Innovative Optimization of Mechanical Performance in Carbon Fiber-Reinforced Nylon Composite Using Artificial Neural Networks and Multi-Objective Genetic Algorithms

This research paper extensively investigates the mechanical performance and optimization for composite materials of carbon fiber-reinforced nylon (CF-nylon). All specimens are fabricated by utilizing an FFF 3D printer, with model 2040 industrial X from Delta Wasp company. Important mechanical tests, including tensile testing, compression testing, wear resistance assessment, and Izod impact testing, are conducted to evaluate the composite's strength, stiffness, wear resistance, and toughness. The minimum wear rate is 0.033939394 mm³ m⁻¹, and the maximum strengths for tensile, compression, and impact resistance of 40 MPa, 50 MPa, and 35.82 J m⁻¹ were, respectively, achieved with significant process parameters as per the experimental design matrix. The data derived from the experimental tests were utilized to train and validate an artificial neural network (ANN) model. The performance of CF-nylon is further optimized using multi-objective optimization using genetic algorithm (MOGA). The highest tensile strength, highest compression strength, lowest wear rate, and the highest impact resistance of 42.91 MPa, 51.51 MPa, 0.016275777 mm³ m⁻¹, and 37.55 J m⁻¹ have been achieved at 0.1811 mm layer height, 87% infill density, and in the x orientation, as per the hybrid heuristic tool.

Graphical Abstract