Scholarlink

<p>Ultrasonic Additive Manufacturing (UAM) employs ultrasonic welding to bond similar or dissimilar metal foils to a substrate, resulting in solid, consolidated metal components. However, certain processing conditions can lead to inter-layer defects, affecting the final product’s quality. This study develops a method to monitor in-process quality using deep learning-based convolutional neural networks (CNNs). We evaluated the CNN on their ability to classify samples with and without embedded thermocouples across five power levels (300&#xa0;W, 600&#xa0;W, 900&#xa0;W, 1200&#xa0;W, 1500&#xa0;W) using thermal images with supervised labeling. Four distinct CNN classification models were created for different scenarios including without (baseline) and with thermocouples, only without thermocouples across power levels, only with thermocouples across power levels, and combined without and with thermocouples across power levels. The models achieved 99.14% accuracy on combined baseline and thermocouple images, 98.55% for baseline images across power levels, 96.70% for thermocouple images, and 98.36% for both types across power levels. The high accuracy, above 96.00%, demonstrates the system’s effectiveness in identifying and classifying conditions within the UAM process, providing a reliable machine learning tool for quality assurance and process control in manufacturing environments.</p> Graphical abstract <p></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

Advanced predictive quality assessment for ultrasonic additive manufacturing with deep learning model

  • 期刊论文

  • 发表日期：

    2025年2月17日

查看全文
  • Lokendra Poudel,
  • Sushant Jha,
  • Ryan Meeker,
  • Duy-Nhat Phan,
  • Rahul Bhowmik

摘要

Ultrasonic Additive Manufacturing (UAM) employs ultrasonic welding to bond similar or dissimilar metal foils to a substrate, resulting in solid, consolidated metal components. However, certain processing conditions can lead to inter-layer defects, affecting the final product’s quality. This study develops a method to monitor in-process quality using deep learning-based convolutional neural networks (CNNs). We evaluated the CNN on their ability to classify samples with and without embedded thermocouples across five power levels (300 W, 600 W, 900 W, 1200 W, 1500 W) using thermal images with supervised labeling. Four distinct CNN classification models were created for different scenarios including without (baseline) and with thermocouples, only without thermocouples across power levels, only with thermocouples across power levels, and combined without and with thermocouples across power levels. The models achieved 99.14% accuracy on combined baseline and thermocouple images, 98.55% for baseline images across power levels, 96.70% for thermocouple images, and 98.36% for both types across power levels. The high accuracy, above 96.00%, demonstrates the system’s effectiveness in identifying and classifying conditions within the UAM process, providing a reliable machine learning tool for quality assurance and process control in manufacturing environments.

Graphical abstract