Scholarlink

<p>This paper presents a cloud-native cyber-physical CNC manufacturing framework that integrates collaborative CNC operation with a tool wear condition monitoring (TWCM) case study for supervisory decision support. The framework combines edge–cloud connectivity, secure data exchange, and data-driven analytics to enable condition-informed scheduling and coordination across distributed manufacturing resources. As a representative analytics service, a vibration-based TWCM pipeline is implemented for CNC turning, where laser Doppler vibrometry signals are decomposed using variational mode decomposition (VMD) and processed through an AutoML-based regression workflow to estimate flank wear. Tool-health outputs are published to the cloud and linked to supervisory scheduling logic, supporting actions such as tool-change recommendations and job-queue updates. The system is demonstrated on CNC turning of AISI 1045 steel using carbide inserts in a multi-node edge–cloud testbed. The results show accurate wear estimation and illustrate how tool-health intelligence can be integrated into a collaborative cloud environment for decision support. The proposed framework does not implement autonomous machine-level closed-loop control, but provides an extensible pathway toward condition-aware CNC collaboration aligned with Industry 4.0 principles.</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

Cloud-based collaborative CNC manufacturing framework integrating tool wear monitoring and scheduling support

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年3月9日

查看全文
  • Imran,
  • Mourad Nouioua,
  • Samir Mekid

摘要

This paper presents a cloud-native cyber-physical CNC manufacturing framework that integrates collaborative CNC operation with a tool wear condition monitoring (TWCM) case study for supervisory decision support. The framework combines edge–cloud connectivity, secure data exchange, and data-driven analytics to enable condition-informed scheduling and coordination across distributed manufacturing resources. As a representative analytics service, a vibration-based TWCM pipeline is implemented for CNC turning, where laser Doppler vibrometry signals are decomposed using variational mode decomposition (VMD) and processed through an AutoML-based regression workflow to estimate flank wear. Tool-health outputs are published to the cloud and linked to supervisory scheduling logic, supporting actions such as tool-change recommendations and job-queue updates. The system is demonstrated on CNC turning of AISI 1045 steel using carbide inserts in a multi-node edge–cloud testbed. The results show accurate wear estimation and illustrate how tool-health intelligence can be integrated into a collaborative cloud environment for decision support. The proposed framework does not implement autonomous machine-level closed-loop control, but provides an extensible pathway toward condition-aware CNC collaboration aligned with Industry 4.0 principles.