Method for determining material parameters of crystal plasticity finite element model

Abstract

The invention discloses a method for determining material parameters of a crystal plasticity finite element model. The method comprises the following steps: (1) setting different material parameter combinations A; (2) performing crystal plasticity finite element calculation by adopting the parameter combination A to obtain true stress and true strain under different parameters; (3) establishing a deep belief neural network model by taking the parameter combination A as input and taking the true stress and true strain obtained in the step (2) as output; (4) selecting an additional material parameter combination B, calculating a crystal plasticity finite element and a deep belief neural network model to obtain true stress and true strain of different models, comparing the true stress and true strain, and verifying the accuracy of the deep belief neural network model; and (5) setting a plurality of groups of material parameter combinations C, carrying out deep belief network model calculation, comparing the calculated true stress true strain with a test value, and if the error is greater than a set value, continuing to modify the material parameter combinations C until the error is less than the set value, wherein the parameter combinations C are the material parameters of the crystal plasticity finite element model.

Description

Technical field: [0001] The invention belongs to the technical field of metal material processing engineering and relates to a method for determining material parameters of a crystal plastic finite element model. Background technique: [0002] High-strength titanium alloy has the advantages of high specific strength, good impact toughness, strong fatigue resistance and corrosion resistance, and is widely used to manufacture key structural parts such as aircraft landing gear and aeroengine blades. Through thermal deformation, the β phase is refined due to dynamic recrystallization, and then a fine and uniform structure can be obtained, which is conducive to improving the mechanical properties of the material. However, due to the different orientations of the β-phase in titanium alloys, the material will undergo inhomogeneous deformation and inhomogeneous recrystallization. [0003] Crystal plastic finite element is an important method to simulate the inhomogeneous deformatio...

AI Technical Summary

Problems solved by technology

[0004] The object of the present invention is to provide a method for determining the material parameters of the crystal plastic finite element model, the method obtains accurate crystal plastic finite element material parameters through the depth confidence neural network model, and adopts less calculation amount of the crystal plastic finite element, Solve the problems of uncertainty, large number of iterations, large amount of calculation, poor convergence and low precision caused by the trial and error method of crystal plastic finite element material parameters

Images