Scholarlink

<p>Advancements in the smart manufacturing industry have proliferated real-time equipment health monitoring. It has the potential to enhance product dimensional accuracy, increase machine tool uptime, and reduce rework costs. Digital Twins introduce new opportunities for real-time monitoring of machining processes, enabling the consideration of variations in operations and environmental conditions. Digital Twin facilitates a deeper understanding of equipment’s health condition and enhances anomaly detection and fault diagnosis. Conspicuously, the proposed research leverages Digital Twin technology by proposing an innovative anomaly detection framework for machining that enables real-time equipment health monitoring. The proposed model identifies manufacturing patterns through secure surveillance utilizing Internet of Things-integrated blockchain technology. Additionally, a dual-directional convolutional neural network deep learning technique is employed to evaluate vulnerability detection in real-time, facilitating optimal decision-making. Performance validations indicate that the presented approach significantly enhances manufacturing monitoring capabilities. The results are validated in terms of low latency rate (6.32s), low data processing complexity with recall (96.63%), precision (95.56%), and F-Measure (95.60%).</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

Blockchain-based intelligent equipment assessment in manufacturing industry

  • 期刊论文

  • 发表日期：

    2025年5月16日

查看全文
  • Tariq Ahamed Ahanger,
  • Munish Bhatia,
  • Abdulrahman Alabduljabbar,
  • Abdullah Albanyan

摘要

Advancements in the smart manufacturing industry have proliferated real-time equipment health monitoring. It has the potential to enhance product dimensional accuracy, increase machine tool uptime, and reduce rework costs. Digital Twins introduce new opportunities for real-time monitoring of machining processes, enabling the consideration of variations in operations and environmental conditions. Digital Twin facilitates a deeper understanding of equipment’s health condition and enhances anomaly detection and fault diagnosis. Conspicuously, the proposed research leverages Digital Twin technology by proposing an innovative anomaly detection framework for machining that enables real-time equipment health monitoring. The proposed model identifies manufacturing patterns through secure surveillance utilizing Internet of Things-integrated blockchain technology. Additionally, a dual-directional convolutional neural network deep learning technique is employed to evaluate vulnerability detection in real-time, facilitating optimal decision-making. Performance validations indicate that the presented approach significantly enhances manufacturing monitoring capabilities. The results are validated in terms of low latency rate (6.32s), low data processing complexity with recall (96.63%), precision (95.56%), and F-Measure (95.60%).