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.

Process optimization using Artificial Intelligence in glass industry

Reference number
Coordinator RISE Research Institutes of Sweden AB - RISE Glas
Funding from Vinnova SEK 2 874 000
Project duration March 2021 - September 2024
Status Ongoing
Venture Strategic innovation programme for process industrial IT and automation – PiiA

Purpose and goal

The project wants to improve the competitiveness of Swedish glassworks by improving quality and energy consumption. The goal is therefore to create a smart tool that analyzes input data from the production environment, then provide direct feedback on the quality of the glass mass before production and to adjust the influencing factors to achieve a perfect glass mass. A tool to evaluate the quality of glass samples will also be developed.

Expected results and effects

The purpose of this project is to be able to predict the quality of the glass mass before the work begins with the help of Artificiell Intelligens (AI). It also provides the opportunity to optimize the glass mass. The goal of the project is to develop a system for data collection, analysis and feedback to optimize the glass.

Planned approach and implementation

Identify the variables that affect the quality of the glass mass. To be able to influence or counteract the effects of the factors that degrade glass quality. The results will be analyzed using AI where deep learning is planned to be used to identify the quality of the glass via image recognition and machine learning is intended to be used to analyze data and correlate the effects with the results of the image recognition. To implement the method at the glassworks, a software must be developed that continuously performs the operations and provides feedback.

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

Last updated 14 December 2023

Reference number 2020-04618

Page statistics