DigiTube - Digitized in-line measurement and analysis of surface defects on tubes.

Purpose and goal

The project´s objective is to identify surface defects in tube manufacturing with relevant data from surface measurements with machine vision and a developed AI-based method for data management. Methods for in-line quality control will be tested and evaluated on a pilot scale. A methodology for data management will be developed. The work also includes evaluation and adaption of methods and technologies for how data can and should be sorted, packaged, analyzed and implemented into a customer-specific user environment in the process industry, in addition with AI.

Expected results and effects

The results of the project will give Sandvik the opportunity to replace manual inspection of surface defects with an automated quality control with machine vision systems in combination with an AI-based method for data management. System suppliers participating in the project will be able to improve their products through increased knowledge of how data management for machine vision can provide increased customer value.

Planned approach and implementation

The project is divided into four work packages (WP) where the first includes evaluation of measurement methods for detection of surface defects on tubes. In WP2 a methodology for measurement data management will be developed. A third work package addresses activities in a company-specific case to develop a solution for automated quality control of tubes and will end with a pilot-scale trial to show how selected measurement methods and data management can identify surface defects on tubes. The fourth AP contains project management and dissemination of results.