A Materials Informatics Approach to Predicting the Sintered Density in Powder Metallurgy
The mechanical properties of powder metallurgy(PM)materials are closely related to their density,which is a result of a variety of combined factors including processing parameters,chemical composition,and raw materials.In this case we demonstrate an approach that uses machine-learning algorithms trained on experimental data to predict the sintered density of PM materials.Several regression algorithms were used to train the machine-learning models on the experimental dataset,and the multilayer perceptron model outperformed other models with a high correlation coefficient and low error.Then the sintered density was predicted by using this model and the predicted one agreed very well with the experimental data for each material,with the inaccuracy less than 2.7%.
Powder metallurgy sintered density machine learning data mining multilayer perceptron
Deng Zhenghua Yin Haiqing Jiang Xue Zhang Cong Zhang Kaiqi Zhang Tong Zheng Qingjun Qu Xuanhui
Collaborative Innovation Center of Steel Technology,University of Science and Technology Beijing,Bei Kennametal Inc,1600 Technology Way,PA 15650,USA Collaborative Innovation Center of Steel Technology,University of Science and Technology Beijing,Bei
国际会议
北京
英文
2041-2049
2018-09-16（万方平台首次上网日期，不代表论文的发表时间）