No abstract

No abstract

No abstract

A preliminary study on the potential application of artificial neural networks in welded structures was expanded to metal inert gas welding of steel plates of grades D and DH 36. The main controllable variables were plate thickness, steel grade, plate cutting process, and heat input. A series of welded plates of each grade was manufactured, covering plate thicknesses of 6 and 8 mm. The topography of each welded plate was evaluated after tacking the plates together and after welding, allowing the actual distortion to be calculated. It was established that a multilayer perceptron network architecture configuration accurately represented the distortion for the 6 mm thickness plate, and for the 8 mm thickness plate after treatment of the data. The data generated were used to develop the PREDICTOR software package, which allows a distortion prediction to be produced, and to carry out a sensitivity analysis. Heat input was found to be the most sensitive factor related to distortion, with carbon content of the plates, yield/tensile strength ratio, carbon equivalent, and steel grade also having significant effects. Some test plates were modelled using finite element method software packages: the initially poor agreement was improved via the addition of significant detail, but the finite element model by its nature will normally predict symmetrical distortion from a symmetric weld, whereas the artificial neural network model developed was capable of predicting the asymmetric distortion observed in reality.

The current trend in ship construction is to reduce the thickness of the ship panels, in order to minimize weight and maximize vessel speed. The ship panels of interest consist of 4 mm thick butt welded plates. This reduction in panel thickness may lead to excessive plate distortion during welding, resulting in significant additional costs during assembly. A ferritic-pearlitic DH-36 steel is used, in which phase transformations during welding may affect the distortion and stress states observed. Two large plates, representative of ship panels, have been butt welded using a metal inert gas (MIG) process. The temperature histories have been recorded during welding and the resulting distortion profile has been obtained using digital photography. Neutron diffraction measurements have been performed to determine the residual stress state in the plates before welding, due to e.g. processing and laser cutting, and after butt welding of the plates. Reference matchsticks from the weld, heat affected zone (HAZ) and parent plate have been taken from similar locations in nominally identical plates and measured to obtain the strain/stress free lattice parameter, α0. A Rietveld analysis has been performed on the diffraction data. Post welding, hardness surveys have indicated the microstructural variation in the weld, parent plate and HAZ. Results from these on-going studies are presented which identify the key factors responsible for thin plate distortion.