Development of NOx removal process for LNG evaporation system: Comparative assessment between response surface methodology (RSM) and artificial neural network (ANN)

A green and efficient approach for the simultaneous extraction and mechanisms of essential oil and lignin from Cinnamomum camphora: Process optimization based on deep learning

The utilization and economic benefits of biomass resources can be maximized through rational design and process optimization. In this study, an innovative approach for the simultaneous extraction of essential oil and lignin from Cinnamomum camphora leaves by deep eutectic solvent (DES) and optimization of the process parameters was achieved using deep learning tools. With the water content of 40 %, liquid-solid ratio of 9.00 mL/g, and distillation time of 51.81 min, the yields of the essential oil and lignin reached 3.15 ± 0.02 % and 9.75 ± 0.15 %, respectively. Notably, the efficiency of simultaneous extraction of essential oil improved by 23 % compared to that of traditional steam distillation. Moreover, the extraction mechanism of the process was clarified. The connection between lignin with cellulose and hemicellulose was disintegrated by the DES, resulting in lignin shedding and hence accelerating the dissolution of essential oil. Moreover, the compositions of lignin and essential oil were also identified.

Nutrient sequestration and lipid production potential of Chlorella vulgaris under pharmaceutical wastewater treatment: experimental, optimization, and prediction modeling studies

The efficient management and treatment of pharmaceutical industry wastewater (PIWW) have become a serious environmental issue due to its high toxicity. To overcome this problem, the present study deals with the phycoremediation of PIWW using Chlorella vulgaris microalga isolated from the Ganga River at Haridwar, India. For this, response surface methodology (RSM) and artificial neural network (ANN) tools were used to identify the best reduction of total phosphorus (TP) and total Kjeldahl's nitrogen (TKN) based pollutants along with the lipid production efficiency of C. vulgaris. Three different concentrations of pharmaceutical wastewater (0, 50, and 100%), operating temperatures (20, 25, and 30 °C), and light intensity (2000, 3000, and 4000 lx) were used to design the phycoremediation experiments having 6:18 h of dark/light period and reactor functional volume of 15L. Findings revealed that C. vulgaris was good enough to remove maximum TP (90.35%), TKN (83.55%) along 20.88% of lipid yield at 25.62 °C temperature, 60.73% PIWW concentration, and 4000 lx of light intensity, respectively. Based on the model performance and validation results, ANN showed more accuracy as compared to the RSM tool. Therefore, the findings of this study showed that C. vulgaris is capable of treating PIWW efficiently along with significant production of lipid content which can further be used in various applications including biofuel production.

Process optimization of cypermethrin biodegradation by regression analysis and parametric modeling along with biochemical degradation pathway

Pyrethroid pesticides are of great environmental and health concern with regard to neurotoxicity and ubiquitous occurrence. Here, we reported a new bacterial strain identified as Bacillus cereus AKAD 3-1 that degraded 88.1% of 50 mg/l of cypermethrin in an aqueous medium. The biodegradation of cypermethrin was optimized by CCD (central composite design) and validated by ANN-GA (artificial neural network-genetic algorithm). Both the approaches proved to possess good performance in modeling and optimizing the growth conditions. Results indicated that the process variables have a significant (< 0.0001) impact on cypermethrin biodegradation. Moreover, the predicted CCD model had a "lack of fit p-value" of "0.9975." The optimum CCD and ANN model had an R² value of 0.9703 and 0.9907, indicating that the two models' experimental and predicted values are closely fitted. The isolate successfully converted cypermethrin to CO₂ and phenol without producing any toxic metabolite. Finally, a degradation pathway was proposed with the intermediate compounds identified by GC-MS. The present study highlights an important potential application of strain AKAD 3-1 for the in situ bioremediation of cypermethrin-contaminated environments.

Experimental analysis and parameter optimization on the reduction of NOx from diesel engine using RSM and ANN Model

The major emission sources of NO_X are from automobiles, trucks, and various non-road vehicles, power plants, coal fired boilers, cement kilns, turbines, etc. Plasma reactor technology is widely used in gas conversion applications, such as NOx conversion into useful chemical by-product. Among the plasma treatment techniques, nonthermal plasma (NTP) is widely used because it does not cause any damage to the surfaces of the reacting chamber. In this proposed work, the feasibility of Dielectric Barrier Discharge (DBD) reactor-based nonthermal plasma (NTP) process is examined based on four operating parameters including NOx concentration (300-400 ppm), gas flow rate (2-6 lpm), applied plasma voltage (20-30 kVpp), and electrode gap (3-5 mm) for removing NOx gas from diesel engine exhaust. Optimization of NTP process parameters has been carried out using response surface-based Box-Behnken design (BBD) method and artificial neural network (ANN) method and compared with the performance measures such as R², MSE (mean square error), RMSE (root mean square error), and MAPE (mean absolute percentage error). Two kinds of analysis were carried out based on (1) NOx removal efficiency and (2) energy efficiency. Based on the simulation studies carried out for Nox removal efficiency, the RSM methodology produces the performance measures, 0.98 for R², 1.274 for MSE, 1.128 for RMSE, and 2.053 for MAPE, and for ANN analysis method, 0.99 for R², 2.167 for MSE, 1.472 for RMSE, and 1.276 for MAPE. These results shows that ANN method is having enhanced performance measures. For the second case, based on the energy efficiency study, the R², MSE, RMSE, and MAPE values from the RSM model are 0.97, 2.230, 1.493, and 2.903 respectively. Similarly based on ANN model, the R², MSE, RMSE, and MAPE values are 0.99, 0.246, 0.46, and 0.615, respectively. From the performance measures, it is found that the ANN model is accurate than the RSM model in predicting the NOx removal/reduction and efficiency. These models demonstrate that they have strong agreement with the experimental results. The experimental results are indicated that optimum conditions arrived based on the RSM model resulted in a maximum NOx reduction of 60.5% and an energy efficiency of 66.24 g/J. The comparison between the two models confirmed the findings, whereas this ANN model displayed a stronger correlation to the experimental evidence.

