Application of hybrid SFLA-ACO algorithm and CAM softwares for optimization of drilling tool path problems

Area of Science:

• Manufacturing Engineering
• Operations Research
• Computational Intelligence

Background:

• Drilling processes incur significant non-productive time (up to 70%) due to tool switching and spindle movement.
• Minimizing this non-productive tool travel time is essential for optimizing manufacturing efficiency.
• Existing Computer-Aided Manufacturing (CAM) software is widely used but may not always provide optimal tool paths.

Purpose of the Study:

• To develop and evaluate a hybrid metaheuristic algorithm for minimizing non-productive tool travel time in drilling operations.
• To demonstrate the superiority of the proposed hybrid algorithm over commercially available CAM software solutions.
• To address the limitations of current CAM software in achieving optimal tool path solutions for real-world manufacturing problems.

Main Methods:

• Hybridization of the shuffled frog leaping algorithm (SFLA) and ant colony optimization (ACO) into a novel SFLA-ACO algorithm.
• Application of the hybrid SFLA-ACO algorithm to two industrial case studies: ventilator manifold and lift axle mounting bracket drilling problems.
• Comparative analysis of the SFLA-ACO algorithm's results against four commercial CAM software packages (Creo 6.0, Pro E, Siemens NX, Solidworks).

Main Results:

• The hybrid SFLA-ACO algorithm achieved superior results in minimizing non-productive tool travel time for both industrial case studies.
• The optimized tool paths generated by SFLA-ACO demonstrated significant improvements compared to those produced by commercial CAM software.
• The study validates that CAM software solutions are not universally optimal for drilling tool path optimization.

Conclusions:

• The proposed hybrid SFLA-ACO algorithm offers a more effective approach to optimizing drilling tool paths than conventional CAM software.
• Metaheuristic hybridization presents a promising avenue for enhancing efficiency in manufacturing processes by reducing non-productive time.
• Further research into hybrid optimization techniques can lead to substantial gains in industrial productivity and cost reduction.