Application of machine learning techniques to the modeling of solubility of sugar alcohols in ionic liquids

The current trend of chemical industries demands green processing, in particular with employing natural substances such as sugar-derived compounds. This matter has encouraged academic and industrial sections to seek new alternatives for extracting these materials. Ionic liquids (ILs) are currently paving the way for efficient extraction processes. To this end, accurate estimation of solubility data is of great importance. This study relies on machine learning methods for modeling the solubility data of sugar alcohols (SAs) in ILs. An initial relevancy analysis approved that the SA-IL equilibrium governs by the temperature, density and molecular weight of ILs, as well as the molecular weight, fusion temperature, and fusion enthalpy of SAs. Also, temperature and fusion temperature have the strongest influence on the SAs solubility in ILs. The performance of artificial neural networks (ANNs), least-squares support vector regression (LSSVR), and adaptive neuro-fuzzy inference systems (ANFIS) to predict SA solubility in ILs were compared utilizing a large databank (647 data points of 19 SAs and 21 ILs). Among the investigated models, ANFIS offered the best accuracy with an average absolute relative deviation (AARD%) of 7.43% and a coefficient of determination (R²) of 0.98359. The best performance of the ANFIS model was obtained with a cluster center radius of 0.435 when trained with 85% of the databank. Further analyses of the ANFIS model based on the leverage method revealed that this model is reliable enough due to its high level of coverage and wide range of applicability. Accordingly, this model can be effectively utilized in modeling the solubilities of SAs in ILs.

Modeling of Nitrogen Removal from Natural Gas in Rotating Packed Bed Using Artificial Neural Networks

Novel or unconventional technologies are critical to providing cost-competitive natural gas supplies to meet rising demands and provide more opportunities to develop low-quality gas fields with high contaminants, including high carbon dioxide (CO₂) fields. High nitrogen concentrations that reduce the heating value of gaseous products are typically associated with high CO₂ fields. Consequently, removing nitrogen is essential for meeting customers' requirements. The intensification approach with a rotating packed bed (RPB) demonstrated considerable potential to remove nitrogen from natural gas under cryogenic conditions. Moreover, the process significantly reduces the equipment size compared to the conventional distillation column, thus making it more economical. The prediction model developed in this study employed artificial neural networks (ANN) based on data from in-house experiments due to a lack of available data. The ANN model is preferred as it offers easy processing of large amounts of data, even for more complex processes, compared to developing the first principal mathematical model, which requires numerous assumptions and might be associated with lumped components in the kinetic model. Backpropagation algorithms for ANN Lavenberg-Marquardt (LM), scaled conjugate gradient (SCG), and Bayesian regularisation (BR) were also utilised. Resultantly, the LM produced the best model for predicting nitrogen removal from natural gas compared to other ANN models with a layer size of nine, with a 99.56% regression (R²) and 0.0128 mean standard error (MSE).

Nonlinear Control of Fouling in Polyethylene Reactors

Fouling formation in reactor vessels poses a serious threat to the safe operation of the industrial low-density polyethylene (LDPE) polymerization. Fouling also degrades the polymer quality and causes productivity loss to some extent. In this work, neural Wiener model predictive control (NWMPC) is introduced to address the fouling concern. In addition, a soft sensor model is used to activate the fouling-defouling (F-D) mechanism when the fouling surpasses the thickness limit to prevent vessel overheating. NWMPC is proven to be fast, stable, and robust under various control scenarios. The use of a soft sensor model in conjunction with NWMPC enables the online monitoring and controlling of the F-D processes. When comparison is made with a state space (SSMPC) utilizing only the linear block, NWMPC is found to be able to control the LDPE grade with quicker grade transition and lower resource consumption.

