Optimization process planning using hybrid genetic algorithm and intelligent search for job shop machining.

Area of Science:

• Manufacturing Engineering
• Operations Research
• Computational Intelligence

Background:

• Process planning is crucial for computer-aided manufacturing, yet complex.
• Effective process plans require optimized operation sequences and resource selection (machine, tool, TAD).

Purpose of the Study:

• To develop an integrated approach for optimizing both operation sequencing and resource selection in process planning.
• To enhance the efficiency and effectiveness of computer-aided process planning (CAPP).

Main Methods:

• Divided process planning into preliminary (intelligent search for feasible sequences) and detailed stages (genetic algorithm for optimization).
• Utilized order and clustering constraints for operation sequencing and optimization constraints for resource selection.
• Employed intelligent search strategies and genetic algorithms concurrently.

Main Results:

• Generated feasible operation sequences through intelligent search in the preliminary stage.
• Achieved optimized operation sequences and resource selections (machine, cutting tool, TAD) in the detailed stage.
• Demonstrated simultaneous optimization of sequence and resources using integrated algorithms.

Conclusions:

• The proposed method effectively optimizes both operation sequence and resource selection in process planning.
• Integration of intelligent search and genetic algorithms offers a robust solution for complex CAPP challenges.
• This approach contributes to improved manufacturing efficiency through advanced process planning optimization.