Your browser doesn't support javascript. This means that the content or functionality of our website will be limited or unavailable. If you need more information about Vinnova, please contact us.

PICTORIAL - Predictive Intelligent Control for Resistance Welding

Reference number
Coordinator SWERIM AB
Funding from Vinnova SEK 3 678 601
Project duration August 2023 - March 2026
Status Completed
Venture Circularity - FFI
Call Circularity - FFI - spring 2023
End-of-project report 2023-00806 eng.pdf (pdf, 768 kB)

Important results from the project

PICTORIAL has investigated how machine learning can be used for predictive quality monitoring of resistance spot welding in industrial production. The project gave mainly the desired results, it has shown that it is possible to use existing production data from weld control systems to predict obtained weld quality, also identifying a quality drift over time. The developed models were integrated into a demonstrator system and tested in an environment similar to industrial production.

Expected long term effects

PICTORIAL contributes to strengthening the industry´s ability to introduce digital and data-driven quality methods. The results support increased process robustness and reduced scrap in welding production, improved working environment, better conditions for introduction of advanced and more sustainable materials, and strengthened competitiveness. The project shows that safe industrial application of AI requires risk management, updating of data & a close connection between model and production.

Approach and implementation

The project was run with 7 work packages from August 2023 to March 2026. The work packages were: AP1: Data collection & variation analysis AP2: Data curation & labelling AP3: Evaluation of ML algorithms AP4: Development of prediction tools AP5: Test and evaluation AP6: Display design AP7: Project management & dissemination The work was sequential. Production data was collected and structured, linked to quality measures and finally used in the model development and -evaluation.

The project description has been provided by the project members themselves and the text has not been looked at by our editors.

Last updated 1 July 2026

Reference number 2023-00806