Scholarlink

<p>The intelligent transformation of the pharmaceutical industry is of great significance for improving production efficiency and reducing costs, and workshop scheduling optimization is a key approach to achieving this goal. This study proposes a pharmaceutical intelligent manufacturing workshop scheduling method based on a hybrid particle swarm optimization algorithm. By integrating three well-established mechanisms including elite learning mechanism, dynamic inertia weight adjustment, and spiral contraction search strategy, the algorithm’s solution quality and convergence speed are improved. A multi-objective optimization model considering pharmaceutical-specific constraints such as batch tracing, cleaning validation, and quality inspection is constructed, with coordinated optimization aimed at minimizing completion time and production costs. Validation based on actual production data from a large pharmaceutical enterprise shows that the hybrid algorithm increases equipment utilization by 20.1%, shortens average flow time by 18.1%, achieves an on-time delivery rate of 91.5%, and reduces total production costs by 6.3%, with energy costs and inventory costs decreasing by 14.9% and 36.8% respectively. The research finds that the impact of scheduling efficiency on indirect costs is significantly greater than on direct costs, with a comprehensive indirect cost reduction rate of 42.3%. Statistical significance tests and ablation studies validate the algorithm’s effectiveness and the contribution of each component. Sensitivity analysis validates the algorithm’s robustness and parameter stability. The contributions of this study lie in three aspects: constructing an integrated scheduling model with pharmaceutical-specific constraints, developing an effective hybrid optimization approach, and establishing a systematic cost-efficiency analytical framework. This study provides theoretical support and practical guidance for pharmaceutical enterprises to implement intelligent manufacturing and holds important value for promoting digital transformation in the pharmaceutical industry.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Research on the Impact of Scheduling Efficiency on Production Costs in Pharmaceutical Intelligent Manufacturing Workshops Based on Improved Particle Swarm Optimization Algorithm

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年2月27日

查看全文
  • Ang Li

摘要

The intelligent transformation of the pharmaceutical industry is of great significance for improving production efficiency and reducing costs, and workshop scheduling optimization is a key approach to achieving this goal. This study proposes a pharmaceutical intelligent manufacturing workshop scheduling method based on a hybrid particle swarm optimization algorithm. By integrating three well-established mechanisms including elite learning mechanism, dynamic inertia weight adjustment, and spiral contraction search strategy, the algorithm’s solution quality and convergence speed are improved. A multi-objective optimization model considering pharmaceutical-specific constraints such as batch tracing, cleaning validation, and quality inspection is constructed, with coordinated optimization aimed at minimizing completion time and production costs. Validation based on actual production data from a large pharmaceutical enterprise shows that the hybrid algorithm increases equipment utilization by 20.1%, shortens average flow time by 18.1%, achieves an on-time delivery rate of 91.5%, and reduces total production costs by 6.3%, with energy costs and inventory costs decreasing by 14.9% and 36.8% respectively. The research finds that the impact of scheduling efficiency on indirect costs is significantly greater than on direct costs, with a comprehensive indirect cost reduction rate of 42.3%. Statistical significance tests and ablation studies validate the algorithm’s effectiveness and the contribution of each component. Sensitivity analysis validates the algorithm’s robustness and parameter stability. The contributions of this study lie in three aspects: constructing an integrated scheduling model with pharmaceutical-specific constraints, developing an effective hybrid optimization approach, and establishing a systematic cost-efficiency analytical framework. This study provides theoretical support and practical guidance for pharmaceutical enterprises to implement intelligent manufacturing and holds important value for promoting digital transformation in the pharmaceutical industry.