Scholarlink

We present an IoT-enabled mobile solution for industrial predictive maintenance that combines real-time monitoring, advanced analytics, and robust offline capabilities. By integrating TensorFlow-based models with IoT sensor data, our system achieves 85% fault-detection accuracy and proactively reduces unplanned downtime by 47%, lowering maintenance costs by 32%. Its three-layer architecture—data acquisition, real-time data integration, and ML-driven analytics—supports intelligent alerting and continuous monitoring. Local SQLite storage synchronizes seamlessly with the cloud, ensuring uninterrupted operation even during network outages. This approach enhances production continuity, optimizes resource allocation, and illustrates the strong potential of IoT-based predictive maintenance strategies in modern industrial settings.

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

IoT-Enabled Mobile System for Industrial Predictive Maintenance with Offline Capabilities and Real-Time Analytics

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Jesús Betancourt,
  • Leandro Dias,
  • Miguel Batista,
  • Rodrigo Correia,
  • Paulo Váz,
  • José Silva,
  • Pedro Martins,
  • Maryam Abbasi

摘要

We present an IoT-enabled mobile solution for industrial predictive maintenance that combines real-time monitoring, advanced analytics, and robust offline capabilities. By integrating TensorFlow-based models with IoT sensor data, our system achieves 85% fault-detection accuracy and proactively reduces unplanned downtime by 47%, lowering maintenance costs by 32%. Its three-layer architecture—data acquisition, real-time data integration, and ML-driven analytics—supports intelligent alerting and continuous monitoring. Local SQLite storage synchronizes seamlessly with the cloud, ensuring uninterrupted operation even during network outages. This approach enhances production continuity, optimizes resource allocation, and illustrates the strong potential of IoT-based predictive maintenance strategies in modern industrial settings.