Severstal completes key phase of digital quality management

2026: Key Phase of Digital Quality Management System Implementation

Severstal provides digital quality control for about 60% of Cherepovets Steel Mill's products. The advanced system of automatic certification of rolled metal products covers 35 key units. Severstal announced this on February 17, 2026.

Severstal was one of the first domestic metallurgical companies to develop a comprehensive quality control system. Technical solutions are created by our experts, including mastering the production of their own measuring systems - analogues of tools that were previously purchased abroad. Over the 10 years of the project, we have invested about two billion rubles in the development of such an end-to-end digital system. By the end of the year, we expect to complete the key stage of its implementation, increasing the volume of digital control of commodity production to 67%, and move on to local replication of solutions, "said Alexander Shevelev, CEO of Severstal.

The complex of digital tools works in order to help the employee decide on the suitability of rolled metal based on the previously inaccessible large amount of information received at all stages - the life path of its creation. Every four seconds, the company certifies a product, every day - about 20 thousand certifications.

The implementation of the project provides for equipping industrial units with meters using technologies computer vision and, artificial intelligence which are responsible for recording visible deviations. The developed predictive models perform calculations of the probability of occurrence of defects invisible to the human eye based on technological parameters. Metal tracking systems provide binding data to each meter of a specific product, and incident recording systems monitor critical areas that affect its quality. Using them helps the employee to cope with the task of evaluation, as well as ensure a timely response to deviations in technological processes. In total, the system uses more than 17.5 thousand parameters, of which about 500 are certification. Based on the data obtained, the Sherlock auto-certification system recommends a decision on the suitability of rolled metal.

The development covered a through chain for the production of polymer rolled products, galvanized rolled products, hot-rolled rolled products, etched products, and commercial slabs. In February 2026, the system is being scaled up to produce flat and large diameter pipes at Severstal's Kolpino industrial site, as well as retrofitting units in Cherepovets with measuring systems. These works are planned to be completed by the end of 2026.

Severstal's team of experts, who have the necessary competencies, from the Technical Development and Quality Directorate, the production divisions of Cherepovets Steel Mill, as well as specialized companies - Severstal-infokom"" and Laboratory of Measuring Systems"."

2025

Implementation of the discrete optimization model in the area of thermal furnaces of the metal finishing shop No. 1

Severstal has implemented a discrete optimization model in the thermal furnaces area of the Cherepovets Steel Mill's No. 1 metal finishing shop. She collects a schedule of roller furnaces, taking into account the switching of the unit between steel grades and the minimum pause between sheets. The solution was developed by the specialists of Severstal's Artificial Intelligence cluster together with the automation group of the Rolling Production Directorate. Severstal announced this on November 20, 2025.

In roller furnaces, sheets are heated for further normalization, hardening and tempering to the temperatures required for these types of heat treatment. Previously, the plotting of the posad was carried out manually, and switching between steel grades led to long pauses and a drop in performance due to the need to adjust the temperature regime.

The model determines the optimal order of posade in roller furnaces No. 1 and 2 available sheets, taking into account the heating parameters, steel grade, sheet geometry, technical capabilities of furnaces and the location of sheets in the warehouse. The result is a time-optimized schedule on the user interface with the ability to upload and work on it.

The solution is based on an optimization model based on constraint programming (programming in constraints), which plans the posad of sheets from the current availability in optimal order a certain number of times a day. Then the optimal schedule is displayed in the user interface, where the foreman or master can confirm it and accept it into work.

As a result, due to the optimization of pauses between the switching of steel grades, additional production amounted to 3.41 thousand tons, and the economic effect - 27.55 million rubles.

The intelligent furnace planning system automatically determines the optimal order of sheet loading, ensuring the absence of unproductive pauses of the unit. This not only unloaded operators and foremen from routine calculations, but also allowed them to devote more time to quality control and the process as a whole, "commented Svetlana Potapova, head of Severstal's Artificial Intelligence cluster.

