Directional solidification continuous casting (DSCC) process is a new manufacturing technology for metallic materials which combines advantages of both directional solidification technology and continuous casting tech...Directional solidification continuous casting (DSCC) process is a new manufacturing technology for metallic materials which combines advantages of both directional solidification technology and continuous casting technology. Unlimited long shaped metal with directionally solidifying microstructure can be produced by this process. It is experimentally shown that controlling condition of stable and continuous growth of single crystal structure means the precise control of the location of the S/L interface, which is affected and determined by seven process parameters. Moreover, these parameters are also interacted each other, so the disturbance of any parameters may cause the failure of controlling of S/L interface. In this paper, on the basis of analyzing the forming conditions of continuously directional microstructures in DSCC process, the control model of DSCC procedure by neural network control (NNC) method was proposed and discussed. Combining with the experiments, we first used the computer to simulate the effects of the solidification parameters on destination control variable (S/L interface) and the interactions among these parameters during DSCC procedure. Secondly many training samples necessary for neural network calculation can be obtained through the simulation. Moreover, these samples are inputted into neural network software (NNs) and trained, then the control model can be built up.展开更多
On the basis of analyzing the principles, equipment and control needs of directional solidification continuous casting (DSCC) process, the building and fulfilling methods of control model of DSCC procedure by neural n...On the basis of analyzing the principles, equipment and control needs of directional solidification continuous casting (DSCC) process, the building and fulfilling methods of control model of DSCC procedure by neural network control (NNC) method were proposed and discussed. Combining the experimental researches, firstly the computer is used to simulate the effects of those solidification parameters on destination control variable (S/L interface) and the reactions among those parameters during DSCC procedure; secondly many training samples can be obtained. Moreover, after these samples are input into neural network software (NNs) and trained, the control model can be built.展开更多
Microstructures of Cu-4.7Sn(%) alloys prepared by two-phase zone continuous casting(TZCC)technology contain large columnar grains and small grains.A compound grain structure,composed of a large columnar grain and at l...Microstructures of Cu-4.7Sn(%) alloys prepared by two-phase zone continuous casting(TZCC)technology contain large columnar grains and small grains.A compound grain structure,composed of a large columnar grain and at least one small grain within it,is observed and called as grain-covered grains(GCGs).Distribution of small grains,their numbers and sizes as well as numbers and sizes of columnar grains were characterized quantitatively by metallographic microscope.Back propagation(BP) artificial neural network was employed to build a model to predict microstructures produced by different processing parameters.Inputs of the model are five processing parameters,which are temperatures of melt,mold and cooling water,speed of TZCC,and cooling distance.Outputs of the model are nine microstructure quantities,which are numbers of small grains within columnar grains,at the boundaries of the columnar grains,or at the surface of the alloy,the maximum and the minimum numbers of small grains within a columnar grain,numbers of columnar grains with or without small grains,and sizes of small grains and columnar grains.The model yields precise prediction,which lays foundation for controlling microstructures of alloys prepared by TZCC.展开更多
The continuous casting technological parameters have a great influence on the secondary dendrite arm spacing of the slab, which determines the segregation behavior of materials. Therefore, the identification of techno...The continuous casting technological parameters have a great influence on the secondary dendrite arm spacing of the slab, which determines the segregation behavior of materials. Therefore, the identification of technological parameters of continuous casting process directly impacts the property of slab. The relationships between continuous casting technological parameters and cooling rate of slab for spring steel were built using BP neural network model, based on which, the relevant secondary dendrite arm spacing was calculated. The simulation calculation was also carried out using the industrial data. The simulation results show that compared with that of the traditional method, the absolute error of calculation result obtained with BP neural network model reduced from 0. 015 to 0. 0005, and the relative error reduced from 6, 76 % to 0.22 %. BP neural network model had a more precise accuracy in the optimization of continuous casting technological parameters.展开更多
An intelligent control plan for the secondary cooling of continuous casting of slab was put forward. An off-line simulation of the system by using neural networks combined with fuzzy logic control is provided. The res...An intelligent control plan for the secondary cooling of continuous casting of slab was put forward. An off-line simulation of the system by using neural networks combined with fuzzy logic control is provided. The results show that the intelligent control system can not only control the surface temperature of the bloom of the secondary cooling but also has a good ability of self-adaptation and self-learning.展开更多
文摘Directional solidification continuous casting (DSCC) process is a new manufacturing technology for metallic materials which combines advantages of both directional solidification technology and continuous casting technology. Unlimited long shaped metal with directionally solidifying microstructure can be produced by this process. It is experimentally shown that controlling condition of stable and continuous growth of single crystal structure means the precise control of the location of the S/L interface, which is affected and determined by seven process parameters. Moreover, these parameters are also interacted each other, so the disturbance of any parameters may cause the failure of controlling of S/L interface. In this paper, on the basis of analyzing the forming conditions of continuously directional microstructures in DSCC process, the control model of DSCC procedure by neural network control (NNC) method was proposed and discussed. Combining with the experiments, we first used the computer to simulate the effects of the solidification parameters on destination control variable (S/L interface) and the interactions among these parameters during DSCC procedure. Secondly many training samples necessary for neural network calculation can be obtained through the simulation. Moreover, these samples are inputted into neural network software (NNs) and trained, then the control model can be built up.
