Comparison of NSGA-II, MOALO and MODA for Multi-Objective Optimization of Micro-Machining Processes.

Area of Science:

• Manufacturing Engineering
• Materials Science
• Computational Intelligence

Background:

• Micro-machining is crucial for miniature products, with micro-turning and micro-milling being key processes.
• Machining performance is heavily influenced by cutting parameters, necessitating optimization.
• Conflicting objectives, such as maximizing material removal rate (MRR) while minimizing surface roughness (SR), complicate optimization.

Purpose of the Study:

• To apply metaheuristic multi-objective optimization algorithms for micro-machining.
• To generate Pareto optimal solutions for micro-turning and micro-milling.
• To comparatively evaluate the performance of NSGA-II, MOALO, and MODA algorithms in this context.

Main Methods:

• Utilized metaheuristic multi-objective optimization algorithms: Non-Dominated Sorting Genetic Algorithm II (NSGA-II), Multi-Objective Ant Lion Optimization (MOALO), and Multi-Objective Dragonfly Optimization (MODA).
• Generated Pareto optimal fronts representing trade-offs between conflicting machining objectives.
• Employed the Complex Proportional Assessment (COPRAS) method for comparative analysis of the algorithms' solutions.

Main Results:

• The study presents a comparative assessment of NSGA-II, MOALO, and MODA in micro-machining applications.
• Pareto optimal solutions were generated, illustrating the trade-offs between machining performance metrics.
• The COPRAS method provided a framework for evaluating and comparing the effectiveness of the different optimization algorithms.

Conclusions:

• Metaheuristic algorithms offer effective approaches for optimizing complex micro-machining processes.
• The comparative study provides insights into the relative performance of NSGA-II, MOALO, and MODA for achieving desired machining outcomes.
• Optimized cutting parameters are essential for enhancing the efficiency and quality of miniature product manufacturing.