Increasing the volume of production of etched rolled products using machine learning

Severstal"" introduced a set of models machine learning for controlling the speed of continuous etching unit No. 4 (NTA-4). Cherepovets Steel Mill The solution allowed to automate key processes and increase the performance of the unit. The project was developed by specialists of the cluster "" Artificial intelligence together with the Center for Technological Development of Rolling Production and the cluster "Industrial Processes." This was announced Severstal on September 29, 2025.

The main task of the solution was to control the speed of the technological part of the unit. Previously, this process was completely dependent on the actions of the operator, who manually set the line parameters based on his experience and generally accepted performance values ​ ​ for a particular metal range. This approach often led to suboptimal use of production facilities. In addition, the etching rate could vary depending on the operator, which did not allow the maximum possible production volume.

This system analyzes the key parameters of the product and the state of the unit in real time and automatically sets the optimal speed of the process part of the NTA-4. The model also predicts the duration of the pause in the head and tail parts of the unit, which allows you to minimize downtime and increase overall performance.

To work out the control effects of the model, a digital NTA-4 twin was developed. This is a virtual copy of the unit that allowed specialists to test algorithms in a safe environment before they were implemented in real production. This approach ensured high reliability of the solution and reduced the risks associated with its integration.

Thanks to the use of this solution, in three months it was possible to increase NTA-4 productivity by 4%, the economic effect amounted to 273.5 million rubles. A few years ago, we accelerated NTA-3 using AI, now it's the turn of a newer and more modern unit. In addition, the decision was one of the first major projects implemented in the closed circuit of the APCS, - commented Svetlana Potapova, head of the Artificial Intelligence cluster at Severstal.

Implementation of ML model to prevent emergency downtime due to motor failures

At Mill 5000 of the Kolpino production site of Cherepovets Steel Mill, a machine learning model has been introduced that helps to avoid emergency downtime of the unit due to breakage of electric motors. The solution was developed by the specialists of Severstal Digital and Severstal-Infokom together with the technologists of the sheet rolling shop and experts from the center for technological development of pipe rolling production. Severstal announced this on August 7, 2025.

𝓲

Фото: Severstal

The rolling process is carried out in the horizontal reversing stand of Quatro "5000." Its operation is provided by two electric motors for which the torque load must be calculated. The motor force moment, or torque, is a physical quantity that characterizes the rotational force generated by the motor. It determines its ability to overcome resistance and rotate a shaft or mechanism. The higher the moment of force, the greater the load that the engine can overcome at a given rotational speed. However, at critical values, the risk of breakage of the shaft lines of the main drive of the cage increases, which leads to its failure and downtime of the entire unit. Previously, the operator set the settings of the cage, relying on his own experience, which was not optimal. For August 2025, the moment of force indicator is calculated using a machine learning model.

Before starting rolling, the control station operator sets the deformation mode parameters, and then clicks the Calculate Mode button. Based on these data, the program calculates clearances and compression along the passes, after which they, together with the parameters of the deformation mode, are transferred to the model. The model predicts the average and maximum moments of power of the cage motors and displays the results in the user interface as a value in kilonewton meters (kNm) with color indication. If the calculated motor moment exceeds the specified limit, it is highlighted in yellow or red. In this case, there is a possibility of damage to the equipment. This means that the operator must change the parameters of the deformation mode so that the design moment of the cage motors does not exceed the permissible threshold, or take other compensating measures to reduce torque loads during actual rolling.

To predict the moments of force of the Stan 5000 cage motors, a gradient boosting model was used, as well as separate models for forecasting on final and rough passes. Models are trained on actual rental data.

Our solution provides accurate adaptation to changing loads, increasing energy efficiency and reducing equipment wear. Already in the first half of the year, this made it possible to reduce the emergency downtime of the 5000 camp by 3.9 hours with an economic effect of 4.53 million rubles. At the same time, the system has an intuitive interface familiar to the operator, - said Svetlana Potapova, director of Severstal Digital.

