate for the ANN ensemble models to achieve a good model fit, while an ensemble size of 50 was adequate to achieve good stability. This case study highlighted both the necessity and potential of the ensemble simulation approach to achieve a reliable ANN model with good model fit and stability.     

Lower extremity joint torque predicted by using artificial neural network during vertical jump

The purpose of this study was to develop an artificial neural network (ANN) for predicting lower extremity joint torques using the ground reaction force (GRF) and related parameters derived by the GRF during counter-movement jump (CMJ) and squat jump (SJ). Ten student athletes performed CMJ and SJ. Force plate and kinematic data were recorded. Joint torques were calculated using inverse dynamics and ANN. We used a fully connected, feed-forward network. The network comprised of one input layer, one hidden layer and one output layer. It was trained by error back-propagation algorithm using Steepest Descent Method. Input parameters of the ANN were GRF measurements and related parameters. Output parameters were three lower extremity joint torques. ANN model fitted well with the results of the inverse dynamics output. Our observations indicate that the model developed in this study can be used to estimate three lower extremity joint torques for CMJ and SJ based on ground reaction force data and related parameters.     

Motion control of musculoskeletal systems with redundancy

Motion control of musculoskeletal systems for functional electrical stimulation (FES) is a challenging problem due to the inherent complexity of the systems. These include being highly nonlinear, strongly coupled, time-varying, time-delayed, and redundant. The redundancy in particular makes it difficult to find an inverse model of the system for control purposes. We have developed a control system for multiple input multiple output (MIMO) redundant musculoskeletal systems with little prior information. The proposed method separates the steady-state properties from the dynamic properties. The dynamic control uses a steady-state inverse model and is implemented with both a PID controller for disturbance rejection and an artificial neural network (ANN) feedforward controller for fast trajectory tracking. A mechanism to control the sum of the muscle excitation levels is also included. To test the performance of the proposed control system, a two degree of freedom ankle–subtalar joint model with eight muscles was used. The simulation results show that separation of steady-state and dynamic control allow small output tracking errors for different reference trajectories such as pseudo-step, sinusoidal and filtered random signals. The proposed control method also demonstrated robustness against system parameter and controller parameter variations. A possible application of this control algorithm is FES control using multiple contact cuff electrodes where mathematical modeling is not feasible and the redundancy makes the control of dynamic movement difficult.     

Lovastatin biosynthesis depends on the carbon–nitrogen proportion: Model development and controller design

Lovastatin biosynthesis depends on the relative concentrations of dissolved oxygen and the carbon and nitrogen resources. An elucidation of the underlying relationship would facilitate the derivation of a controller for the improvement of lovastatin yield in bioprocesses. To achieve this goal, batch submerged cultivation experiments of lovastatin production by Aspergillus flavipus BICC 5174, using both lactose and glucose as carbon sources, were performed in a 7‐L bioreactor and the data used to determine how the relative concentrations of lactose, glucose, glutamine, and oxygen affected lovastatin yield. A model was developed based on these results and its prediction was validated using an independent set of batch data obtained from a 15‐L bioreactor using five statistical measures, including the Willmott index of agreement. A non‐linear controller was designed considering that dissolved oxygen and lactose concentrations could be measured online, and using the lactose feed rate and airflow rate as process inputs. Simulation experiments were performed to demonstrate that a practical implementation of the non‐linear controller would result in satisfactory outcomes. This is the first model that correlates lovastatin biosynthesis to carbon–nitrogen proportion and possesses a structure suitable for implementing a strategy for controlling lovastatin production.     

On-line biomass estimation in biosurfactant production process by <Emphasis Type="Italic">Candida lipolytica</Emphasis> UCP 988

Biomass is an important variable in biosurfactant production process. However, such bioprocess variable, usually, is collected by sampling and determined by off-line analysis, with significant time delay. Therefore, simple and reliable on-line biomass estimation procedures are highly desirable. An artificial neural network model (ANN) is presented for the on-line estimation of biomass concentration, in biosurfactant production by Candida lipolytica UCP 988, as a nonlinear function of pH and dissolved oxygen. Several configurations were evaluated while developing the optimal ANN model. The optimal ANN model consists of one hidden layer with four neurons. The performance of the ANN was checked using experimental data. The results obtained indicate a very good predictive capacity for the ANN-based software sensor with values of R2 of 0.969 and RMSE of 0.021 for biomass concentration. Estimated biomass using the ANN was proved to be a simple, robust and accurate method.