Scholarlink

<p>Cognitive machine tools are not new, but few are fully or even partially cognitive. Emerging technologies like machine learning and machine vision can transform a regular machine into a cognitive one. This work aims to retrofit an existing drilling machine into a cognitive tool by integrating a variable frequency drive, microcomputer, and camera. A dataset was created using images of four materials: Aluminium, copper, wood, and mild steel. average red, green, and blue pixel values were extracted as features. A decision tree algorithm was trained on these features to identify materials. Based on the material, an algorithm calculates spindle speed using standard cutting speeds, converting it to frequency for a variable frequency drive. Experiments show that the retrofitted machine produces holes with lower roughness and vibrations. This cost-effective solution is suitable for small industries and meets industry 4.0 requirements.</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

Material detection and tuning of machining parameters using machine vision and machine learning in drilling operations

  • 期刊论文

  • 发表日期：

    2025年11月5日

查看全文
  • Durga Prasad Penumuru,
  • Sreekumar Muthuswamy,
  • Premkumar Karumbu

摘要

Cognitive machine tools are not new, but few are fully or even partially cognitive. Emerging technologies like machine learning and machine vision can transform a regular machine into a cognitive one. This work aims to retrofit an existing drilling machine into a cognitive tool by integrating a variable frequency drive, microcomputer, and camera. A dataset was created using images of four materials: Aluminium, copper, wood, and mild steel. average red, green, and blue pixel values were extracted as features. A decision tree algorithm was trained on these features to identify materials. Based on the material, an algorithm calculates spindle speed using standard cutting speeds, converting it to frequency for a variable frequency drive. Experiments show that the retrofitted machine produces holes with lower roughness and vibrations. This cost-effective solution is suitable for small industries and meets industry 4.0 requirements.