Modelling of viscosity of fluorine-free mold fluxes using neural network

Abstract

Viscosity is an important property of mold fluxes for steel continuous casting. However, direct measurement of viscosity of multi-component systems in a broad range of temperatures and compositions is an onerous work and has some limitations. This paper developed a model using the back propagation (BP) neural network to describe the viscosity of fluorine-free mold fluxes. The BP neural network model was developed and validated using 70 experimental values of viscosity of fluorine-free mold fluxes CaO-SiO 2 -Al 2 O 3 -B 2 O 3 -Na 2 O-TiO 2 -MgO-Li 2 O-MnO-ZrO 2 ; 51 of them were used for developing the neural network model and the rest 19viscosity data for the model validation. Calculated viscosities were in a good agreement with the experimental data. Based on the developed model, the effects of temperature and composition on the viscosity of fluorine-free fluxes were predicted and discussed.

Viskositas: Viscosity Prediction of Multicomponent Chemical Systems

“…With the dissociation in the chemical species MO, there is a reaction between the M 2+ ions that weaken the chain between Si-O-Si. MgO decreases the viscosity of chemical systems SiO2-CaO-Al2O3-MnO-MgO-K2O [49], FeO decreases the viscosity of chemical systems CaO-SiO2-Al2O3-MgO-P2O5 [50], CaO and MgO decay the viscosity of chemical systems CaO-MgO-SiO2-Al2O3 [51] and CaO-SiO2-Al2O3-B2O3-Na2O-TiO2-MgO-Li2O-MnO-ZrO2 [52], MnO in binary systems SiO2-MnO [53] and the addition of NiO decreases the viscosity of chemical systems SiO2-Al2O3-Fe2O3-CaO-MgO-TiO2-SO3-K2O-Na2O-P2O5 [54] in fully liquid physical systems. The addition of MO chemical species can cause an increase in viscosity in chemical systems when linked to the precipitation of solid phases, thus increasing their viscosity by the non-Newtonian behavior indicated by the Roscoe-Einstein equation [55] (Equation 11).…”

“…The action of O 2also results from the depolymerization of chains of chemical systems. Na2O decreases the viscosity of chemical systems CaO-SiO2-Al2O3-B2O3-Na2O-TiO2-MgO-Li2O-MnO-ZrO2 [52], Li2O decreases the viscosity of chemical systems SiO2-CaO-Al2O3-MgO-F --Na2O-MnO-Li2O-B2O3 [58] and the action K2O+Na2O decreases the viscosity of fluxes [59].…”

“…The M2O3 oxides weaken the structure of chemical systems by presenting high coordination [7] and by reacting with O 2- [49] for example. B2O3 decreases the viscosity of chemical systems CaO-SiO2-Al2O3-B2O3-Na2O-TiO2-MgO-Li2O-MnO-ZrO2 [52], Fe2O3, Cr2O3 and Al2O3 have amphoteric behavior in chemical systems Fe2O3-SiO2-FeO-MgO-Al2O3-CaO [60], CaO-SiO2-MgO-Al2O3-TiO2-Cr2O3 [61] and Al2O3-Na2O-K2O [62] respectively. Al2O3 increases the viscosity of chemical systems Al2O3-MgO [62] and SiO2-CaO-Al2O3-MgO-F --Na2O-MnO-Li2O-B2O3 [58]…”

“…In the development of an artificial neural network, training and test databases are usually used, and a validation database can also be used [11][12][13][14][15][16][17]. The training database is used to obtain the best parameter ratio of the artificial neural network, the validation database assists in the artificial neural network evaluation process during training, and the test database aims at the evaluation of the artificial neural network on unknown data.…”

“…Artificial neural networks (ANN) are computational models capable of establishing mathematical relationships in order to approach an optimal value, by updating these mathematical relationships in a finite number of interactions. Artificial neural networks are widely used in classification, resulting in discrete variables for image processing and recognition [11] with image-based search engines and biomedical diagnosis [12] and regression where the result is a continuous variable for the prediction of mechanical properties in microalloyed steels [13] and nickel superalloys [14] and in the prediction of viscosity in metallurgical slags [15] and oxide liquids [16].…”