VDEh-Betriebsforschungsinstitut

Cryogenic treatment can be employed as an additional heat treatment step for martensitic steels, particularly high-carbon and high-alloy tool steels, to improve their mechanical properties and wear resistance. This enhancement results from a transformation of retained austenite and precipitation of finely distributed secondary carbides. The present study examines the impact of a shallow cryogenic treatment, performed between the quenching and tempering processes, on the corrosion resistance and fracture toughness of cold work tool steel X153CrMoV12. The influence of the shallow cryogenic treatment was evaluated using potentiodynamic polarization test, salt spray tests and three-point bending tests in various hydrogen charging conditions. In addition, the microstructure and phase transformation of the tool steel were investigated using high-resolution scanning electron microscopy, X-ray diffraction and dilatometer tests. The results suggest that the shallow cryogenic treatment followed by a single tempering cycle can slightly enhance the corrosion resistance of the steel. More importantly, the shallow cryogenic treatment positively affects fracture toughness and reduces hydrogen susceptibility. It is discussed how these improvements in the properties of the X153CrMoV12 steel are linked to the microstructural changes induced by the shallow cryogenic treatment.

Sinter with high and consistent quality, produced with low costs and emissions is very important for iron production. Transport and storage degrade sinter quality, generating fines and segregation effects. Conventional sinter quality monitoring is insufficient as it is slow and expensive. Consequently, sinter quality and the impact of different sinter quality on daily BF operation is extremely non-transparent. In this work, a new approach will be implemented to strengthen the data base that describes the sinter quality at a sinter plant. New on-line measurements will be established, combined, and analyzed with Big Data technologies. This break-through in continuous quality monitoring should help to get continuous quality indices for sinter and will enable combined optimization of sinter plant and BF.

A data model for the steel production is presented, based loosely on ETSI’s SAREF4INMA standard. It models the production resources, such as steel billets, slabs or coils, production equipment, such as a continuous casting machine or a hot rolling mill, and is capable of representing the tracking uncertainty characteristic of the production of steel long products. A property graph representation of the involved entities is used, where not only each entity is typed, but also the links between entities. The model has been developed as part of a digital twin software platform in the CAPRI project and serves as documentation for the application programming interfaces. A decision support system for through-process quality control is being realised as the main application based on the platform.

This work explores different artificial intelligence based alternatives to create automatic classification system based on salience maps of coil surface when heavy unbalanced datasets are considered and where the labels have been assigned by human operators, considering different complex rules. After testing the possibilities of classifier setup process, additional effort was spend create synthetic features based on the characteristics of the salience maps and such features have been used to verify the need for additional check of scores coming from the human operators. Although it is a preliminary result, it provide evidences of the significant impact that confusing scores can have on the classifier final performance.

In Germany, the steel industry in particular is characterized by high carbon-rich waste gas flows, although the composition and quality of the gas mixtures resulting from various process steps can vary greatly. In addition to the use of resulting gases to generate heat and electricity, which in turn are required in steel processing operations, approaches are being pursued to specifically reduce CO2 emissions through Carbon Direct Avoidance (CDA), Process Integration (PI), Carbon Capture and Storage (CCS) or Carbon Capture and Utilization (CCU).

Optimizing the energy distribution in energy intensive industries is a difficult task. It requires a global vision for synchronizing the energy demands of all the involved processes. In this work, a decision support system is presented, which aims at supporting process operators and plant managers in monitoring and control of energy flows, e.g., process off-gases, steam and electricity in integrated steelworks. The software includes a digital twin of the integrated steelworks, for modelling or predicting internal energy production and consumption, exploited by a hierarchical control system that calculates in real-time the scheduling of the power plant, steam boilers and all the involved manipulable equipment. The digital twin implements a wide set of continuous learning models based on machine learning methodologies and standard system identification techniques. The control system integrates a high-level controller for calculating optimal references for a time horizon up to one day. These references are exploited by a set of distributed economic model predictive controllers that focus on optimizing the behavior of each specific energy network. This system allows minimizing the waste of energy, and minimizing the costs' management, by improving the synchronization of the main energy actors.

