Scholarlink

This study studies the role of machine availability in improving production efficiency in manufacturing and explores neural networks (NN) for predictive maintenance. Frequent machine downtime poses a significant challenge to operational reliability and customer satisfaction. Advanced NN-based models were developed using data from a case study in the flooring industry, incorporating maintenance schedules, staffing levels and operational parameters. The results showed exceptional performance, with validation accuracies ranging from 99.6% to 100%, error rates as low as 0% and F1 scores of up to 100%. Shapley analysis identified key factors influencing machine availability, including maintenance personnel, preventive tasks and work schedules. These results underscore the potential of predictive analytics to minimise downtime, improve equipment effectiveness and optimise maintenance strategies, providing valuable insights to improve industrial operations.

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

Predictive Maintenance Using Neural Networks and Shapley Analysis – Case Study

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Monika Kulisz,
  • Katarzyna Antosz,
  • Justyna Michaluk,
  • Arkadiusz Gola

摘要

This study studies the role of machine availability in improving production efficiency in manufacturing and explores neural networks (NN) for predictive maintenance. Frequent machine downtime poses a significant challenge to operational reliability and customer satisfaction. Advanced NN-based models were developed using data from a case study in the flooring industry, incorporating maintenance schedules, staffing levels and operational parameters. The results showed exceptional performance, with validation accuracies ranging from 99.6% to 100%, error rates as low as 0% and F1 scores of up to 100%. Shapley analysis identified key factors influencing machine availability, including maintenance personnel, preventive tasks and work schedules. These results underscore the potential of predictive analytics to minimise downtime, improve equipment effectiveness and optimise maintenance strategies, providing valuable insights to improve industrial operations.