A Connectionist Model for Dynamic Economic Risk Analysis of Hydrocarbons Production Systems

This study presents a connectionist model for dynamic economic risk evaluation of reservoir production systems. The proposed dynamic economic risk modeling strategy combines evidence-based outcomes from a Bayesian network (BN) model with the dynamic risks-based results produced from an adaptive loss function model for reservoir production losses/dynamic economic risks assessments. The methodology employs a multilayer-perceptron (MLP) model, a loss function model; it integrates an early warning index system (EWIS) of oilfield block with a BN model for process modeling. The model evaluates the evidence-based economic consequences of the production losses and analyzes the statistical disparities of production predictions using an EWIS-assisted BN model and the loss function model at the same time. The proposed methodology introduces an innovative approach that effectively minimizes the potential for dynamic economic risks. The model predicts real-time daily production/dynamic economic losses. The connectionist model yields an encouraging overall predictive performance with average errors of 1.954% and 1.957% for the two case studies: cases 1 and 2, respectively. The model can determine transitional/threshold production values for adequate reservoir management toward minimal losses. The results show minimum average daily dynamic economic losses of $267,463 and $146,770 for cases 1 and 2, respectively. It is a multipurpose tool that can be recommended for the field operators in petroleum reservoir production management related decision making.

Artificial neural network and statistical modelling of biosorptive removal of hexavalent chromium using macroalgal spent biomass

This study focused on the sustainable removal of chromium in its hexavalent form by adsorption using sugar-extracted spent marine macroalgal biomass - Ulva prolifera. The adsorption of Cr (VI) from aqueous solutions utilizing macroalgal biomass was studied under varying conditions of pH, adsorbent amount, agitation speed, and time to assess and optimize the process variables by using a statistical method - response surface methodology (RSM) to enhance the adsorption efficiency. The maximum adsorption efficiency of 99.11 ± 0.23% was obtained using U. prolifera under the optimal conditions: pH: 5.4, adsorbent dosage: 200 mg, agitation speed: 160 rpm, and time: 75 min. Also, a prediction tool - artificial neural network (ANN) model was developed using the RSM experimental data. Eight neurons in the hidden layer yielded the best network topology (4-8-1) with a high correlation coefficient (R_ANN: 0.99219) and low mean squared error (MSE_ANN: 0.99219). Various performance parameters were compared between RSM and ANN models, which confirmed that the ANN model was better in predicting the response with a high coefficient of determination value (R²_ANN: 0.9844, R²_RSM: 0.9721) and low MSE value (MSE_ANN: 3.7002, MSE_RSM: 6.2179). The adsorption data were analyzed by fitting to various equilibrium isotherms. The maximum adsorption capacity was estimated as 6.41 mg/g. Adsorption data was in line with Freundlich isotherm (R² = 0.97) that confirmed the multilayer adsorption process. Therefore, the spent U. prolifera biomass can credibly be applied as a low-cost adsorbent for Cr (VI) removal, and the adsorption process can be modelled and predicted efficiently using ANN.

Sequential modelling for carbohydrate and bioethanol production from Chlorella saccharophila CCALA 258: a complementary experimental and theoretical approach for microalgal bioethanol production

Bioethanol production from microalgal biomass is an attractive concept, and theoretical methods by which bioenergy can be produced indicate saving in both time and efficiency. The aim of the present study was to investigate the efficiencies of carbohydrate and bioethanol production by Chlorella saccharophila CCALA 258 using experimental, semiempirical, and theoretical methods, such as response surface methods (RSMs) and an artificial neural network (ANN) through sequential modeling. In addition, the interactive response surface modeling for determining the optimum conditions for the variables was assessed. The results indicated that the maximum bioethanol concentration was 11.20 g/L using the RSM model and 11.17 g/L using the ANN model under optimum conditions of 6% (v/v %) substrate and 4% (v/v %) inoculum at 96-h fermentation, pH 6, and 40 °C. In addition, the value of the experimental data for carbohydrate concentration was 0.2510 g/g biomass at ANN with the maximums of 50% (v/v) wastewater concentration, 4% (m/m) hydrogen peroxide concentration, and 6000 U/mL enzyme activity. Finally, although the RSM model was more effective than the ANN model for predicting bioethanol concentration, the ANN model yielded more precise values than the RSM model for carbohydrate concentration.

