The composition control of molten steel is one of the main functions in the ladle furnace(LF)refining process.In this study,a feasible model was established to predict the alloying element yield using principal compon...The composition control of molten steel is one of the main functions in the ladle furnace(LF)refining process.In this study,a feasible model was established to predict the alloying element yield using principal component analysis(PCA)and deep neural network(DNN).The PCA was used to eliminate collinearity and reduce the dimension of the input variables,and then the data processed by PCA were used to establish the DNN model.The prediction hit ratios for the Si element yield in the error ranges of±1%,±3%,and±5%are 54.0%,93.8%,and98.8%,respectively,whereas those of the Mn element yield in the error ranges of±1%,±2%,and±3%are 77.0%,96.3%,and 99.5%,respectively,in the PCA-DNN model.The results demonstrate that the PCA-DNN model performs better than the known models,such as the reference heat method,multiple linear regression,modified backpropagation,and DNN model.Meanwhile,the accurate prediction of the alloying element yield can greatly contribute to realizing a“narrow window”control of composition in molten steel.The construction of the prediction model for the element yield can also provide a reference for the development of an alloying control model in LF intelligent refining in the modern iron and steel industry.展开更多
The yield criteria of geomaterials play a crucial role in studying and designing the strength of materials and structures.The basic characteristics of yield criteria for geomaterials need to be studied under the frame...The yield criteria of geomaterials play a crucial role in studying and designing the strength of materials and structures.The basic characteristics of yield criteria for geomaterials need to be studied under the framework of continuum mechanics.These characteristics include the effects of strength difference（SD） of materials in tension and compression,normal stress,intermediate principal stress,intermediate principal shear stress,hydrostatic stress,twin-shear stresses,and the convexity of yield surface.Most of the proposed yield criteria possess only one or some of these basic characteristics.For example,the Tresca yield criterion considers only single-shear stress effect,and ignores the effect of SD,normal stress,intermediate principal stress,intermediate principal shear stress,hydrostatic stress,and twin-shear stresses.The Mohr-Coulomb yield criterion accounts for the effect of SD,normal stress,single-shear stress and hydrostatic stress,but disregards the effect of intermediate principal stress,intermediate principal shear stress,and twin-shear stresses.The basic characteristics remain to be fully addressed in the development of yield criterion.In this paper,we propose a new yield criterion with three features,that is,newly developed,better than existing criteria and ready for application.It is shown that the proposed criterion performs better than the existing ones and is ready for application.The development of mechanical models for various yield criteria and the applications of the unified strength theory to engineering are also summarized.According to a new tetragonal mechanical model,a tension-cut condition is added to the unified strength theory.The unified strength theory is extended to the tension-tension region.展开更多
基金supported by the National Natural Science Foundation of China(No.51974023)State Key Laboratory of Advanced Metallurgy,University of Science and Technology Beijing(No.41621005)。
文摘The composition control of molten steel is one of the main functions in the ladle furnace(LF)refining process.In this study,a feasible model was established to predict the alloying element yield using principal component analysis(PCA)and deep neural network(DNN).The PCA was used to eliminate collinearity and reduce the dimension of the input variables,and then the data processed by PCA were used to establish the DNN model.The prediction hit ratios for the Si element yield in the error ranges of±1%,±3%,and±5%are 54.0%,93.8%,and98.8%,respectively,whereas those of the Mn element yield in the error ranges of±1%,±2%,and±3%are 77.0%,96.3%,and 99.5%,respectively,in the PCA-DNN model.The results demonstrate that the PCA-DNN model performs better than the known models,such as the reference heat method,multiple linear regression,modified backpropagation,and DNN model.Meanwhile,the accurate prediction of the alloying element yield can greatly contribute to realizing a“narrow window”control of composition in molten steel.The construction of the prediction model for the element yield can also provide a reference for the development of an alloying control model in LF intelligent refining in the modern iron and steel industry.
基金supported by the National Natural Science Foundation of China(No.51604166)the China Postdoctoral Science Foundation(No.2016M590645)+2 种基金the Natural Science Foundation of Shandong Province(Nos.BS2015NJ003 and ZR2016JL018)the Qingdao Postdoctoral Research Project(No.2016130)China
基金Supported by the National Natural Science Foundation of China (59924033)
文摘The yield criteria of geomaterials play a crucial role in studying and designing the strength of materials and structures.The basic characteristics of yield criteria for geomaterials need to be studied under the framework of continuum mechanics.These characteristics include the effects of strength difference（SD） of materials in tension and compression,normal stress,intermediate principal stress,intermediate principal shear stress,hydrostatic stress,twin-shear stresses,and the convexity of yield surface.Most of the proposed yield criteria possess only one or some of these basic characteristics.For example,the Tresca yield criterion considers only single-shear stress effect,and ignores the effect of SD,normal stress,intermediate principal stress,intermediate principal shear stress,hydrostatic stress,and twin-shear stresses.The Mohr-Coulomb yield criterion accounts for the effect of SD,normal stress,single-shear stress and hydrostatic stress,but disregards the effect of intermediate principal stress,intermediate principal shear stress,and twin-shear stresses.The basic characteristics remain to be fully addressed in the development of yield criterion.In this paper,we propose a new yield criterion with three features,that is,newly developed,better than existing criteria and ready for application.It is shown that the proposed criterion performs better than the existing ones and is ready for application.The development of mechanical models for various yield criteria and the applications of the unified strength theory to engineering are also summarized.According to a new tetragonal mechanical model,a tension-cut condition is added to the unified strength theory.The unified strength theory is extended to the tension-tension region.