Predicting protection capacities of pyrimidine-based corrosion inhibitors for mild steel/HCl interface using linear and nonlinear QSPR models

Pyrimidine compounds have proven to be effective and efficient additives capable of protecting mild steel in acidic media. This class of organic compounds often functions as adsorption-type inhibitors of corrosion by forming a protective layer on the metallic substrate. The present study reports a computational study of forty pyrimidine compounds that have been investigated as sustainable inhibitors of mild steel corrosion in molar HCl solution. Quantitative structure property relationship was conducted using linear (multiple linear regression) and nonlinear (artificial neural network) models. Standardization method was employed in variable selection yielding five top chemical descriptors utilized for model development along with the inhibitor concentration. Multiple linear regression model yielded a fair predictive model. Artificial neural network model developed using k-fold cross-validation method provided a comprehensive insight into the corrosion protection mechanism of studied pyrimidine-based corrosion inhibitors. Using a multilayer perceptron with Levenberg-Marquardt algorithm, the study obtained the optimal model having a MSE of 8.479, RMSE of 2.912, MAD of 1.791, and MAPE of 2.648. The optimal neural network model was further utilized to forecast the protection capacities of nine non-synthesized pyrimidine derivatives. The predicted inhibition efficiencies ranged from 89 to 98%, revealing the significance of the considered chemical descriptors, the predictive capacity of the developed model, and the potency of the theoretical inhibitors.

Fault Diagnosis of Tennessee Eastman Process with XGB-AVSSA-KELM Algorithm

In fault detection and the diagnosis of large industrial systems, whose chemical processes usually exhibit complex, high-dimensional, time-varying and non-Gaussian characteristics, the classification accuracy of traditional methods is low. In this paper, a kernel limit learning machine (KELM) based on an adaptive variation sparrow search algorithm (AVSSA) is proposed. Firstly, the dataset is optimized by removing redundant features using the eXtreme Gradient Boosting (XGBOOST) model. Secondly, a new optimization algorithm, AVSSA, is proposed to automatically adjust the network hyperparameters of KELM to improve the performance of the fault classifier. Finally, the optimized feature sequences are fed into the proposed classifier to obtain the final diagnosis results. The Tennessee Eastman (TE) chemical process is used to verify the effectiveness of the proposed method through multidimensional diagnostic metrics. The results show that our proposed diagnosis method can significantly improve the accuracy of TE process fault diagnosis compared with traditional optimization algorithms. The average diagnosis rate for 21 faults was 91.00%.

Multiparameter Neural Network Modeling of Facilitated Transport Mixed Matrix Membranes for Carbon Dioxide Removal

Membranes for carbon capture have improved significantly with various promoters such as amines and fillers that enhance their overall permeance and selectivity toward a certain particular gas. They require nominal energy input and can achieve bulk separations with lower capital investment. The results of an experiment-based membrane study can be suitably extended for techno-economic analysis and simulation studies, if its process parameters are interconnected to various membrane performance indicators such as permeance for different gases and their selectivity. The conventional modelling approaches for membranes cannot interconnect desired values into a single model. Therefore, such models can be suitably applicable to a particular parameter but would fail for another process parameter. With the help of artificial neural networks, the current study connects the concentrations of various membrane materials (polymer, amine, and filler) and the partial pressures of carbon dioxide and methane to simultaneously correlate three desired outputs in a single model: CO₂ permeance, CH₄ permeance, and CO₂/CH₄ selectivity. These parameters help predict membrane performance and guide secondary parameters such as membrane life, efficiency, and product purity. The model results agree with the experimental values for a selected membrane, with an average absolute relative error of 6.1%, 4.2%, and 3.2% for CO₂ permeance, CH₄ permeance, and CO₂/CH₄ selectivity, respectively. The results indicate that the model can predict values at other membrane development conditions.

A Novel Fault Diagnosis Method for TE Process Based on Optimal Extreme Learning Machine

Chemical processes usually exhibit complex, high-dimensional and non-Gaussian characteristics, and the diagnosis of faults in chemical processes is particularly important. To address this problem, this paper proposes a novel fault diagnosis method based on the Bernoulli shift coyote optimization algorithm (BCOA) to optimize the kernel extreme learning machine classifier (KELM). Firstly, the random forest treebagger (RFtb) is used to select the features, and the data set is optimized. Secondly, a new optimization algorithm BCOA is proposed to automatically adjust the network hyperparameters of KELM and improve the classifier performance. Finally, the optimized feature sequence is input into the proposed classifier to obtain the final diagnosis results. The Tennessee Eastman (TE) chemical process have been collected and used to verify the effectiveness of the proposed method. A comprehensive comparison and analysis with widely used algorithms is also performed. The results demonstrate that the proposed method outperforms other methods in terms of classification accuracy. The average diagnosis rate of 21 faults is found to be 89.32%.

