Create Your First Project
Start adding your projects to your portfolio. Click on "Manage Projects" to get started
Optimization of Milling Parameters for GFRCs using Genetic Algorithms
Project type
Mechanical Design
Date
Dec 2021 - Jan 2022
Skills
MATLAB
This project focuses on optimizing milling parameters for Glass Fiber Reinforced Composites (GFRCs) by employing Genetic Algorithms to minimize surface roughness and meet specific quality standards. This involved developing and fine-tuning a genetic algorithm to identify the optimal cutting speed, feed rate, and depth of cut. The project also explored the impact of various algorithm parameters on solution quality and convergence speed, ultimately achieving a balance between computational efficiency and accuracy.
Key Features:
- The project involved integrating an Artificial Neural Network (ANN) model to predict surface roughness based on input variables such as cutting speed, feed rate, and depth of cut. This model was developed in a separate project titled "Artificial Neural Networks for Predicting Surface Roughness in Milling GFRCs." Further details on the neural network model can be found in that project.
- A thorough investigation was conducted into key parameters of the Genetic Algorithm, including population size, number of generations, and genetic operator settings. The project compared different initialization methods to assess their impact on convergence speed and solution quality.
- A penalty-based approach was adopted to handle categorical variables and constraints, ensuring that solutions remained within feasible and realistic bounds.
- Multiple solutions from various initializations were compared to evaluate the effectiveness of the Genetic Algorithm in reaching global minima, analyzing convergence behavior to identify optimal configurations.
- The Genetic Algorithm was fine-tuned to balance the exploration of the solution space with rapid convergence, adjusting population sizes and the number of generations to enhance robustness.
- The project successfully reduced surface roughness to the desired 2 μm target, demonstrating the effectiveness of the optimized milling parameters in improving the quality and precision of GFRC components.
