Production Scheduling Optimization of Garment Intelligent Manufacturing System Based on Big Data

Area of Science:

• Industrial Engineering
• Operations Research
• Computer Science

Background:

• The integrated cloth laying and cutting process in garment manufacturing faces efficiency challenges.
• Optimizing production schedules is crucial for minimizing waste and maximizing output.

Purpose of the Study:

• To propose an optimal scheduling method for the cloth laying and cutting garment production system.
• To leverage big data and genetic algorithms for enhanced production efficiency.

Main Methods:

• Utilized a genetic algorithm with real string chromosome representation.
• Implemented bit string crossover and mutation techniques to address algorithm premature convergence.
• Applied big data analytics to inform scheduling decisions.

Main Results:

• The proposed genetic algorithm method reduced cutting time from 736 minutes to 627 minutes.
• The optimized schedule eliminated all production idle time, compared to 113 minutes in the traditional plan.
• Identified specific processes (25, 28, 34, 35, 31) where idle time previously occurred.

Conclusions:

• The big data and genetic algorithm-based optimal scheduling method is effective for cloth laying and cutting production.
• This approach significantly improves production efficiency by reducing time and eliminating idle periods.