The aim of present experimental investigation is to compare the mechanical properties of Sisal, jute and kenaf fiber reinforced with glass fiber in polyester matrix hybrid composites. Hybrid composites were fabricated by hand lay-up technique. The tensile, flexural and impact tests were carried out on different composite samples as per the ASTM standards. It was observed that the tensile strength of jute/glass fiber composite is 1.94 and 1.59 times more than that of sisal/glass and kenaf/glass composites, respectively. The flexural load carrying capacity of sisal/glass composite is 3.4 and 2.83 times greater than those of jute/glass and kenaf/glass composites, respectively. Also, it can be seen that impact strength of jute/glass composite is almost equal to that of kenaf/glass composite and 1.13 times more than that of sisal/glass composite.

The Natural fiber composites form a combination of plant derived fibers with plastic binders (Polymer matrices). The fibers form the fillers or reinforcements of the composite and the matrix is the continuous phase. In general, fibers are principal load carrying members while the surrounding matrix keeps them in the desired position, acts as a load transfer medium between them. So fibers with good strength and modulus and having good bonding with matrix should be used to a produce a good quality composite material [1-3]. The mechanical efficiency of a fiber composite depends on the adhesion between the matrix and the reinforcement [4-7]. This paper is to evaluate impact and compression properties of pineapple fiber based reinforced composite with epoxy resin as matrix.

In this work, an interpretable machine learning framework was developed for optimizing friction stir welding (FSW) parameters during joining of AZ80A Mg alloy plates for lightweight structural applications. The proposed strategy integrates a multi-task neural network (MTNN) with particle swarm optimization (PSO) to enhance tensile strength (TS) and hardness (H). Welding speed (WS), rotational speed (RS), axial force (AF), tool tilt angle (TA), and pin geometry (PG) were considered as input variables. A face-centered central composite design was adopted for generating training data. MTNN architecture effectively captured nonlinear interactions among process variables and mechanical responses through shared feature learning and task-specific prediction branches, achieving prediction accuracies (R²) of 95.13% and 93.35% during training, and 86.57% and 84.02% during testing for TS and H, respectively, with the lowest mean prediction deviations among all evaluated models. SHapley Additive exPlanations (SHAP) analysis revealed WS, AF, and tapered cylindrical (TC) pin geometry significantly influenced joint performance. Subsequently, PSO was coupled with the trained MTNN to identify optimal parameter combinations yielding superior TS and H, and experimentally validated. SEM fractography confirmed ductile fracture behavior and Compared with RR, SVR, ANN, and RFR models, MTNN–PSO framework demonstrated lower prediction error, improved robustness, and enhanced interpretability.