Simulation of The Nickel Alloys Solvus Temperature in Accordance with Content: Compartison of Twodeep Learning Networks
Simulating the physical and mechanical properties of such complex alloys as nickel-based is challenging scientific task due to the nonlinearity of all relationship in the materials. The model being created should consider a huge number of uncorrelated factors, for many of which information may be absent or vague. The individual contribution of a chemical element out of a dozen possible ligants cannot be determined by traditional methods, and there are no general analytical models describing the effect of elements on the characteristics of alloys. Artificial neural networks might bea successful simulation tools that may account many implicit correlations and establish correspondences that cannot be identified by other, more familiar mathematical methods. However, the appropriate networks are hard to build as they require complex tuning to achieve high performance. Data engineering and data preprocessing may help at this stage. This paper focuses on combining deep network configuration selection based on physics and input engineering to simulate the solvus temperature of nickel alloys. We compare two frameworks. The bestperformance and stability achieved in the network with additional differential layer.
Keywords - Nickel Alloys, Artificial Neural Network, Simulation, Framework, Solvus Temperature.