In this work, a practical approach for a decision support system for the electric arc furnace (EAF) is presented, with real-time heat state monitoring and control set-point optimization, which has been developed within the EU-funded project REVaMP and applied at the EAF of Sidenor in Basauri, Spain. The system consists of a dynamic process model based on energy and mass balances, including thermodynamic calculations for the most important metallurgical reactions, with particular focus on the modelling of the dephosphorisation reaction, as this is a critical parameter for production of high-quality steel grades along the EAF process route. A statistical scrap characterization tool is used to estimate the scrap properties, which are critical for reliable process performance and accurate online process control. The underlying process models and control functions were validated on the basis of historical production and measurement data of a large number of heats produced at the Sidenor plant. The online implementation of the model facilitates the accurate monitoring of the process behaviour and can be applied for exact process end-point control regarding melt temperature as well as oxygen, carbon and phosphorus content. Embedded within a model predictive control concept, the model can provide useful advice to the operator to adjust the relevant set-points for energy and resource-efficient process control.

Zusammenfassung In der modernen Stahlproduktion sind automatische Oberflächeninspektionssysteme (OIS) zur Detektion und Klassifikation von Oberflächenfehlern weit verbreitet und ihre Ergebnisse haben stark an Bedeutung gewonnen. Trotzdem fehlt es bis heute an anerkannten Methoden für eine objektive und umfassende Leistungsbewertung der Systeme, um mit vertretbarem Aufwand geeignete Kenngrößen für die OIS-Klassifikationsleistung im realen Produktionsbetrieb zu ermitteln. Dieser Beitrag widmet sich der Problematik der Abschätzung des Recalls bei unbekannter „Grundwahrheit“ (ground truth), als zentrales Maß für die Fähigkeitsbewertung klassifizierender Bildverarbeitungssysteme (BV-Systeme). Es werden eine Methodik für die Recall-Schätzung mittels Hilfsklassifikator vorgestellt und Forschungsbedarfe für deren praktische Umsetzung erörtert.

In the steel sector, sustainable management of by-products is a key challenge to preserve natural resources and achieve the zero waste goal. In this paper, the main trends of future research and development on reuse and recycling of by-products of the steel industry are presented in the form of a roadmap, which is the outcome of a dissemination project funded by the European Union based on the analysis of the most relevant and recent European projects concerning reuse and recycling of by-products from the steel production cycle. In particular, the developed roadmap highlights the most important topics of future research activities and challenges related to reuse and recycling of by-products from the existing or alternative steelmaking routes. A time horizon of 10 years has been considered, taking into account the European Commission targets to achieve carbon neutrality in a circular economy context. In addition, current technological trends derived from past and ongoing research projects are analysed. Research needs are based on the main categories of by-products and residual materials. Due to the different pathways to reduce CO 2 emissions, each category is divided into subcategories considering both current and novel process routes targeting decarbonization of steel production. This work identifies the most urgent and demanding research directions for the coming years based on a survey targeting the steel companies, services providers of the steel industry and research organizations active in the field.

A laser vibrometer system in combination with appropriate artificial intelligence methods for clustering of the measured vibration spectra was tested at a continuous steel casting machine to receive information on the solidification status of the strand. Measurements with the laser vibrometer at a fixed strand position of the billet caster of ESF under conditions of incrementally increasing casting speeds revealed a transition in the population of the identified vibration clusters as a footprint of the passed crater end position with a change from a fully solidified strand to a strand with some liquid core at the measurement position. This was in accordance with the results from a three-dimensional dynamic temperature and solidification model which was set up based on a state-of-the-art approach for solution of the heat flow equation with tailored submodels for the different boundary zones of the ESF billet caster (i.e., mould, secondary spray water zones and radiation zones) and installed at the steel plant for online monitoring and control of the casting process. The application of the newly installed measurement and model-based information systems at ESF revealed significant improvements in their billet casting process in terms of halved strand breakout rates and correspondingly increased productivity.

Nowadays the steel market is becoming ever more competitive for European steelworks, especially as far as flat steel products are concerned. As such competition determines the price products, profit can be increased only by lowering production and commercial costs. Production yield can be significantly increased through an appropriate scheduling of the semi-manufactured products among the available sub-processes, to ensure that customers’ orders are timely completed, resources are optimally exploited, and delays are minimized. Therefore, an ever-increasing attention is paid toward production optimization through efficient scheduling strategies in the scientific and industrial communities. This paper proposes a hybrid approach to improve the flexibility of production scheduling in steelworks producing flat steel products. Such approach combines three methods holding different scopes and modelling different aspects: an auction-based multi-agent system is applied to face production uncertainties, multi-objective mixed-integer linear programming is used for global optimal scheduling of resources under steady conditions, while a continuous flow model copes with long-term production scheduling. According to the obtained simulation results, the integration and combination of these three approaches allow scheduling production in a flexible way by providing the capability to adapt to different production conditions.

