Optimization Of Process Parameters For U-Shape Sheet Metal Stamping

Generally speaking, springback problems have always existed in sheet metal forming process. Especially during the course of sheet metal bending and low-drawing, this phenomenon is obviously serious which greatly affect precision of parts and manufacture efficiency. So it is necessary to do further research to control the springback. There is not much research work of springback control formerly, however, and experience as well as trial-and-error method is used to reduce or eliminate the springback in engineering practice. But since the 90th of last century, with the gradual solution of wrinkling and cracking in the course of drawing, springback problem has daily risen to an important research project. In addition, ceaseless perfection of CAE simulation technology of sheet-metal pressing also provides a necessary foundation for research of springback control.The principal contents studied in this thesis are as follows:1. Several process parameters influencing springback are comprehensively studied. Taking U-shape sheet metal in NUMISHEET'93 into account, we arrange the combination of process parameters in orthogonal experiment method and get numerical simulation of sheet metal stamping. Then, the orthogonal table is obtained. In addition, how much the different process parameters influence springback is studied, and the parameter combination is obtained to minimize the springback quantity. Then a useful conclusion can be reached: several other parameters besides variable blank holder force, such as friction, also influence springback strongly.2. Nonlinear relationship between stamping process parameters and quantity of springback is obtained through the neural network, which accuracy is testified by the test samples.3. Nonlinear relationship of ANN model is used to get the smooth curve of process parameters to springback quantity, so as to compensate the deficiency of the widely used polygonal chart.4. Optimization of process parameters based on the neural network and orthogonal test is carried out. Within the range process parameters, ANN model, as the substitute of CAE numerical simulation test, combined with orthogonal test is introduced to further optimize the process parameters to make the sheet mental less. The work in paper shows: the combination of network, orthogonal test and numerical simulation may obviously lessen the time of optimizing process parameters and improve the process design efficiency. At the same time ,on condition that the time ofnumerical simulation is available, the more precise conclusion can be obtained.Less springback quantity is obtained via using both the ANN model and orthogonal experiment, comparing with only usage of the orthogonal test method.5. Springback quantity prediction is studied. Aided with Nonlinear relationship of ANN model, within the specimen of experiment, a certain springback quantity can be attained from the given suit of parameters without reusing the CAE software, thus time of process program is saved.