Artificial Neural Network Model Assisted Optimization of Preparation of Sm-Co Nanoparticles
Sm-Co permanent magnets have the advantages of high Curie temperature and high anisotropic field strength,Sm-Co nanoparticles have important applications in the fields of ultra-high-density magnetic recording,nanocomposites,and biomedicine.However,it is difficult to synthesis Sm-Co nanoparticles,and the mechanism of the influence of various components and processes on the magnetic properties of Sm-Co nanoparticles is not clear.Machine learning algorithm enable to quickly find the relationship between multi-factor parameters and the material properties of interest,so it is widely used in the field of materials.This paper adopted a meth-od of calcium thermal reduction to synthesize Sm-Co nanoparticles.With machine learning algorithm,Sm-Co nanoparticle magnetic performance could be predicted.The model was used to analyze the influence of various factors on Sm-Co nanoparticle magnetic proper-ties,and the composition of Sm-Co nanoparticles was optimized.Sm-Co nanoparticles were prepared according to the optimization re-sults.Sm-Co nanoparticles were stably prepared by the inorganic method,and the composition parameters were changed through the experiments.The composition and process parameters of each sample were recorded,and the samples remanence(Br)and coercivity(Hcj)were tested,and the sample data table was finally established,and a neural network model was built.The model structure with three layers was built:input layer,hidden layer and output layer,in which,the input layer was consist of the composition parame-ters,the output layer was composed with Br and Hcj.The test set was used on the trained model,and the initial model performance was obtained.To optimize the neural network model,according to the training and prediction results of the model,extreme values in the da-ta were filtered out.By adjusting the model structure,the best fit model structure was set.Br and Hcj of the data samples were stratified shuffle split separately,and different iterations of the test to fit Br and Hcj of the samples were also performed.Using the optimized mod-el,the influence of each component parameter on Br and Hcj was studied separately through the curves of concentrations of SmCl3,CoCl2 and CaCl2 with the magnetic properties separately.By analyzing the interaction between the concentrations of SmCl3 and CoCl2 on the magnetic properties,an optimized composition window could be obtained,and Sm-Co nanoparticles with higher magnetic proper-ties could be obtained.Based on the optimized composition parameters predicted by the model,Sm-Co nanoparticles with Br of 42.10 A·m2·kg-1 and Hcj of 4.06 T were prepared,and the error between the predicted data and the experiment data could be lower than 10％,which further verified the prediction accuracy of the model.
NETL
NSTL
万方数据
