Application of BPANN in spinning deformation of thin-walled tubular parts with longitudinal inner ribs

Abstract

Back-propagation artificial neural network (BPANN) is used in ball backward spinning in order to form thin-walled tubular parts with longitudinal inner ribs. By selecting the process parameters which have a great influence on the height of inner ribs as well as fish scale on the surfaceof the spun part, a BPANN of 3-8-1 structure is established for predicting the height of inner rib and recognizing the fish scale defect. Experiments data have proved that the average relative error between the measured value and the predicted value of the height of inner rib is not more than 5%. It is evident that BPANN can not only predict the height of inner ribs of the spun part accurately, but recognize and prevent the occurrence of the quality defect of fish scale successfully, and combining BPANN with the ball backward spinning is essential to obtain the desired spun part.

Keywords

artificial neural network / back-propagation / ball spinning / power spinning

References

[1] BasheerI A, HajmeerM. Artificial neural networks: fundamentals, computing, design and application [J]. Journal of Microbiological Methods, 2000, 43(1): 3-31

[2] WuR H, LiuH B, ChangH B, et al.. Prediction of the flow stress of 0.4C-1.9Mn-1.0Ni-0.2Mo steel during hot deformation [J]. J Mater Process Technol, 2001, 116(1–2): 211-218

[3] ChunM S, BiglouJ, LenardJ G, et al.. Using neural networks to predict parameters in the hot working of aluminum alloys[J]. J Mater Process Technol, 1999, 86(1–3): 245-251

[4] LiPing, XueKe-min, LüYan, et al.. Influence and prediction of hot deformation parameters on microstructure of Ti-15-3 alloy[J]. Trans Nonferrous Met Soc China, 2002, 12(3): 454-457

[5] WangXue-ye, QiuGuan-zhou, WangDian-zuo. Molten salt phase diagrams calculation using artificial neural network or pattern recognition bond parameters[J]. Trans Nonferrous Met Soc China, 1998, 8(1): 142-148

[6] KimD J, KimY C, KimB M. Optimization of the irregular shape rolling process with an artificial neural network [J]. J Mater Process Technol, 2001, 113(1–3): 131-135

[7] InamdarM V, DateP P, DesaiU B. Studies on the prediction of springback in air vee bending of metallic sheets using an artificial neural network [J]. J Mater Process Technol, 2000, 108(1): 45-54

[8] SeibiA, AlalawiS M. Prediction of fracture toughness using artificial neural networks (ANNs) [J]. Engineering Fracture Mechanics, 1997, 56(3): 311-319

[9] RotarescuM I. A theoretical analysis of tube spinning using balls [J]. J Mater Process Technol, 1995, 54(1–4): 224-229

[10] ParkJ W, KimY H, BaeW B. Analysis of tube-spinning processes by the upper-bound stream-function method [J]. J Mater Process Technol, 1997, 66(1–3): 195-203

[11] PrakashR, SinghalR P. Shear spinning technology for manufacture of long thin wall tubes of small bore [J]. J Mater Process Technol, 1995, 54(1–4): 186-192

[12] XueKe-min, LuYan. The disposal of key problems in the FEM analysis of tube stagger spinning [J]. J Mater Process Technol, 1997, 69(1–3): 176-179

[13] KangDa-chang. Study on the deformation mode of conventional spinning of plates [J]. J Mater Process Technol, 1999, 91(1–3): 226-230

[14] QuigleyE, MonaghanJ. Metal forming: an analysis of spinning processes [J]. J Mater Process Technol, 2000, 103(1): 114-119

[15] ChenM D, HsuR Q, FuhK H. Forecast of shear spinning force and surface roughness of spun cones by employing regression analysis[J]. International Journal of Machine Tools and Manufacture, 2001, 41(12): 1721-1734