Scholarlink

<p>Laser bending is a non-contact metal forming technique that utilizes thermal deformation induced by a laser beam, offering advantages in precision manufacturing for applications in aerospace, MEMS (micro-electro-mechanical-systems), and biomedical sectors. However, traditional laser bending processes lack real-time monitoring and adaptive control, leading to inefficiencies, inaccuracies, and increased energy consumption. This paper presents an integrated Internet of Things (IoT)-based system for real-time monitoring and control of laser bending operations using a 2 kW fiber laser. The system incorporates camera sensors for in-situ angle measurement via a mobile application, machine learning models for parameter optimization and error assessment against CAD (computer aided design) models. The proposed approach bridges mechanical manufacturing aspects with artificial intelligence/machine learning (AI/ML)-driven data science, enabling scalable, precise sheet metal forming. Key contributions include the development of the functional curve alignment loss (FCAL) metric for curve alignment and synthetic data generation for ML training.</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

Development of Laser Bending Strategy with IoT-Based Sensors and Control

  • 期刊论文

  • 发表日期：

    2026年8月4日

查看全文
  • Aditya Narayan Thakur,
  • Rohan Kumar Mishra,
  • Kushagra Katare,
  • Vedant Marodkar,
  • Ashwin Jaiswal,
  • Kaushik Bandyopadhyay,
  • Avishek Adhikary

摘要

Laser bending is a non-contact metal forming technique that utilizes thermal deformation induced by a laser beam, offering advantages in precision manufacturing for applications in aerospace, MEMS (micro-electro-mechanical-systems), and biomedical sectors. However, traditional laser bending processes lack real-time monitoring and adaptive control, leading to inefficiencies, inaccuracies, and increased energy consumption. This paper presents an integrated Internet of Things (IoT)-based system for real-time monitoring and control of laser bending operations using a 2 kW fiber laser. The system incorporates camera sensors for in-situ angle measurement via a mobile application, machine learning models for parameter optimization and error assessment against CAD (computer aided design) models. The proposed approach bridges mechanical manufacturing aspects with artificial intelligence/machine learning (AI/ML)-driven data science, enabling scalable, precise sheet metal forming. Key contributions include the development of the functional curve alignment loss (FCAL) metric for curve alignment and synthetic data generation for ML training.