Global sensitivity analyses of a neural networks model for a flotation circuit

Saldaña, Manuel Romero; Ayala, Luis F.; Torres, David; Toro, Norman

doi:10.2298/hemind20060523s

Cited by 6 publications

(3 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The general ANN model, used in this study, consisted of input, hidden and output layers, as it is shown in Figure 2. [17,18]. The ANN has two neurons in the input layer (time and temperature), selected to predict the torque as a single neuron in the output layer.…”

Section: Artificial Neural Network Developmentmentioning

confidence: 99%

Prediction of rubber vulcanization using an artificial neural network

Lubura

Kojić

Pavličević

et al. 2021

Hem Ind

View full text Add to dashboard Cite

Determination of rubber rheological properties is indispensable in order to conduct efficient vulcanization process in rubber industry. The main goal of this study was development of an advanced artificial neural network (ANN) for quick and accurate vulcanization data prediction of commercially available rubber gum for tire production. The ANN was developed by using the platform for large-scale machine learning TensorFlow with the Sequential Keras-Dense layer model, in a Python framework. The ANN was trained and validated on previously determined experimental data of torque on time at five different temperatures, in the range from 140 to 180 oC, with a step of 10 oC. The activation functions, ReLU, Sigmoid and Softplus, were used to minimize error, where the ANN model with Softplus showed the most accurate predictions. Numbers of neurons and layers were varied, where the ANN with two layers and 20 neurons in each layer showed the most valid results. The proposed ANN was trained at temperatures of 140, 160 and 180 oC and used to predict the torque dependence on time for two test temperatures (150 and 170 oC). The obtained solutions were confirmed as accurate predictions, showing the mean absolute percentage error (MAPE) and mean squared error (MSE) values were less than 1.99 % and 0.032 dN2 m2, respectively.

show abstract

Section: Artificial Neural Network Developmentmentioning

confidence: 99%

Prediction of rubber vulcanization using an artificial neural network

Lubura

Kojić

Pavličević

et al. 2021

Hem Ind

View full text Add to dashboard Cite

show abstract

“…The mining industry in Chile is constantly growing [1][2][3][4] . Historically, Chile has traded copper, this commodity being the main economic income contributing approximately 10 % of the gross domestic product (GDP) [5].…”

Section: Introductionmentioning

confidence: 99%

Lithium carbonate sedimentation using flocculants with different ionic bases

Morales

Herrera

Pérez

2021

Hem Ind

View full text Add to dashboard Cite

Lithium has become a metal of enormous interest worldwide. The extensive use of rechargeable batteries for a range of applications has pushed for rapid growth in demand for lithium carbonate. This compound is produced by crystallization, by reaction with lithium chloride (in solution) and by adding sodium carbonate. Low sedimentation rates in the evaporation pools present a problem in the crystallization process. For this reason, in this work, mineral sedimentation tests were carried out with the use of two flocculant types with different ionic charges. The tests were carried out at a laboratory level using different dosages for each flocculant and measurements were performed to obtain the increase in the content of solids in the sediment. The anionic flocculant had better performance as compared to that of the cationic flocculant, increasing the sedimentation rate of lithium carbonate by up to 6.5. However, similar solids contents were obtained with the use of the cationic flocculant at 3.5 times lower dosage making it the flocculant of choice regarding the economic point of view.

show abstract

“…The vast majority of copper minerals in the world correspond to sulfide minerals and a smaller quantity to oxidized minerals [5][6][7][8]. Among the sulfurous minerals, the most abundant copper mineral is chalcopyrite [9][10][11], followed by chalcocite [12].…”

Section: Introductionmentioning

confidence: 99%

Leaching of Pure Chalcocite with Reject Brine and MnO2 from Manganese Nodules

Torres

Trigueros

Robles

et al. 2020

Metals

Self Cite

View full text Add to dashboard Cite

Chalcocite (Cu2S) has the fastest kinetics of dissolution of Cu in chlorinated media of all copper sulfide minerals. Chalcocite has been identified as having economic interest due to its abundance, although the water necessary for its dissolution is scarce in many regions. In this work, the replacement of fresh water by sea water or by reject brine with high chloride content from desalination plants is analyzed. Additionally, the effect of adding MnO2 from available manganese nodules in vast quantities at the bottom of the sea is studied. Reject brine shows better results than sea water, and the addition of MnO2 to the brine significantly increases the kinetics of chalcocite dissolution in a short time. H2SO4 concentration is found to be irrelevant when working at high concentrations of chloride and MnO2. The best results, 71% Cu extractions in 48 h, are obtained for reject brine, 100 mg of MnO2 per 200 g of mineral and H2SO4 0.5 mol/L. The results are expected to contribute to a sustainable process of dissolution of chalcocite by using the reject brine from desalination plants.

show abstract

Global sensitivity analyses of a neural networks model for a flotation circuit

Cited by 6 publications

References 43 publications

Prediction of rubber vulcanization using an artificial neural network

Prediction of rubber vulcanization using an artificial neural network

Lithium carbonate sedimentation using flocculants with different ionic bases

Leaching of Pure Chalcocite with Reject Brine and MnO2 from Manganese Nodules

Contact Info

Product

Resources

About