Using Neural Networks to Obtain Indirect Information about the State Variables in an Alcoholic Fermentation Process

This work provides a manual design space exploration regarding the structure, type, and inputs of a multilayer neural network (NN) to obtain indirect information about the state variables in the alcoholic fermentation process. The main benefit of our application is to help experts reduce the time needed for making the relevant measurements and to increase the lifecycles of sensors in bioreactors. The novelty of this research is the flexibility of the developed application, the use of a great number of variables, and the comparative presentation of the results obtained with different NNs (feedback vs. feed-forward) and different learning algorithms (Back-Propagation vs. Levenberg–Marquardt). The simulation results show that the feedback neural network outperformed the feed-forward neural network. The NN configuration is relatively flexible (with hidden layers and a number of nodes on each of them), but the number of input and output nodes depends on the fermentation process parameters. After laborious simulations, we determined that using pH and CO2 as inputs reduces the prediction errors of the NN. Thus, besides the most commonly used process parameters like fermentation temperature, time, the initial concentration of the substrate, the substrate concentration, and the biomass concentration, by adding pH and CO2, we obtained the optimum number of input nodes for the network. The optimal configuration in our case was obtained after 1500 iterations using a NN with one hidden layer and 12 neurons on it, seven neurons on the input layer, and one neuron as the output. If properly trained and validated, this model can be used in future research to accurately predict steady-state and dynamic alcoholic fermentation process behaviour and thereby improve process control performance.

Accurate and cost-effective prediction of HBsAg titer in industrial scale fermentation process of recombinant Pichia pastoris by using neural network based soft sensor

In the current work, the attempt was made to apply best-fitted artificial neural network (ANN) architecture and the respective training process for predicting final titer of hepatitis B surface antigen (HBsAg), produced intracellularly by recombinant Pichia pastoris Mut⁺ in the commercial scale. For this purpose, in large-scale fed-batch fermentation, using methanol for HBsAg induction and cell growth, three parameters of average specific growth rate, biomass yield, and dry biomass concentration-in the definite integral form with respect to fermentation time-were selected as input vectors; the final concentration of HBsAg was selected for the ANN output. Used dataset consists of 38 runs from previous batches; feed-forward ANN 3:5:1 with training algorithm of backpropagation based on a Bayesian regularization was trained and tested with a high degree of accuracy. Implementing the verified ANN for predicting the HBsAg titer of the five new fermentation runs, excluded from the dataset, in the full-scale production, the coefficient of regression and root-mean-square error were found to be 0.969299 and 2.716774, respectively. These results suggest that this verified soft sensor could be an excellent alternative for the current relatively expensive and time-intensive analytical techniques such as enzyme-linked immunosorbent assay in the biopharmaceutical industry.

Application of neural networks in membrane separation

Artificial neural networks (ANNs) as a powerful technique for solving complicated problems in membrane separation processes have been employed in a wide range of chemical engineering applications. ANNs can be used in the modeling of different processes more easily than other modeling methods. Besides that, the computing time in the design of a membrane separation plant is shorter compared to many mass transfer models. The membrane separation field requires an alternative model that can work alone or in parallel with theoretical or numerical types, which can be quicker and, many a time, much more reliable. They are helpful in cases when scientists do not thoroughly know the physical and chemical rules that govern systems. In ANN modeling, there is no requirement for a deep knowledge of the processes and mathematical equations that govern them. Neural networks are commonly used for the estimation of membrane performance characteristics such as the permeate flux and rejection over the entire range of the process variables, such as pressure, solute concentration, temperature, superficial flow velocity, etc. This review investigates the important aspects of ANNs such as methods of development and training, and modeling strategies in correlation with different types of applications [microfiltration (MF), ultrafiltration (UF), nanofiltration (NF), reverse osmosis (RO), electrodialysis (ED), etc.]. It also deals with particular types of ANNs that have been confirmed to be effective in practical applications and points out the advantages and disadvantages of using them. The combination of ANN with accurate model predictions and a mechanistic model with less accurate predictions that render physical and chemical laws can provide a thorough understanding of a process.

