BP algorithm is the most widely used supervised training algorithms for multi-layered feedforward neural net works. However, BP takes long time to converge and quite sensitive to the initial weights of a network. In this paper, a modified cuckoo search algorithm is used to get the optimal set of initial weights that will be used by BP algorithm. And changing the value of BP learning rate to improve the error convergence. The performance of the proposed hybrid algorithm is compared with the stan dard BP using simple data sets. The simulation result show that the proposed algorithm has improved the BP training in terms of quick convergence of the solution depending on the slope of the error graph.

In this work, two groups of nanocomposite material, was prepared from unsaturated polyester resin (UPE), they were prepared by hand lay-up method. The first group was consisting of (UPE) reinforced with individually (ZrO2) nanoparticles with particle size (47.23nm). The second group consists of (UPE) reinforced with hybrid nanoparticles consisting of zirconium oxide and yttrium oxide (70% ZrO2 + 30% Y2O3) with particles size (83.98nm). This study includes the effect of selected volume fraction (0.5%, 1%, 1.5%, 2%, 2.5%, 3%) for both reinforcement nano materials. Experimental investigation was carried out by analyzing the thermo-physical properties like thermal conductivity, thermal diffusivity and specific heat for the polymeric composit