After nearly one hundred years of research, metallurgy (metallurgical science and engineering) has gradually become a system with three levels of knowledge: (1) micro metallurgy at the atomic/molecular scale, (2) process metallurgy at the procedure/device, and (3) macro-dynamic metallurgy at the full process/process group. Macro-dynamic metallurgy development must eliminate the concept of an “isolated system” and establish concepts of “flow,” “process network,” and “operating program” to study the “structure–function–efficiency” in the macro-dynamic operation of metallurgical manufacturing processes. It means considering “flow” as the ontology and observing dynamic change by “flow” to solve the green and intelligent potential of metallurgical enterprises. Metallurgical process engineering is integrated metallurgy, top-level designed metallurgy, macro-dynamic operated metallurgy, and engineering science level metallurgy. Metallurgical process engineering is a cross-level, comprehensive, and integrated study of the macro-dynamic operation of manufacturing processes. Metallurgical process engineering studies the physical nature and constitutive characteristics of the dynamic operation of steel manufacturing process, as well as the analysis-optimization of the set of procedure functions, coordination-optimization of the set of procedures’ relations, and reconstruction-optimization of the set of procedures in the manufacturing process. The study establishes rules for the macro operation of the manufacturing process, as well as dynamic and precise objectives of engineering design and production operation.

In order to promote the intelligent transformation and upgrading of the steel industry, intelligent technology features based on the current situation and challenges of the steel industry are discussed in this paper. Based on both domestic and global research, functional analysis, reasonable positioning, and process optimization of each aspect of steel making are expounded. The current state of molten steel quality and implementation under narrow window control is analyzed. A method for maintaining stability in the narrow window control technology of steel quality is proposed, controlled by factors including composition, temperature, time, cleanliness, and consumption (raw material). Important guidance is provided for the future development of a green and intelligent steel manufacturing process.

Against the realistic background of excess production capacity, product structure imbalance, and high material and energy consumption in steel enterprises, the implementation of operation optimization for the steel manufacturing process is essential to reduce the production cost, increase the production or energy efficiency, and improve production management. In this study, the operation optimization problem of the steel manufacturing process, which needed to go through a complex production organization from customers’ orders to workshop production, was analyzed. The existing research on the operation optimization techniques, including process simulation, production planning, production scheduling, interface scheduling, and scheduling of auxiliary equipment, was reviewed. The literature review reveals that, although considerable research has been conducted to optimize the operation of steel production, these techniques are usually independent and unsystematic. Therefore, the future work related to operation optimization of the steel manufacturing process based on the integration of multi technologies and the intersection of multi disciplines were summarized.

Considering the precise composition control on the vacuum refining of high-Mn steel, the behaviors of both Mn evaporation and nitrogen removal from molten Mn steel were investigated via vacuum slag refining in a vacuum induction furnace. It was found that the reaction interfaces of denitrification and Mn evaporation tend to migrate from the surface of slag layer to the surface of molten steel with the gradual exposure of molten steel during the vacuum slag refining process. Significantly, compared with the experimental group without slag addition, the addition of slag into steel can result in a lower Mn evaporation rate constant of 0.0192 cm·min⁻¹ at 370 Pa, while the denitrification rate is almost not affected. Besides, the slag has a stronger inhibitory effect on Mn evaporation than the reduced vacuum pressure. Moreover, the inhibitory effect of the slag layer on Mn evaporation can be weakened with the increase of the initial Mn content in molten steel. The slag layer can work as an inhibitory layer to reduce the Mn evaporation from molten steel, the evaporation reaction of Mn mainly proceeds on the surface of the molten steel. This may be attributed to the Mn mass transfer coefficient for one of reaction at steel/slag interface, mass transfer in molten slag, and evaporation reaction at slag/gas interface is lower than that of evaporation reaction at steel/gas interface. The introduction of slag is proposed for both denitrification and manganese control during the vacuum refining process of Mn steels.

The mass transfer among the multiphase interactions among the steel, slag, lining refractory, and nonmetallic inclusions during the refining process of a bearing steel was studied using laboratory experiments and numerical kinetic prediction. Experiments on the system with and without the slag phase were carried out to evaluate the influence of the refractory and the slag on the mass transfer. A mathematical model coupled the ion and molecule coexistence theory, coupled-reaction model, and the surface renewal theory was established to predict the dynamic mass transfer and composition transformation of the steel, the slag, and nonmetallic inclusions in the steel. During the refining process, Al₂O₃ inclusions transformed into MgO inclusions owing to the mass transfer of [Mg] at the steel/refractory interface and (MgO) at the slag/refractory interface. Most of the aluminum involved in the transport entered the slag and a small part of the aluminum transferred to lining refractory, forming the Al₂O₃ or MgO·Al₂O₃. The slag had a significant acceleration effect on the mass transfer. The mass transfer rate (or the reaction rate) of the system with the slag was approximately 5 times larger than that of the system without the slag. In the first 20 min of the refining, rates of magnesium mass transfer at the steel/inclusion interface, steel/refractory interface, and steel/slag interface were x, 1.1x, and 2.2x, respectively. The composition transformation of inclusions and the mass transfer of magnesium and aluminum in the steel were predicted with an acceptable accuracy using the established kinetic model.