Degradation of Bisphenol A by ozonation in a rotating packed bed: Modeling by response surface methodology and artificial neural network

The ozonation process of Bisphenol A (BPA) in a rotating packed bed (RPB) was modeled by response surface methodology (RSM) and artificial neural network (ANN). Experiments were performed according to the Box-Behnken design, and the interactive effects of various parameters including ozone concentration, pH, rotation speed of RPB and liquid flow rate on BPA degradation efficiency were investigated. Ozone concentration and pH had the most significant interactive effects on BPA degradation efficiency while rotation speed of RPB had no significant interactive effects with other variables. A second order polynomial equation was obtained to predict BPA degradation efficiency. Also, a multi-layered feed-forward ANN model was constructed based on the data of RSM experiments. Six neurons in hidden layer had the highest correlation coefficient (R_ANN = 0.99158). A comparison between RSM and ANN models suggested that both can accurately predict BPA degradation efficiency (R_RSM = 0.99559). The highest BPA degradation efficiency (99.52 %) was achieved under the conditions of ozone concentration of 20 mg L^-1, pH of 11, liquid flow rate of 10 L h^-1 and rotation speed of RPB of 800 rpm, which was well predicted by the RSM model (99.54 %) and the ANN model (99.82 %). However, the RSM model was slightly better than the ANN model owing to its higher determination coefficient (R²_RSM = 0.9912, R²_ANN = 0.9827) and lower mean square error (MSE_RSM = 0.0001684, MSE_ANN = 0.0003305).

Process optimization and enhancement of pesticide adsorption by porous adsorbents by regression analysis and parametric modelling

In the present study, the adsorptive removal of organophosphate diazinon pesticide using porous pumice adsorbent was experimentally investigated in a batch system, modelled and optimized upon response surface methodology (RSM) and artificial neural network-genetic algorithm (ANN-GA), fitted to isotherm, kinetic and thermodynamic models. The quantification of adsorbent elements was determined using EDX. XRD analysis was utilized to study the crystalline properties of adsorbent. The FT-IR spectra were taken from adsorbent before and after adsorption to study the presence and changes in functional groups. The constituted composition of the adsorbent was determined by XRF. Also, the ionic strength and adsorbent reusability were explored. The influences of operational parameters like pH, initial pesticide concentration, adsorbent dosage and contact time were investigated systematically. ANN-GA and RSM techniques were used to identify the optimal process variables that result in the highest removal. Based on the RSM approach, the optimization conditions for maximum removal efficiency is obtained at pH = 3, adsorbent dosage = 4 g/L, contact time = 30 min, and initial pesticide concentration = 6.2 mg/L. To accurately identify the parameters of nonlinear isotherm and kinetic models, a hybrid evolutionary differential evolution optimization (DEO) is applied. Results indicated that the equilibrium adsorption data were best fitted with Langmuir and Temkin isotherms and kinetic data were well described by pseudo-first and second-order kinetic models. The thermodynamic parameters such as entropy, enthalpy and Gibbs energy were evaluated to study the effect of temperature on pesticide adsorption.

Modeling the performance of Single-stage Nitrogen removal using Anammox and Partial nitritation (SNAP) process with backpropagation neural network and response surface methodology

Two novel feedforward backpropagation Artificial Neural Networks (ANN)-based-models (8:N_H:1 and 7:N_H:1) combined with Box-Behnken design of experiments methodology was proposed and developed to model NH₄⁺ and Total Nitrogen (TN) removal within an upflow-sludge-bed (USB) reactor treating nitrogen-rich wastewater via Single-stage Nitrogen removal using Anammox and Partial nitritation (SNAP) process. ANN were developed by optimizing network architecture parameters via response surface methodology. Based on the goodness-of-fit standards, the proposed three-layered NH₄⁺ and TN removal ANN-based-models trained with Levenberg-Marquardt-algorithm demonstrated high-performance as computations exhibited smaller deviations-(±2.1%) as well as satisfactory coefficient of determination (R²), fractional variance-(FV), and index of agreement-(IA) ranging 0.989-0.997, 0.003-0.031 and 0.993-0.998, respectively. The computational results affirmed that the ANN architecture which was optimized with response surface methodology enhanced the efficiency of the ANN-based-models. Furthermore, the overall performance of the developed ANN-based models revealed that modeling intricate biological systems (such as SNAP) using ANN-based models with the view to improve removal efficiencies, establish process control strategies and optimize performance is highly feasible. Microbial community analysis conducted with 16S rRNA high-throughput approach revealed that Candidatus Kuenenia was the most pronounced genera which accounted for 13.11% followed by Nitrosomonas-(6.23%) and Proteocatella-(3.1%), an indication that nitrogen removal pathway within the USB was mainly via partial-nitritation/anammox process.