A review on empirical correlations estimating gas holdup for shear-thinning non-Newtonian fluids in bubble column systems with future perspectives

Gas holdup is one of the most important parameters for characterizing the hydrodynamics of bubble columns. Modeling and design of bubble columns require empirical correlations for precise estimation of gas holdup. Empirical correlations available for prediction of gas holdup (ε G) in various non-Newtonian systems for both gas-liquid and gas-liquid-solid bubble columns have been presented in this review. Critical analysis of correlations presented by different researchers has been made considering the findings and pitfalls. As the magnitude of gas holdup depends on many factors, such as physicochemical properties of gas and/or liquid, column geometry, type and design of gas distributors, operating conditions, phase properties, and rheological properties, etc., all of these have been discussed and examined. In order to emphasize the significance, relative importance of parameters such as flow behavior index, consistency index, column diameter, gas flow rate, and density of aqueous carboxymethylcellulose (CMC) solution on gas holdup has been quantified using artificial neural network and Garson’s algorithm for an experimental data set of air-CMC solution from the literature. Besides, potential areas for research encompassing operating conditions, column geometry, physical properties, modeling and simulation, rheological properties, flow regime, etc., have been underlined, and the need for developing newer correlations for gas holdup has been outlined. The review may be useful for the modeling and design of bubble columns.

Removal of synthetic dyes from multicomponent industrial wastewaters

Colored effluents containing dyes from various industries pollute the environment and pose problems in municipal wastewater treatment systems. Industrial effluents consist of a mixture of dyes and require study of the simultaneous removal of dyes. Simultaneous quantification of dyes in the solution is a common problem while using a spectrophotometric method due to overlapping of their absorption spectra. Derivative spectroscopy and chemometric methods in spectrophotometric analysis facilitate simultaneous quantification of dyes. Adsorption is a widely used treatment method for the removal of a mixture of recalcitrant dyes in industrial wastewaters. Confirming the assertion, this paper presents a state-of-the-art review on methods used for simultaneous quantification of dyes and the effects of various parameters on their adsorptive removal. This paper also reviews the adsorption equilibrium, modeling, mechanisms of dyes adsorption, and adsorbent regeneration techniques in multicomponent dye systems. It has been observed that chemometric techniques provide accuracy, repeatability, and high speed in processing and helps in better operability in real wastewater treatment plants. The conclusions include the need for the development of thermodynamic models that can predict simultaneous physisorption and chemisorption exhibited by different dyes and to develop isotherm models that can describe chemisorption of a mixture of dyes. The paper delves into inadequately researched gray areas of adsorption of a mixture of dyes which require the development of modified adsorption methods that serves process intensification for complete degradation/mineralization.

Estimation of Chlamydomonas reinhardtii biomass concentration from chord length distribution data

A novel method to estimate the concentration of Chlamydomonas reinhardtii biomass was developed. The method employs the chord length distribution information gathered by means of a focused beam reflectance probe immersed in the culture sample and processes the data through a feedforward multilayer perceptron. The multilayer perceptron architecture was systematically optimised through the application of a simulated annealing algorithm. The method developed can predict the concentration of microalgae with acceptable accuracy and, with further development, it could be implemented online to monitor the aggregation status and biomass concentration of microalgal cultures.

Neural networks and differential evolution algorithm applied for modelling the depollution process of some gaseous streams

The depollution of some gaseous streams containing n-hexane is studied by adsorption in a fixed bed column, under dynamic conditions, using granular activated carbon and two types of non-functionalized hypercross-linked polymeric resins. In order to model the process, a new neuro-evolutionary approach is proposed. It is a combination of a modified differential evolution (DE) with neural networks (NNs) and two local search algorithms, the global and local optimizers, working together to determine the optimal NN model. The main elements that characterize the applied variant of DE consist in using an opposition-based learning initialization, a simple self-adaptive procedure for the control parameters, and a modified mutation principle based on the fitness function as a criterion for reorganization. The results obtained prove that the proposed algorithm is able to determine a good model of the considered process, its performance being better than those of an available phenomenological model.