Lin Qiquan

Establishment of constitutive relationship model for 2519 aluminum alloy based on BP artificial neural network

An isothermal compressive experiment using Gleeble 1500 thermal simulator was studied to acquire flow stress at different deformation temperatures, strains and strain rates. The artificial neural networks with the error back propagation(BP) algorithm was used to establish constitutive model of 2519 aluminum alloy based on the experiment data. The model results show that the systematical error is small(δ=3.3%) when the value of objective function is 0.2, the number of nodes in the hidden layer is 5 and the learning rate is 0.1. Flow stresses of the material under various thermodynamic conditions are predicted by the neural network model, and the predicted results correspond with the experimental results. A knowledge-based constitutive relation model is developed.

Research on Galling Behavior in Square Cup Drawing of High Tensile Strength Steel

Based on the laboratory experiments, the drawing galling behavior in macro-scale is investigated in the square cup drawing of a high tensile strength steel SPFC590 in semi-dry condition. When using the non-coated dies (cold alloy tool steel (SKD11, SLD) and austempered ductile irons (ADI)) in semi-dry, the macro-scale galling can clearly observed on die and drawn cup surface after a few drawing cycles. The galling on the die surface occurs at the bottom point of the boundary between the straight and corner edge, and grows upward with the drawing cycles. On the drawn cup, the galling starts at the top of the same boundary and grows downward. Simultaneously, the finite element method (FEM) with DEFORM-3D was used as a tool to simulate the square cup drawing process with respect to the drawing force distribution and volume change analysis, which gave us a rational interpretation of the drawing galling phenomena and illustrated the galling performance and seizing tumour theoretically.