Artificial Neural Network Prediction of Weld Distortion Rectification using a Travelling Induction Coil
نویسندگان
چکیده
An experimental investigation has been carried out to determine the applicability of an induction heating process with a travelling induction coil for the rectification of angular welding distortion. The results obtained from experimentation have been used to create artificial neural network models with the ability to predict the welding induced distortion and the distortion rectification achieved using a travelling induction coil. The experimental results have shown the ability to reduce the angular distortion for 8 mm and 10 mm thick DH36 steel plate and effectively eliminate the distortion on 6 mm thick plate. Results for 6 mm plate also show the existence of a critical induction coil travel speed at which maximum corrective bending occurs. Artificial neural networks have demonstrated the ability to predict the final distortion of the plate after both welding and induction heating. The models have also been used as a tool to determine the optimum speed to minimise the resulting distortion of steel plate after being subjected to both welding and induction heating processes.
منابع مشابه
Surface Tension Prediction of Hydrocarbon Mixtures Using Artificial Neural Network
In this study, artificial neural network was used to predict the surface tension of 20 hydrocarbon mixtures. Experimental data was divided into two parts (70% for training and 30% for testing). Optimal configuration of the network was obtained with minimization of prediction error on testing data. The accuracy of our proposed model was compared with four well-known empirical equations. The arti...
متن کاملSolubility Prediction of Drugs in Supercritical Carbon Dioxide Using Artificial Neural Network
The descriptors computed by HyperChem® software were employed to represent the solubility of 40 drug molecules in supercritical carbon dioxide using an artificial neural network with the architecture of 15-4-1. The accuracy of the proposed method was evaluated by computing average of absolute error (AE) of calculated and experimental logarithm of solubilities. The AE (±SD) of data sets was 0.4 ...
متن کاملStream Flow Prediction in Flood Plain by Using Artificial Neural Network (Case Study: Sepidroud Watershed)
In order to determine hydrological behavior and water management of Sepidroud River (North of Iran-Guilan) the present study has focused on stream flow prediction by using artificial neural network. Ten years observed inflow data (2000-2009) of Sepidroud River were selected; then these data have been forecasted by using neural network. Finally, predicted results are compared to the observed dat...
متن کاملEvaluation of Ultimate Torsional Strength of Reinforcement Concrete Beams Using Finite Element Analysis and Artificial Neural Network
Due to lack of theory of elasticity, estimation of ultimate torsional strength of reinforcement concrete beams is a difficult task. Therefore, the finite element methods could be applied for determination of strength of concrete beams. Furthermore, for complicated, highly nonlinear and ambiguous status, artificial neural networks are appropriate tools for prediction of behavior of such states. ...
متن کامل