Search

• Experimental data for SO 2 removal process via spray tower were produced. • A large set of data was collected to evaluate several process conditions. • Optimization presented higher removal efficiency and lower solution consumption. • New ANN model for SO 2 removal and k g a ¯ in spray tower was proposed. • ANNs are more precise than the usual correlations found in the literature. Spray towers to can be used to absorb pollutants gases. Due to the complexity of the process, to propose mathematical models for prediction of removal efficiency and volumetric mass transfer coefficient, is a difficult task. This work aimed to evaluate the influence of variables on the SO 2 removal process in a spray tower and to obtain an artificial neural network (ANN) to predict the removal efficiency and the volumetric mass transfer coefficient for columns with different heights, gas and liquid flow rates. The tower built in this study reached a maximum efficiency of 99.47% and showed that it was possible to achieve high levels of removal without the need to build high towers. The best ANN obtained presented error of 2.76% for the removal efficiency of the SO 2 and 6.79% for the volumetric mass transfer coefficient. The obtained results were very promising in the prediction of important parameters in the process of removing atmospheric pollutants via spray tower. [ABSTRACT FROM AUTHOR]

Despite the concern about climate change and the associated negative impacts, fossil fuels continue to prevail in the global energy consumption. This paper aimed to propose the first model that relates CO2 emissions of Sao Paulo, the main urban center emitter in Brazil, with gross national product and energy consumption. Thus, we investigated the accuracy of three different methods: multivariate linear regression, elastic-net regression, and multilayer perceptron artificial neural networks. Comparing the results, we clearly demonstrated the superiority of artificial neural networks when compared with the other models. They presented better results of mean absolute percentage error (MAPE = 0.76%) and the highest possible coefficient of determination (R2 = 1.00). This investigation provides an innovative integrated climate-economic approach for the accurate prediction of carbon emissions. Therefore, it can be considered as a potential valuable decision-support tool for policymakers to design and implement effective environmental policies. [ABSTRACT FROM AUTHOR]

• New correlation for SO 2 removal in spray tower was proposed. • Mathematical models are difficult to obtain due process complexity. • Neural networks can predict removal efficiency and the volumetric coefficient of mass transfer of the gas phase (k g a). • Neural networks are more precise than the usual empirical correlations. One of the most common methods for controlling SO 2 is the process of desulfurization using spray tower. Due to the large number of parameters to be evaluated and the process complexity, there are difficulties in the proposal of mathematical models to predict the removal efficiency and the gas phase volumetric mass transfer coefficient (k g a). The aim of this study was to obtain an artificial neural network (ANN) to predict the removal efficiency and the k g a in a spray tower for SO 2 removal. The results showed that the choosing of the best model from the training and validation steps did not generate reliable results. The best structure was defined by analyzing the results of a simulation step, which used independent data. The best model was obtained with the structure 5-9-2, trained using the Levenberg–Marquardt algorithm with Bayesian Regularization and having the softmax and linear transfer functions in the hidden and output layers, respectively. This network presented an average error of 8.44% for the outlet SO 2 concentration and 4.53% for the k g a. This work showed that the use of neural networks is promising in the prediction of important variables in the processes of removal of air pollutants in spray towers. [ABSTRACT FROM AUTHOR]

• The estimation of vaporization properties using artificial neural networks were evaluated. • One ANN for prediction of vaporization properties of different substances was obtained. • One ANN was capable to predict several vaporization properties with high accuracy. • ANN results were more accurate than those calculated by correlations or equations of state. Vaporization properties are important for equipment modeling and process control involving liquid-vapor equilibrium. The aim of this work was to obtain an Artificial Neural Network (ANN) to predict volume, internal energy, enthalpy, and entropy of vaporization, and the saturation pressure (or temperature) of several fluids. Two strategies were proposed: one using saturation temperature in the inputs and another using saturation pressure. Five physicochemical descriptors were used to distinguish each substance. All ANNs were trained using the Levenberg-Marquardt method. Nine outputs combination were evaluated to obtain the best model, which was determined by simulating a dataset not shown in the training/validation/test steps. The results showed that ANNs with three outputs presented higher accuracy. The best one (structure 4-40-40-3) predicted saturation pressure, internal energy and enthalpy of vaporization as outputs and presented relative errors as low as 0.02%. Finally, we showed that ANNs can be reliable for vaporization properties prediction. [ABSTRACT FROM AUTHOR]