شبيه سازي تاثير سرعت انجماد بر ريزساختار آلياژهاي ريختگي آلومينيوم با استفاده از مدل شبكه عصبي مصنوعي

Simulation of Solidification Rate Effects on the Microstructure of AI-Alloy Castings Using Artificial Neural Network

III cast aluminum and its alloys. ʹlie microstructure varies under different solidification conditions, causing variations ill their mechanical properties. Thew materials IUtʹ basically produced in sand and metallic molds or through die casting, each of whictt is associated with a unique .\OUdlfiea/ion regime with significantly different (ʹooling rates so that the resulting microstructure strongly depends 011 tlte casting method used. In the present study, the effect." of such important sotidlfication parameters as cooling rate, solidification front velocity, and thermal gradient at tire solid-liquid interface on secondary dendrite arm spacing were Investigated. B.v a directional solidification system, tile muthematicul relation between cooling rate and dendrite spacing was extracted for several commercially important ahnnintun 0110)ʹ.c, A neural network model was trained using the experimental values of cooling rates and secondary dendrite arm spocing. Reliable prediction of these values was made from the trained network aud their corresponding diagrams were constructed.. .4 gooa agreement was found between simulation and experimental values. It is concluded thut the neurul network constructed ill this study cun be employed to predict the relationship between cooling rate and dendrite arm spacing, which is difficult, if not iompossible, to accomplish experimentally.