Data-driven approaches in incremental forming: Unravelling the path to enhanced manufacturing efficiency using data acquisition

Abstract

Incremental forming is a versatile and cost-effective sheet metal forming technique widely adopted in low-volume manufacturing and prototyping across various industries. Recent advancements in data-driven approaches, including machine vision, neural networks, and 3D reconstruction methods, have significantly enhanced the precision and efficiency of incremental forming processes. This study explores the integration of advanced data acquisition and processing techniques to improve the accuracy, automation, and defect detection capabilities in incremental forming. Key advancements such as robot-assisted forming, computer-controlled toolpath generation from CAD models, and real-time quality monitoring using machine vision are discussed. The potential of single- and multi-view 3D reconstruction methods for optimizing toolpath strategies and enhancing formability is also examined. The findings highlight opportunities for full automation in incremental forming, demonstrating its potential to revolutionize modern manufacturing by reducing costs, increasing customization, and improving product quality. These advancements could benefit industries such as aerospace, automotive, and medical device manufacturing, where precision and flexibility are critical.