Prediction of Wear Characteristics of AA2219-Gr Matrix Composites Using GRNN and Taguchi-Based Approach

Insitu synthesis of Al- MgAl2O4 composites and parametric optimization of tribological characteristics

In this research, multiobjective optimization of tribological characteristics of Al-4Mg/in-situ MgAl2O4 composites fabricated via ultrasonic cavitation treatment assisted stir casting technique was carried out. Al-4Mg alloy dispersed with 0.5, 1 and 2 wt% in-situ MgAl2O4 was prepared and the microstructural and mechanical characterisation of the same has been carried out. Reinforcement addition, load and sliding velocity at 3 different levels was considered to attain the responses wear rate and friction coefficient. To identify optimised process condition for the developed composites to attain reduced friction coefficient and wear rate condition, grey analysis is tried out. Experimental results analysed via Grey relation and analysis of variance (ANOVA) proved wt.% of MgAl2O4 particles as significant parameter trailed by load and speed. Based on grey relational grade, minimal wear loss at lowest frictional coefficient can be attained for the composite dispersed with 2 wt% of in-situ MgAl2O4 at 20 N load and 2 m/s sliding velocity. Mechanisms behind the wear loss was analysed from worn out surface micrographs.

Multi-objective optimization of injection molded parts with insert based on IFOA-GRNN-NSGA-II

The physical properties of plastic products, such as local strength, wear resistance and electrical properties, can be improved by adding embedded parts in the appropriate position of the products, and the precision of plastic parts can also be improved. However, due to the addition of inserts, the flow and shrinkage around inserts will be affected. Compared with traditional injection molding products, the quality is difficult to predict. To solve this problem, the injection molded parts with inserts (electrostatic test box) was used as an example, according to the product structure, three objectives of volume shrinkage, warpage in the X direction, and warpage in the Z direction were optimized. A generalized regression neural network (GRNN) model was established with molding parameters as input and quality objectives as output. Improved fruit fly optimization algorithm (IFOA) was proposed to select the optimal smoothing parameters dynamically. Through the prediction of samples, the experimental results show that the model is superior to two comparative models. Non-dominated sorting genetic algorithm (NSGA-II) was used to solve the model, and the Pareto-optimal front was obtained. The entropy TOPSIS method was used to evaluate the Pareto-optimal front, and the optimal solution was obtained. The results show that IFOA-GRNN-NSGA is a reliable multi-objective optimization method.