Artificial neural networks – an aid to welding induced ship plate distortion?

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.

Artificial neural networks as an aid to steel plate distortion reduction

“…Along with carbon these were largely unknown contributors to distortion, and the effects have been explained elsewhere [5,6]. The plate rolling treatment results showed that a normalised rolled process generated less subsequent distortion.…”

Weldability and weld performance of candidate austenitic alloys for advanced ultrasupercritical fossil power plants

“…Several investigators have used neural network models to predict properties and process variables. [64][65][66][67] In the function fit model by Babu et al, the free energy difference between ferrite and austenite was calculated as a function of composition and was related to FN. Vitek et al developed two neural net models, the first one, FNN-1998, to predict FN based on composition, and the second one, ORFN, to include the effects of cooling rate on the weld microstructure.…”

Modelling weld bead geometry using neural networks for GTAW of austenitic stainless steel

“…Artificial neural networks have been applied to analyse weld induced deformation in ship plate. 17 The prediction of weld bead geometry using ANNs has also been reported in the work of Vasudevan et al 18 Multilayer feed forward neural networks have been developed for modelling and online adjustment of welding parameters. 19 Fuzzy logic based techniques have also been used in the welding process.…”