High Temperature Flow Stress Prediction of Nano-Al_2O_3/Cu Composite Using an Artificial Neural Network

Alumina dispersion strengthened copper composite (nano-Al2O3/Cu composite) was recently emerged as a kind of potentially vi-able and attractive engineering material for applications requiring high strength, high thermal and electrical conductivities and resistance to softening at elevated temperatures. The nano-Al2O3/Cu composite was produced by internal oxidation. The microstructures of the composite were analyzed by the TEM and its hot deformation behavior was investigated by means of continuous compression tests per-formed on a Gleeble 1500 thermo-simulator. Making use of the modified algorithm–Levenberg-Marquardt (L-M) algorithm BP neural network, a model for predicting the flow stresses during hot deformation was set up on the base of the experimental data. Results show that the microstructures of the composite are characterized by uniform distribution of nano-Al2O3 particles in Cu-matrix. The sliding of dislocations is the main deformation mechanism. The dynamic recovery is the main softening mode with the flow stress decreasing gen-tly from 500 ℃ to 850 ℃. The recrystallization of Cu-matrix can be retarded late into as high as 850 ℃, when it happens only partially. The well-trained BP neural network model can accurately describe the influence of the temperature, strain rate, and true strain on the flow stresses, therefore, it can precisely predict the flow stresses of the composite under given deforming conditions and provide a new way to optimize hot deforming process parameters.

High Temperature Flow Stress Prediction of Nano-Al2O3/Cu Composite Using an Artificial Neural Network

Alumina dispersion strengthened copper composite (nano-Al2O3/Cu composite) was recently emerged as a kind of potentially viable and attractive engineering material for applications requiring high strength, high thermal and electrical conductivities and resistance to softening at elevated temperatures. The nano-Al2O3/Cu composite was produced by internal oxidation. The microstructures of the composite were analyzed by the TEM and its hot deformation behavior was investigated by means of continuous compression tests performed on a Gleeble 1500 thermo-simulator. Making use of the modified algorithm-Levenberg-Marquardt (L-M) algorithm BP neural network, a model for predicting the flow stresses during hot deformation was set up on the base of the experimental data. Results show that the microstructures of the composite are characterized by uniform distribution of nano-Al2O3 particles in Cu-matrix. The sliding of dislocations is the main deformation mechanism. The dynamic recovery is the main softening mode with the flow stress decreasing gently from 500 ℃ to 850 ℃. The recrystallization of Cu-matrix can be retarded late into as high as 850 ℃, when it happens only partially. The well-trained BP neural network model can accurately describe the influence of the temperature, strain rate, and true strain on the flow stresses, therefore, it can precisely predict the flow stresses of the composite under given deforming conditions and provide a new way to optimize hot deforming process parameters.