Scholarlink

<p>The classification of productive systems is essential for optimising industrial operations, enabling organisations to align production processes with strategic goals. This study introduces a computational framework for classifying productive systems—continuous process, mass production, batch production, and project-based production—using machine learning techniques. Input parameters, including production volume, product variety, flexibility, and workforce qualification, were utilised to train decision tree and random forest classifiers. The models were evaluated on synthetic and real-world datasets to ensure accuracy and generalisability. Decision trees provided interpretable classification rules, while random forest models enhanced robustness by aggregating predictions across multiple decision trees. The framework incorporated visualisation tools to highlight decision boundaries and feature importance, offering valuable insights into the underlying classification logic. Results showed that continuous processes are characterised by high production volumes and low flexibility, whereas batch and project-based production systems exhibit greater adaptability and product variety. Despite the models’ effectiveness, feature importance analysis revealed limited differentiation among input parameters, suggesting opportunities for dataset enrichment and feature engineering. The study also identifies potential improvements, such as integrating advanced machine learning algorithms and real-time operational data for dynamic classification. This research provides a scalable and interpretable tool for classifying productive systems, bridging theoretical foundations with practical applications. The proposed methodology aids decision-makers in designing, managing, and optimising production processes, contributing to enhanced operational efficiency and adaptability in diverse industrial contexts. By offering a robust classification framework, this study establishes a foundation for future advancements in production system analysis and optimisation.</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

Machine Learning-Based Classification of Productive Systems: A Framework for Operational Optimisation

  • 期刊论文

  • 发表日期：

    2025年2月24日

查看全文
  • Wendell de Queiróz Lamas,
  • Leonardo Calache

摘要

The classification of productive systems is essential for optimising industrial operations, enabling organisations to align production processes with strategic goals. This study introduces a computational framework for classifying productive systems—continuous process, mass production, batch production, and project-based production—using machine learning techniques. Input parameters, including production volume, product variety, flexibility, and workforce qualification, were utilised to train decision tree and random forest classifiers. The models were evaluated on synthetic and real-world datasets to ensure accuracy and generalisability. Decision trees provided interpretable classification rules, while random forest models enhanced robustness by aggregating predictions across multiple decision trees. The framework incorporated visualisation tools to highlight decision boundaries and feature importance, offering valuable insights into the underlying classification logic. Results showed that continuous processes are characterised by high production volumes and low flexibility, whereas batch and project-based production systems exhibit greater adaptability and product variety. Despite the models’ effectiveness, feature importance analysis revealed limited differentiation among input parameters, suggesting opportunities for dataset enrichment and feature engineering. The study also identifies potential improvements, such as integrating advanced machine learning algorithms and real-time operational data for dynamic classification. This research provides a scalable and interpretable tool for classifying productive systems, bridging theoretical foundations with practical applications. The proposed methodology aids decision-makers in designing, managing, and optimising production processes, contributing to enhanced operational efficiency and adaptability in diverse industrial contexts. By offering a robust classification framework, this study establishes a foundation for future advancements in production system analysis and optimisation.