Scholarlink

In the contemporary business landscape, effective management of production processes is crucial for organizational success. This study explores the application of process technology, particularly big data analysis with the Box-Plot tool, to identify and understand the causes of failures in the manufacturing process. The research employs a quantitative approach, analyzing data from 10,000 pieces using the statistical technique Box-Plot, to identify patterns and relationships between variables such as temperature, torque, and rotation speed. The results highlight the susceptibility of different types of pieces to specific failures, providing valuable insights for strategic management of the production process. Failures related to heat dissipation, power, tool malfunction, and overload are explored, revealing associations with operational variables. The analysis emphasizes the importance of avoiding extreme conditions, such as high temperatures and rotation speeds, to mitigate failures. Practical recommendations are offered to improve production process efficiency, showcasing the potential of big data analysis with the Box-Plot tool as a valuable decision-making tool. This study contributes to understanding the relationships between operational variables and failures in the manufacturing context, providing a solid foundation for future research and managerial practices.

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

Integrating Predictive Analysis into Manufacturing Operations: Improving Production Efficiency and Decision-Making

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Diego Paulo Rhormens,
  • José Folha Mós Neto,
  • Flavio Luiz Rodrigues,
  • Geraldo Cardoso de Oliveira Neto,
  • Marlene Amorim

摘要

In the contemporary business landscape, effective management of production processes is crucial for organizational success. This study explores the application of process technology, particularly big data analysis with the Box-Plot tool, to identify and understand the causes of failures in the manufacturing process. The research employs a quantitative approach, analyzing data from 10,000 pieces using the statistical technique Box-Plot, to identify patterns and relationships between variables such as temperature, torque, and rotation speed. The results highlight the susceptibility of different types of pieces to specific failures, providing valuable insights for strategic management of the production process. Failures related to heat dissipation, power, tool malfunction, and overload are explored, revealing associations with operational variables. The analysis emphasizes the importance of avoiding extreme conditions, such as high temperatures and rotation speeds, to mitigate failures. Practical recommendations are offered to improve production process efficiency, showcasing the potential of big data analysis with the Box-Plot tool as a valuable decision-making tool. This study contributes to understanding the relationships between operational variables and failures in the manufacturing context, providing a solid foundation for future research and managerial practices.