Scholarlink

<p>In response to the growing demands for high-precision machining and optimized operating costs, this study proposes an Internet of Things-enabled smart tool condition monitoring framework for CNC milling operations. The system integrates multi-sensor data acquisition with a Raspberry Pi 4 Model B controller and utilizes Python-based communication with the ThingSpeak™ cloud for real-time monitoring and analysis. A fuzzy logic algorithm is employed for decision making, with rule sets derived from ISO 18434-2008 (infrared thermography) and ISO 10816-3:2009 (vibration severity). Sixteen fuzzy rules link input parameters—temperature and vibration to machine condition, using trapezoidal and triangular membership functions to define operational states. The framework effectively detects flank wear and other tool degradations in real time, supporting proactive maintenance and improved machining efficiency. The implementation demonstrates the feasibility of a scalable, intelligent monitoring system that bridges the gap between traditional CNC systems and Industry 4.0 standards.</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

Internet of Things enabled framework for smart process monitoring in CNC milling: an experimental approach

  • 期刊论文

  • 发表日期：

    2026年1月29日

查看全文
  • Padmaja Anipey,
  • Medidi Rajasekhar,
  • Balla Srinivasa Prasad

摘要

In response to the growing demands for high-precision machining and optimized operating costs, this study proposes an Internet of Things-enabled smart tool condition monitoring framework for CNC milling operations. The system integrates multi-sensor data acquisition with a Raspberry Pi 4 Model B controller and utilizes Python-based communication with the ThingSpeak™ cloud for real-time monitoring and analysis. A fuzzy logic algorithm is employed for decision making, with rule sets derived from ISO 18434-2008 (infrared thermography) and ISO 10816-3:2009 (vibration severity). Sixteen fuzzy rules link input parameters—temperature and vibration to machine condition, using trapezoidal and triangular membership functions to define operational states. The framework effectively detects flank wear and other tool degradations in real time, supporting proactive maintenance and improved machining efficiency. The implementation demonstrates the feasibility of a scalable, intelligent monitoring system that bridges the gap between traditional CNC systems and Industry 4.0 standards.