The optimization of scheduling in spacecraft manufacturing workshops is an important measure taken to reduce production costs and improve processing efficiency. In solving scheduling problems, genetic algorithms have been widely applied as efficient optimization algorithms. This study establishes a mathematical model for workshop job processing with the objective of minimizing processing time. Addressing the issues of premature convergence and low solution accuracy in standard genetic algorithms (SGA), an improved genetic algorithm is proposed. To obtain better populations, the crossover and mutation probabilities are automatically adjusted by referencing individual fitness values. Additionally, to avoid generating invalid solutions, genes are divided into different segments based on processing operations to improve crossover operations. The results of the case study demonstrate that the improved genetic algorithm exhibits better convergence and global search capabilities compared to the standard genetic algorithm, achieving significant improvements in scheduling structure optimization.