R&D PROJECTS

LAY2FORM

SHORT DESCRIPTION

  • ACRONYM: Lay2Form.
  • TITLE: Efficient Material Hybridization by Unconventional Layup and Forming of Metals and Composites for Fabrication of Multifunctional Structures.
  • SUMMARY: LAY2FORM creates a new cost-effective multistage manufacturing platform based on flexible machinery concepts, cognitive automation, inline monitoring and inspection, as well as simulation and modelling, in established composites-based processes, to enable the production of multifunctional 3D hybrid parts from thin layered metals and thermoplastic-matrix composites.

ABSTRACT

The main goal of LAY2FORM is to develop a new advanced and highly integrated manufacturing process for forming of layered metal/ thermoplastic-matrix composite hybrid materials, suitable to highly dynamic and competitive manufacturing environments, such as those of the automotive sector. Unconventional technologies (laser and Ultrasound-US) will be integrated into the manufacturing route, for material modification, adhesion, shaping, spot welding and consolidation, as well as for end-of-life material disassembly. The innovative integrated process will be assisted with simulation, cognitive automation, decision support, real-time control and advanced in-line NDT techniques, in a fully automated multi-stage manufacturing system. Efficient multi-material co-processing is the main priority, and the forming of metal foil / carbon fibre reinforced thermoplastic hybrids will be demonstrated in industrially relevant conditions, where dissimilar materials will be robotically laminated and press-formed.

Tree Technology is the partner in charge of the implementation of the Cognitive Self-Adaptive System, based on predictive modelling techniques. The goal is to enable a zero-defect manufacturing strategy by enabling self-adaption through the use of Machine Learning approaches capable to predict defects or deviations iteratively. This is enabled by pattern identification techniques applied on datasets where the target model, inputs parameters, sensors data and the final outcome (i.e. the final result inspected by NDT (Non-destructive testing) techniques identifying defects) are gathered in different iterations of the process. Machine Learning-based Self-Adaptive techniques enable to predict and anticipate these defects, so the process can be corrected and fine-tuned during the time, coming to the zero-defect strategy pursued.

PROJECT FICHE

  • BUDGET: €4,931,303.75
  • DURATION: 48 months (01/10/2017 – 30/09/2021)
  • PROGRAMME: H2020-FoF-2017 
  • PROJECT COORDINATOR: INEGI - INSTITUTO DE CIENCIA E INOVACAO EM ENGENHARIA MECANICA E ENGENHARIA INDUSTRIAL

MORE INFORMATION AT:

PARTNERS

This project has received funding from the European Union's Horizon 2020 research and innovation programme under grant agreement No 768710.

© Copyright 2022 Tree Technology, S.A. - All Rights Reserved

Created with Mobirise - More info