In recent years, there has been a growing replacement of synthetic fibers by natural ones, particularly by autochthonous materials. In the case of Algeria, the most abundant plant resources are the PALF (Pineapple leaf fiber), the date palm, and the Alfa fibers. In this work, the development and use of analytical and numerical methods are proposed to predict the mechanical properties of layers based on natural fibers that will be applied to manufacture skins of the sandwich cylinder. To achieve these predictions, four analytical models were used, namely the Halpin–Tsai, the Chamis, the Hashin vs. Rosen, and the ROM. The analytical results were compared with the numerical simulations and experimental data. The prediction of the elastic properties of the three fiber-based eco-composites showed an important dispersion in terms of stiffness.
Carbon dioxide emissions due to fossil fuels cause environmental problems, global warming and climatic change, hence the need to replace them with renewable energy sources is necessary and among the solutions is the use of hydrogen. The difficulty in using hydrogen does not lie in its production but rather in securing its transport by canalization and storage in tanks because a simple leak will cause an explosion. At the present time, both industrials and researchers are trying to replace conventional pipes made of very heavy metallic steel, which have corrosion problems and costly maintenance, by pipes made of very light composites, having a long life time and low maintenance due to the fact that they are nonmetallic (i.e. do not have corrosion problems). The use of composite pipes contributes to the reduction of their cost prices and installation costs. In this perspective, the present study focuses on the design and manufacturing, by the filament winding technique, of composite tubes having the same type of twisted natural fiber but two types of polyester resins, supplied by two different manufacturers, have been used. Test specimens were cut from the elaborated composite tubes in their longitudinal direction according to the ASTM D790-17 standard and then tested in 3-point bending with a speed of 5 mm/min using a Walter & Bai tensile machine. It is important to note that the specimens were both on their concave faces and on the convex one. The obtained stress/displacement response curves allowed to determine the mechanical properties, namely the stress, the Young's modulus and the displacement at break. In addition, for both types of polyester resin, the resistances of the specimens tested on their external faces were higher than those tested on their internal ones.
This research work aims to implement empirical models for predicting the failure pressure of a pipeline corroded with a single defect and internal pressure applications. For this purpose, five approaches were used: two artificial intelligence (AI) models with experimental data, a finite-element model (FEM), and two analytical models (ASME B31G modified and DNV-RP-F101). The two proposed artificial models were implemented and optimized in order to find their best performance. The first AI method is an artificial neural network with multilayer perceptron (ANN-MLP), and the second is a support vector machine radial basis function (SVM-RBF). The comparison of the results of these two models proves the good precision of the ANN-MLP, with the correlation coefficient R = 0.9906 and R = 0.9888, ahead of the SVM-RBF with R = 0.9290 and R = 0.9260, respectively, for the two phases of training and testing. In addition, the output results of ANN-MLP are analyzed by William’s diagram; it was noted that 97.82% (180/184) of points belong to the field of validity and applicability of the artificial optimal model. In addition, the sensitivity analysis demonstrates a linear correlation between depth defect and the failure pressure with 32.77%, followed by the length of defect and the inner diameter with 20.04% and 19.81%, respectively. According to the present regression analysis, the results obtained from the ANN-MLP and finite-element method (FEM) are more accurate compared with SVM-RBF and other analytical models. However, the predicted failure pressure values demonstrated strong agreement across all the five approaches.