We develop an efficiently improved knowledge-based neural network(KBNN)associated with optimization algorithms and finite element analysis(FEA)to accurately predict spring-back angles in metal sheet bending.The well-k...We develop an efficiently improved knowledge-based neural network(KBNN)associated with optimization algorithms and finite element analysis(FEA)to accurately predict spring-back angles in metal sheet bending.The well-known V and U prevalent processes of bending are considered.The KBNN predictive results are based on the empirical model and artificial neural network(ANN)modeling.The empirical model is constructed from the FEA results using response surface method,while the multilayer perceptron is employed to create the ANN.The trained KBNN can accurately model the relation-ship between the spring-back angles and process parameters.The obtained results are validated against other existing methods showing a high accuracy.展开更多
The analytical model for springback in arc bending of sheet metal can serve as an excellent design support.The amount of springback is considerably influenced by the geometrical and the material parameters associated ...The analytical model for springback in arc bending of sheet metal can serve as an excellent design support.The amount of springback is considerably influenced by the geometrical and the material parameters associated with the sheet metal.In addition,the applied load during the bending also has a significant influence.Although a number of numerical techniques have been used for this purpose,only few analytical models that can provide insight into the phenomenon are available.A phenomenological model for predicting the springback in arc bending was proposed based on strain as well as deformation energy based approaches.The results of the analytical model were compared with the published experimental as well as FE results of the authors,and the agreement was found to be satisfactory.展开更多
The application of a thermal source in non-contact forming of sheet metal has long been used. However, the replacement of this thermal source with a laser beam promises much greater controllability of the process. Thi...The application of a thermal source in non-contact forming of sheet metal has long been used. However, the replacement of this thermal source with a laser beam promises much greater controllability of the process. This yields a process with strong potential for application in aerospace, shipbuilding, automobile, and manufacturing industries, as well as the rapid manufacturing of prototypes and adjustment of misaligned components. Forming is made possible through laser-induced non-uniform thermal stresses. In this letter, we use the geometrical transition from rectangular to circle-shaped specimen and ring-shaped specimen to observe the effect of geometry on deformation in laser forming. We conduct a series of experiments on a wide range of specimen geometries. The reasons for this behavior are also analyzed. Experimental results are compared with simulated values using the software ABAQUS. The utilization of line energy is found to be higher in the case of laser forming along linear irradiation than along curved ones. We also analyze the effect of strain hindrance. The findings of the study may be useful for the inverse problem, which involves acquiring the process parameters for a known target shape of a wide range of complex shape geometries.展开更多
文摘We develop an efficiently improved knowledge-based neural network(KBNN)associated with optimization algorithms and finite element analysis(FEA)to accurately predict spring-back angles in metal sheet bending.The well-known V and U prevalent processes of bending are considered.The KBNN predictive results are based on the empirical model and artificial neural network(ANN)modeling.The empirical model is constructed from the FEA results using response surface method,while the multilayer perceptron is employed to create the ANN.The trained KBNN can accurately model the relation-ship between the spring-back angles and process parameters.The obtained results are validated against other existing methods showing a high accuracy.
文摘The analytical model for springback in arc bending of sheet metal can serve as an excellent design support.The amount of springback is considerably influenced by the geometrical and the material parameters associated with the sheet metal.In addition,the applied load during the bending also has a significant influence.Although a number of numerical techniques have been used for this purpose,only few analytical models that can provide insight into the phenomenon are available.A phenomenological model for predicting the springback in arc bending was proposed based on strain as well as deformation energy based approaches.The results of the analytical model were compared with the published experimental as well as FE results of the authors,and the agreement was found to be satisfactory.
文摘The application of a thermal source in non-contact forming of sheet metal has long been used. However, the replacement of this thermal source with a laser beam promises much greater controllability of the process. This yields a process with strong potential for application in aerospace, shipbuilding, automobile, and manufacturing industries, as well as the rapid manufacturing of prototypes and adjustment of misaligned components. Forming is made possible through laser-induced non-uniform thermal stresses. In this letter, we use the geometrical transition from rectangular to circle-shaped specimen and ring-shaped specimen to observe the effect of geometry on deformation in laser forming. We conduct a series of experiments on a wide range of specimen geometries. The reasons for this behavior are also analyzed. Experimental results are compared with simulated values using the software ABAQUS. The utilization of line energy is found to be higher in the case of laser forming along linear irradiation than along curved ones. We also analyze the effect of strain hindrance. The findings of the study may be useful for the inverse problem, which involves acquiring the process parameters for a known target shape of a wide range of complex shape geometries.
