Neural network analysis for the solidification scheme of the recycled metal casting

The use of recycled materials as one of the great results for the industrial raw materials shortage may face serious problems during the mold casting process. This paper researches the difference in solidification step between the edges and the center of the aluminum recycled cast. The implementation of such research passes through two verification steps; the removal of the chemical dyes and then to melt the recycled aluminum cans in a ceramic container in order to produce the metallic 60 x 13cm mold. Six thermocouples are inserted on the casting edges and the center and liked directly to a computer system in order to simultaneously record the temperature readings from the start of the cooling/solidification process. The Artificial Neural Network ANN approach is applied to the recorded data via the utilization of the software MATLAB in order to analyze the cooling curves and determine the mathematical representation of the solidification layers through the casting. The interior layers microstructure is examined via SPECTROPORT mobile metal analyzer so as to detect the solidification trend through the examined ingots. The edges of the casting are shown to solidify more quickly than the central region and also it is demonstrated via the microstructural samples that the boundaries are more clear in the center than these at the edges.