Implementation of metal surface inspection systems

Severstal continues to scale computer vision models that automate the quality control of rolled metal. As of March 2025, 12 systems were implemented at the Cherepovets Steel Mill site. The solutions were developed by the Severstal Digital team (Artificial Intelligence cluster), together with the Technical Development and Quality Directorate and the Severstal Repair Directorate. The company announced this on March 26, 2025.

Both neural network systems based on previously installed video surveillance cameras and new surface inspection systems (PIS) based on the company's own designs have been introduced at the Cherepovets Steel Mill site.

So, at the end of 2024, four CIPs were put into operation: they work on the units of polymer coatings of metal No. 1,2,3 and on the unit of longitudinal cutting No. 8. These solutions also work on continuous hot galvanizing units No. 1 and No. 4 and on longitudinal cutting unit No. 4. They are capable of recognizing 40 to 100 classes of defects in color images, making it easier to classify deviations. The systems use a set of computer vision models, each trained to detect defects critical to a particular type of metal. When changing the type of products, for example, from cold-rolled steel to dynamic steel, the algorithm automatically switches to the desired model, and additional rules for classifying defects are flexibly adapted to the type of rolled metal.

In addition, the developed software provides adaptive lighting adjustment depending on the time of day and color tone of the coating, which allows you to obtain a better image for further recognition of defects by the neural network model. This is especially important for systems on polymer coating units, where up to several dozen color versions of polymer rolled metal are produced.

Computer vision solutions are an important part of the digital product qualification system. Due to their accuracy and ability to work 24/7, Severstal customers receive better metal products, and unit operators can switch from routine tasks to those that require greater involvement. The combination of multimodel algorithms, adaptive technologies and import-independent solutions not only improves product quality, but also forms a benchmark for the metallurgical industry. Over the past two years, we have increased the accuracy of solutions by more than 30%. In the future, we plan to introduce inspection systems at other key units, transferring entire production lines under digital control, "commented Svetlana Potapova, Director of Severstal Digital.

2023: Increasing Mill 2000 Productivity with Machine Learning

On May 11, 2023, Severstal announced the introduction of a software complex for managing the rate of rolling and issuing slabs from furnaces based on machine learning models. The solution, called Autotemp 2.0, was implemented at Cherepovets Steel Mill Mill 2000 (a key asset of Severstal). The developers were specialists from Severstal Digital and Severstal-Infocom together with experts from the Center for Technological Development of Downstream Rolling Plants and technologists from the production of rolled steel at Cherepovets Steel Mill.

"Autotemp 2.0" allows you to calculate and adjust the optimal pause before delivering slabs from the heating furnace of the mill and thereby increase its productivity. Earlier, the operator calculated the necessary time for removing the slab on his own, which could cause unproductive pauses in rolling. In addition, the solution is integrated with the metal heating model, which improves the energy efficiency of the heating furnace area and the quality of slab heating.

Autotemp 2.0 is based on a model using a gradient boosting algorithm that allows you to analyze tabular heterogeneous data and calculate the rolling time of metal in the mill with high accuracy. For three months of the solution, the savings in rolling time due to the optimization of pauses amounted to 27 hours, which made it possible to additionally produce 24 thousand tons of rolled metal.

"Autotemp 2.0" is Severstal's own development, which used current technologies and tools for building digital solutions. They allow you to develop the product in the future and not depend on foreign suppliers of software or components. The solution completely controls the issuance of slab, due to which we eliminate the human factor and reduce the likelihood of downtime of the unit. In addition, we are introducing a digital twin at the heating furnaces site in order to determine, based on its forecast, which of the existing furnaces is best loaded at a certain moment for the best productivity of the 2000 mill, "commented Evgeny Vinogradov, CEO of Severstal Russian Steel and resource assets.

The level of digitalization of Severstal's production sites is steadily growing, and Autotemp 2.0 is another successful example of how a digital solution helps improve the productivity of industrial equipment. Our developments cover increasingly large and powerful units, including Camp 2000, one of the key units in the process chain of the plant, "commented Svetlana Potapova, Director of Severstal Digital LLC.