文摘On the basis of analyzing the principles, equipment and control needs of directional solidification continuous casting (DSCC) process, the building and fulfilling methods of control model of DSCC procedure by neural network control (NNC) method were proposed and discussed. Combining the experimental researches, firstly the computer is used to simulate the effects of those solidification parameters on destination control variable (S/L interface) and the reactions among those parameters during DSCC procedure; secondly many training samples can be obtained. Moreover, after these samples are input into neural network software (NNs) and trained, the control model can be built.
基金financially supported by the National Key Research and Development Plan of China (No.2016YFB0301300)the National Natural Science Foundation of China (Nos.51374025,51674027 and U1703131)the Beijing Municipal Natural Science Foundation (No.2152020)
文摘Microstructures of Cu-4.7Sn(%) alloys prepared by two-phase zone continuous casting(TZCC)technology contain large columnar grains and small grains.A compound grain structure,composed of a large columnar grain and at least one small grain within it,is observed and called as grain-covered grains(GCGs).Distribution of small grains,their numbers and sizes as well as numbers and sizes of columnar grains were characterized quantitatively by metallographic microscope.Back propagation(BP) artificial neural network was employed to build a model to predict microstructures produced by different processing parameters.Inputs of the model are five processing parameters,which are temperatures of melt,mold and cooling water,speed of TZCC,and cooling distance.Outputs of the model are nine microstructure quantities,which are numbers of small grains within columnar grains,at the boundaries of the columnar grains,or at the surface of the alloy,the maximum and the minimum numbers of small grains within a columnar grain,numbers of columnar grains with or without small grains,and sizes of small grains and columnar grains.The model yields precise prediction,which lays foundation for controlling microstructures of alloys prepared by TZCC.
文摘The continuous casting technological parameters have a great influence on the secondary dendrite arm spacing of the slab, which determines the segregation behavior of materials. Therefore, the identification of technological parameters of continuous casting process directly impacts the property of slab. The relationships between continuous casting technological parameters and cooling rate of slab for spring steel were built using BP neural network model, based on which, the relevant secondary dendrite arm spacing was calculated. The simulation calculation was also carried out using the industrial data. The simulation results show that compared with that of the traditional method, the absolute error of calculation result obtained with BP neural network model reduced from 0. 015 to 0. 0005, and the relative error reduced from 6, 76 % to 0.22 %. BP neural network model had a more precise accuracy in the optimization of continuous casting technological parameters.
基金Acknowledgements This work was supported by the National Key Fundamental Research Development Program of China （G200067202-2） and by Natural Science Foundation of China （50395102）.
文摘An intelligent control plan for the secondary cooling of continuous casting of slab was put forward. An off-line simulation of the system by using neural networks combined with fuzzy logic control is provided. The results show that the intelligent control system can not only control the surface temperature of the bloom of the secondary cooling but also has a good ability of self-adaptation and self-learning.
