Optimization of work order scheduling in weaving looms using genetic algorithms

In the modern textile industry, customer-oriented production demands and short delivery deadlines create significant challenges in the planning of production processes. Particularly, scheduling job orders in weaving looms to meet delivery deadlines and minimizing type changeover durations are critical factors that directly impact production efficiency. These complex optimization problems require algorithmic solutions beyond traditional methods. In this thesis, genetic algorithms were employed to optimize the job scheduling processes in weaving looms. Genetic algorithms stand out with their strong global search capabilities, especially in high-dimensional and constrained optimization problems. The model developed in this study is based on a fitness function that minimizes type changeover durations while scheduling job orders to meet delivery deadlines. The performance of the model was tested on real production data obtained from a factory, and the results were analyzed in detail. The findings of the thesis demonstrate that genetic algorithms are an effective method for minimizing time losses and bottlenecks in production processes. By optimizing type changeover durations and improving adherence to delivery deadlines, production costs were reduced, and process efficiency was increased. This study highlights the potential of computer science-based methods in addressing industrial challenges and improving operational performance.