A classification system based on a convolutional neural network was performed to recognize the different combustion patterns of Cu concentrate-SiO₂ mixtures tablets under oxidation gas to estimate their combustion behavior and phase changes in flash smelting. A suspended-combustion-test method involving high-speed digital microscopy and thermal measurements was employed to characterize the combustion behavior of each sample. The time series images-based pattern recognition method enabled the calculation of the chemical composition of the blended concentrates by transforming the network output into a probability distribution. The combustion of the blended-concentrate tablet was different from that of each single-concentrate tablet in terms of the combustion pattern, such as the shape of the molten part, and the temperature change pattern. It is interpreted that the change in the free surface shape of a tablet is an important region for combustion pattern recognition. Thus, only when blended samples were used as training data as well as single samples, a good correlation could be obtained between the measured and predicted values of its chemical compositions.

To provide more reliable data, liquidus lines and solidus lines of the Ni-Co-Cu system in the temperature range from 1400 to 1750K were determined by Thermogravimetry-Differential Thermal Analysis (TG-DTA). The liquidus lines and the solidus lines were determined for low Cu and high Ni compositions, for which data were lacking in previous studies. The obtained results can be used to determine the temperature required to melt the metal obtained by reducing waste lithium-ion batteries (LIBs) in the high-temperature metallurgical process of metal recycling from waste LIBs.