材料热物理性能.pdf

Use of ANN to Simulate the Effects of Welding Process Parameters in Curved Steel Plates: Residual Stresses, Strains and Distortions R. L. Klein V.H. Mucino P. Klinkhachorn M. Awang Lane Department of Computer ScienceElectrical Eng., Department of Mechanical and Aerospace Eng. West Virginia University, P.O. Box 6109, West Virginia University, P.O. Box 6106, Morgantown, WV 26506-6109,USA Morgantown, WV 26506-6106, USA Key Words: Steel Welding Process, Finite Element Simulation. Neural Network Abstract- In large steel fabrication industries such as [8,9]. More recently, various research efforts have been shipbuilding, and high-speed train guideways, the problem of made to control welding process parameters, aiming at residual stresses and overall distortion has been and reducing the distortions and residual stress effects [10,11]. continues to he a major issue. In the last few decades, various research efforts have heen directed at the control of the welding process parameters aiming to reduce distortions and 11. FINITE ELEMENT SIMULATION residual stresses. Yet. in actual practice, large amounts of resources are still required to rework welds. These costs In the finite element analysis, direct use of enthalpy and increase production costs and delay work completion. latent heat is made to reflect the phase change of the weld In