This paper aims to modeling and forecasting inflation rate in the Sudan using multilayer feed forward Neural Network with Back Propagation Algorithm. Yearly time–series data representing Inflation Rate (INF) Gross Domestic Product (GDP) , Exchange Rate (EXR), Demand for Money (M_2) for the Sudan covered the period from 1970 to 2014 are used in the analysis of this paper. Multilayer feed forward Neural Network with Back Propagation Algorithm was applied to the data. The empirical findings revealed that the training, validation and test curves are very similar. The best validation performance with mean squared error (MSE) 0.92.422 was found at epoch 4. The comparison between the actual inflation rate and the predicted showed that they are very close to each other which clearly reflected the efficiently of the model. This finding suggests that the ANN models create a significant power to modeling and forecasting the Sudan’s inflation rate.
Springback is a essential factor that impacts the feature of sheet metal in the fabrication. In sheet metal forming/fabrication process, the goal of the implemented research is to analyze the significant of forming parameters on the responses: springback in V-Bending of Cu/Al and Al/Cu. Sheet thickness, die angle, and punch radius with three levels everyone have been considered in the implemented work as the forming parameters. The effects of different mechanical operation/process parameters on V-bending of sheet metal have been tested through proposed sheet metals. Experiments have been executed as per Taguchi method (L9 orthogonal array). The optimum parameter conditions have been identified grounded on their effect on die angle with springback of the multi-layer metal.