The operational conditions, including temperature and gas composition, vary along the radial position in a blast furnace. Nevertheless, very few studies can be found in the literature that discuss how the reduction behavior of the ferrous burden varies along the radial position. In this study, the effect of the radial charging position on the reducibility of acid iron ore pellets was investigated using a laboratory-scale, high-temperature furnace in CO-CO2-N2 and CO-CO2-H2-H2O-N2 atmospheres up to 1100 °C. The experimental conditions were accumulated based on earlier measurements from a multi-point vertical probing campaign that was performed for a center-working European blast furnace. The main finding of this study is that the pellet reduction proceeded faster under simulated blast furnace conditions resembling those in the center area, compared to the wall area, because of a higher share of CO and H2 in the gas. Therefore, the pellet charging position affects its reduction path in a blast furnace. Additionally, it was shown that the presence of H2 and H2O in the reducing gas enhanced the progress of reduction reactions significantly and enhanced the formation of cracks slightly, both of which are desirable in blast furnace operation. The reducibility data attained in this study are important in understanding how temperature and gas composition is connected to the reduction degree under realistic process conditions.

This paper presents an Artificial Intelligence based tool for real-time estimation of ageing status of all the ladles operating within an electric steelworks. The developed system exploits real data collected and operators’ experience for tuning its core models and formulates the problem as a multi-class classification problem on a highly imbalanced dataset. Two classifiers are applied, based on the Decision Tree and Random Forest approaches. Both approaches provide satisfactory results, especially in the identification of the most critical situations, namely when the ladle is close to its end of life or needs an immediate maintenance intervention, but the Decision Tree shows slightly better performance. The system, therefore, effectively supports predictive maintenance approaches.

The processes involved in the metallurgical industry consume significant amounts of energy and materials, so improving their control would result in considerable improvements in the efficient use of these resources. This study is part of the MORSE H2020 Project, and it aims to implement an operator support system that improves the efficiency of the oxygen blowing process of a real cast steel foundry. For this purpose, a machine learning agent is developed according to a reinforcement learning method suitable for the dynamics of the oxygen blowing process in the cast steel factory. This reinforcement learning agent is trained with both historical data provided by the company and data generated by an external model. The trained agent will be the basis of the operator support system that will be integrated into the factory, allowing the agent to continue improving with new and real experience. The results show that the suggestions of the agent improve as it gains experience, and consequently the efficiency of the process also improves. As a result, the success rate of the process increases by 12%.

The aim of this paper is to explore the potential capabilities of nonlinear projectors to represent the integrated behaviour of products when manufacturing involves several plants inside a typical facility of heavy industry. The interest is focused in the integrated supervision of production able to identify sudden failures or infrastructure attacks discovered from the process perspective. In this analysis, not only the feasibility but also computational capabilities are going to be explored. The selected methodology is the case analysis with action research, and the selected facility is a hot rolling mill for long steel products, which involves more than twenty plants or equipment units. The challenge is to define a monitoring procedure able to assess the product as well as the individual behaviour of each equipment. The results obtained allow to define an automatic procedure applicable in intraprocess time, which can have as an additional benefit its visual interpretation from the operator point of view.

Bearings are the most stressed component in the operation of drive trains. This could explain the fact that bearing failure is the most common occurrence in drive trains. For this reason, several methods have been used to monitor the condition of bearings to ensure their proper functioning. The main objective of all these methods is to increase the prediction time of possible anomalies or failures that may cause malfunctions or stoppage of the machines at considerable cost. The objective of this paper is to give an overview of the current methods used for monitoring of drive trains, show their advantages and disadvantages particularly with regard to the prediction time of possible anomalies. Then we will have a brief overview of the physical properties used by the innovative sensor. To validate the efficiency of the sensor a key of performance indicator will be defined for this case. Finally, some measurement results of the sensor will be presented as well as their use in the monitoring of bearings and machines.

At blast furnace B at Salzgitter Flachstahl a series of innovative measuring techniques are installed to monitor the processes at the blast furnace top, making this furnace one of the best equipped furnaces in Europe. These techniques comprise full 2D measurement of the temperature profile of the top gas shortly above the burden surface, 3D radar scan of the whole burden surface and online measurement of the dust concentration in the top gas. After more than 5 years’ experience with most of these techniques, they enable to better understand the complex chemical and physical interrelations occurring in the BF stack between the ascending process gas and the descending solid burden. A couple of examples of incidents that were monitored are presented in this article, including influences of charging programmes on top gas temperature profiles and influences of disturbed gas solids interaction on the BF working state. The new measuring techniques with tailor-made data processing enable the operators to gain a better picture of the processes currently occurring in the blast furnace, consequently supporting them in keeping the blast furnace operation as stable and efficient as possible.