Research And Application On Forming Limiting Of Cylindrical Cup Drawing Based On BP Neural Network

Leading artificial intelligence(AI) technology and method into pressing process is a study hotspot on pressing process field at present. Artificial neural network (ANN) is one kind of AI method which is stood up by imitating person's brain nerve delivering information. It is one kind of distributed parallel processing system, the acquired results save in the matrix with weight values distributed. By the network, a optional nonlinear input-output mapping relationship can be realized. Concrete mapping relationship materialize at the distributed linking weight values between neurons that build up the ANN. Due to the strong self-adaptability and self-learning-ability as well as excellent and robustness and tolerance ability, it can not only replace many traditional algorithm which is very complicated and timeconsuming, but also, because the processing to information is more close to person's thought activity habit, It provides a new way for solving the prediction of nonlinear system and unknown model. Drawing process is the most typical and complicated in sheet metal forming. Also is the widest applying pressing technology. As for drawing process, it is a very important question to confirm limiting drawing rate[m]. The limiting drawing rate is a very important index of blank's pressing capability, and it is the basic reference deciding to drawing pressing technology. Cylindrical cup is a typical axial symmetrical part, though the deformation of material is simple in drawing process, but during the drawing process, exists a lot of influence factors(including workpiece material character itself as well as each technological parameters), and they restrict mutually between the factors. So how to calculate the limiting drawing rate of a cup becomes a complicated nonlinear and multi-gene question. To predicting limiting drawing rate of the cylindrical cup accurately indeed is a very complex subject. The author put forward a method of ANN to calculate limiting drawing rate of cup part this time, it is a new thought for determining the cup's limiting drawing rate. A three-layer BP network structure is built up on the base of detailed analysis of influence factors of cup's limiting drawing rate in the article. Use this ANN model, better forecasting effect has been got, and the network has a higher precision, is satisfied with engineering design requirement. Study results indicate that ANN has obvious advantages to the multi-parameter coupling question, and it is fit for applying in pressing process field completely.The software has been developed by Microsoft Visual Basic 6.0 and MATLAB combined. It can run stably on various Windows's operating system, higher safety, reliability and accuracy are realized. And it possesses good transplant property and friendly man-machine interface.