The Application of Technology Combining FEM andArtificial Neural Networks in Steel Tube FormingProcess

摘要

The quality of the cross piercing tube is related to many factors such as tube billet, processparameters and equipment characteristics. It is difficult to select a group of reasonable parametersto improve the quality of tubes. In this paper, artificial neural networks can be used to project databetween technical and qualitative parameters. the technology of combing FEM and artificial neuralnetworks were proposed, which makes use of results of FEM simulation to train the networks. Andthe parameters of corresponding process were obtained under certain quality conditions by thenetworks. The calculating precision of the technology has been proved by experiments. It isindicated that the technology is feasible for predicting product quality and determining reasonableprocess parameters.