Leveraging advanced algorithms, machine learning techniques, and camera acquisition, CSEM pioneers a proprietary and AI-based vision system for steel billet identification via serial numbers with an impressive accuracy rate of 99.8% even in harsh environments and after long periods of outdoor storage.
Identification number on a steel billet
Zurich-based SMS Concast specializes in manufacturing plants for the steel production process, specifically casting semi-finished long products out of steel, like billets, beam blanks, and blooms. Each billet receives a unique identification number, indicating production details and specific characteristics. In 2007, SMS Concast approached CSEM to co-develop a solution, supported by the Swiss Commission for Technology and Innovation (CTI). CSEM, with over 25 years of expertise in artificial intelligence (AI) enabled vision systems, designed a vision system incorporating a three-color illuminator and trained it using machine learning techniques. This system, known as “Steeltrack” has been successfully implemented by numerous steel plants around the world over the past decade.
Outdoor stocking of steel billets
Taking advantage of advancements in AI, CSEM was approached again by SMS Concast a decade later. Their goal was to develop a system with enhanced accuracy and cost-effectiveness for reading the billet serial numbers, particularly in harsh environments with challenging conditions with temperature changes and dust. Identifying billets and their materials becomes challenging after months or years of outdoor storage, as rust and pollution can alter the embossed unique identification number (or OCR for optical character recognition), resulting in incomplete and/or unreadable serial numbers.
Prototype of the vision system developed by CSEM.
This time, CSEM’s engineers created a proprietary vision system equipped with camera acquisition to read the elements of the serial numbers. Through customized algorithms and intelligent data processing, the system can identify all the necessary characteristics of a billet, even with incomplete serial numbers. The result is a highly robust and reliable billet “detector” prototype solution with an impressive accuracy rate of 99.8%, surpassing the performance of the initial solution.
“Our company is the leader when it comes to questions concerning the process and technology of steel production”, states Stephan Feldhaus, CEO of SMS Concast. “CSEM has helped us develop a highly accurate tracking system for our customers that ensures the highest possible quality to their long steel products.” This is why, in a second phase of this project, SMS Concast challenged the CSEM experts to take the system one step further and to implement quality control monitoring of the billets based only on physical characteristics like contour of the shape, rhomboidity, bulging. This new feature has the potential to provide SMS Concast with a completely new product, utilizing the same hardware as the initial OCR system. Furthermore, the new functionality could help plant operators to perform predictive maintenance by analyzing the drift of the billet shape over time and replacing the wearing parts of the casting machine in time. While this development is still under investigation, the results are again very encouraging, and first sales of the new system are expected in 2024.
Additional information
SMS group is a leading full-line technology partner in the world of metals. SMS Concast is SMS group’s specialist for casting semi-finished long products out of steel – billets, beam blanks and blooms.
Info-box : What is Continuous casting?
Continuous casting is a cost-effective manufacturing process to produce semi-finished steel products for subsequent rolling processes. The technology was first introduced in the 1950s, and nowadays it accounts for over 90% of global liquid steel production. To guarantee that the steel has a homogeneous grain structure, steel is poured into a water-cooled copper mold and quickly chilled. The mold has a specific shape and dimensions corresponding to the desired product (billets, blooms, or slabs). Large quantities of these semi-finished products are stored for several months or years outdoors before they are further processed in rolling mills to become finished products (bars, profiles, plates, strips, or tubes). For later identification, they receive a stamped identification number made up of numbers and letters. Afterwards, the finished products are sold to various sectors (i.e., construction, transportation, production industries), where the tracking of the production has high priority.
Interested in exploring smart, secure IoT solutions at CSEM? Read more on our expertise in IoT and vision.
6 September 2023
A system integrating artificial intelligence and multi-camera imagery can be used to accurately measure the flow of water in a mountain stream. Collected in 24/7 mode, the data can be used, for exampl...
6 June 2023
Elevate your business to the next level! Join our challenge until Monday, September 18, and stand a chance of winning up to CHF 100K worth of digital technology development and transfer time....
4 May 2023
Artificial Intelligence (AI) is now part of our daily lives, embedded in connected wristbands and even smartphones. How is it possible to integrate such powerful algorithms into environments where eve...