Compression moulding networks

In this research, an application of artificial neural network in prediction of the rubber o-ring shrinkage in compression moulding is presented. A back propagation neural network was developed to determine the shrinkage based on amount of sulphur, the amount of carbon black, the mould temperature, an inside diameter and a cross sectional diameter. The neural network prediction for an inside diameter shrinkage and a cross sectional diameter shrinkage indicate that architectures 5-11-21-1 and 5-11-16-1 provide an optimized prediction within 95.9% and 96.1% accuracy, respectively. 

Key Words Neural Network, Shrinkage, Rubber Compression Moulding. 

The networks studied were prepared from reactions carried out at different initial dilutions. Aliquots of reaction mixtures were transferred to moulds, which were maintained at the reaction temperature under anhydrous conditions, and were allowed to proceed to complete reaction(32). Sol fractions were removed and shear moduli were determined in the dry and equilibrium-swollen states at known temperatures using uniaxial compression or a torsion pendulum at 1Hz. The procedures used have been described in detail elsewhere(26,32). The shear moduli(G) obtained were interpreted according to Gaussian theory(33 34 35) to give values of Mc, the effective molar mass between junction points, consistent with the affine behaviour expected at the small strains used(34,35). 

---