A deep belief network to predict the hot deformation behavior of a Ni-based superalloy
- 376 Downloads
The hot deformation behavior of a Ni-based superalloy is studied by hot compressive experiments. The true stress is found to be highly affected by the deformation parameters, including strain rate and deformation temperature. The true stress dramatically decreases with decreasing strain rate or increasing deformation temperature. A deep belief network (DBN) model is developed for predicting true stress of the studied superalloy based on the experimental data. The structure of the developed DBN model is optimized layer by layer. The high accuracy indicates that the developed DBN model is able to effectively characterize the hot deformation behavior of the studied Ni-based superalloy. Moreover, the developed DBN model also has an excellent interpolation ability.
KeywordsNi-based superalloy Hot deformation Deep belief network
This work was supported by the National Natural Science Foundation Council of China (Grant No. 51375502), the National Key Basic Research Program (Grant No. 2013CB035801), the Project of Innovation-driven Plan in Central South University (No. 2016CX008), the Natural Science Foundation for Distinguished Young Scholars of Hunan Province (Grant No. 2016JJ1017), Program of Chang Jiang Scholars of Ministry of Education (No. Q2015140), and the Science and technology leading talent in Hunan Province (Grant No. 2016RS2006), and the Fundamental Research Funds for the Central Universities of Central South University (2016zzts311), China.
- 41.Kuremoto T, Kimura S, Kobayashi K, Obayashi M (2014) Time series forecasting using a deep belief network with restricted Boltzmann machine. Neuro Comput 137:47–56Google Scholar
- 45.Ahmed A, Yu K, Xu W, Gong Y, Xing E (2008) Training hierarchical feed-forward visual recognition models using transfer learning from pseudo-tasks. Comput Vis ECCV 5304:69–82Google Scholar
- 47.Tehovnik F, Burja J, Podgornik B, Godec M, Vode F (2015) Microstructural evolution of inconel 625 during hot rolling. Mater Technol 49(5):801–806Google Scholar