The thermal and acoustic isolation properties of unsaturated polyester composites reinforced by palm waste filler have been experimentally investigated. The composites have been prepared using hand lay-up technique with filler weight fraction of (0%, 3%, 5% and 7%). Three types of palm waste that (Date seed, old leaf bases and petiole) were ground and sieved separately to produce the filler with particle size ≤ 400µm. Thermal conductivity, thermal diffusivity, and specific heat capacity were examined using Hot Disk thermal analyses. The acoustic isolation property examined in a sound-insulated box. The experimental results show that the thermal conductivity and thermal diffusivity of the composite specimens reinforced by seed or old leaf bases filler increased with increasing the fillers weight fraction. While increasing the petiole filler decreased the thermal conductivity and thermal diffusivity by 19% and 40% respectively at 5% weight fraction as compared with a pure unsaturated polyester material. So, the composite reinforced with petiole filler has improved the thermal insulation properties. The composites samples reinforced with palm waste show higher sound absorption in compared to the pure unsaturated polyester material. The sound absorption properties of composite reinforced with 7% old leaf bases filler improved by 15% and 23% at low and high frequency respectively rather than of pure unsaturated polyester material.
Modeling and simulation are indispensable when dealing with complex engineering systems. It makes it possible to do essential assessment before systems are built, Cantilever, which help alleviate the need for expensive experiments and it can provide support in all stages of a project from conceptual design, through commissioning and operation. This study deals with intelligent techniques modeling method for nonlinear response of uniformly loaded paddle. Two Intelligent techniques had been used (Redial Base Function Neural Network and Support Vector Machine). Firstly, the stress distributions and the vertical displacements of the designed cantilevers were simulated using (ANSYS v12.1) a nonlinear finite element program, incremental stages of the nonlinear finite element analysis were generated by using 25 schemes of built paddle Cantilevers with different thickness and uniform distributed loads. The Paddle Cantilever model has 2 NN; NN1 has 5 input nodes representing the uniform distributed load and paddle size, length, width and thickness, 8 nodes at hidden layer and one output node representing the maximum deflection response and NN2 has inputs nodes representing maximum deflection and paddle size, length, width and thickness and one output representing sensitivity (∆R/R). The result shows that of the nonlinear response based upon SVM modeling better than RBFNN on basis of time, accuracy and robustness, particularly when both has same input and output data.