The impact energy prediction model of low carbon steel was investigated based on industrial data. A three-layer neural network, extreme learning machine, and deep neural network were compared with different activation functions, structure parameters, and training functions. Bayesian optimization was used to determine the optimal hyper-parameters of the deep neural network. The model with the best performance was applied to investigate the importance of process parameter variables on the impact energy of low carbon steel. The results show that the deep neural network obtains better prediction results than those of a shallow neural network because of the multiple hidden layers improving the learning ability of the model. Among the models, the Bayesian optimization deep neural network achieves the highest correlation coefficient of 0.9536, the lowest mean absolute relative error of 0.0843, and the lowest root mean square error of 17.34 J for predicting the impact energy of low carbon steel. Among the variables, the main factors affecting the impact energy of low carbon steel with a final thickness of 7.5 mm are the thickness of the original slab, the thickness of intermediate slab, and the rough rolling exit temperature from the specific hot rolling production line.

In the prediction of the end-point molten steel temperature of the ladle furnace, the influence of some factors is nonlinear. The prediction accuracy will be affected by directly inputting these nonlinear factors into the data-driven model. To solve this problem, an improved case-based reasoning model based on heat transfer calculation (CBR-HTC) was established through the nonlinear processing of these factors with software Ansys. The results showed that the CBR-HTC model improves the prediction accuracy of end-point molten steel temperature by 5.33% and 7.00% compared with the original CBR model and 6.66% and 5.33% compared with the back propagation neural network (BPNN) model in the ranges of [−3, 3] and [−7, 7], respectively. It was found that the mean absolute error (MAE) and root-mean-square error (RMSE) values of the CBR-HTC model are also lower. It was verified that the prediction accuracy of the data-driven model can be improved by combining the mechanism model with the data-driven model.

To deal with the increasing demand for low-volume customization of the mechanical properties of cold-rolled products, a two-way control method based on mechanical property prediction and process parameter optimization (PPO) has become an effective solution. Aiming at the multi-objective quality control problem of a company’s cold-rolled products, based on industrial production data, we proposed a process parameter design and optimization method that combined multi-objective quality prediction and PPO. This method used the multi-output support vector regression (MSVR) method to simultaneously predict multiple quality indices. The MSVR prediction model was used as the effect verification model of the PPO results. It performed multi-process parameter collaborative design and realized the optimization of production process parameters for customized multi-objective quality requirements. The experimental results showed that, compared with the traditional single-objective quality prediction model based on support vector regression (SVR), the multi-objective prediction model could better take into account the coupling effect between process parameters and quality index, the MSVR model prediction accuracy was higher than that of the SVR, and the optimized process parameters were more capable and reflected the influence of metallurgical mechanism on the quality index, which were more in line with actual production process requirements.

This research attempts to devise a multistage and multiproduct short-term integrative production plan that can dynamically change based on the order priority and virtual occupancy for application in steel plants. Considering factors such as the delivery time, varietal compatibility between different products, production capacity of variety per hour, minimum or maximum batch size, and transfer time, we propose an available production capacity network with varietal compatibility and virtual occupancy for enhancing production plan implementation and quick adjustment in the case of dynamic production changes. Here available means the remaining production capacity after virtual occupancy. To quickly build an available production capacity network and increase the speed of algorithm solving, constraint selection and cutting methods with order priority were used for model solving. Finally, the genetic algorithm improved with local search was used to optimize the proposed production plan and significantly reduce the order delay rate. The validity of the proposed model and algorithm was numerically verified by simulating actual production practices. The simulation results demonstrate that the model and improved algorithm result in an effective production plan.

The quantitative evaluation of multi-process collaborative operation is of great significance for the improvement of production planning and scheduling in steelmaking–continuous casting sections (SCCSs). However, this evaluation is difficult since it relies on an in-depth understanding of the operating mechanism of SCCSs, and few existing methods can be used to conduct the evaluation, due to the lack of full-scale consideration of the multiple factors related to the production operation. In this study, three quantitative models were developed, and the multi-process collaborative operation level was evaluated through the laminar-flow operation degree, the process matching degree, and the scheduling strategy availability degree. Based on the evaluation models for the laminar-flow operation and process matching levels, this study investigated the production status of two steelmaking plants, plants A and B, based on actual production data. The average laminar-flow operation (process matching) degrees of SCCSs were obtained as 0.638 (0.610) and 1.000 (0.759) for plants A and B, respectively, for the period of April to July 2019. Then, a scheduling strategy based on the optimization of the furnace-caster coordinating mode was suggested for plant A. Simulation experiments showed higher availability than the greedy-based and manual strategies. After the proposed scheduling strategy was applied, the average process matching degree of the SCCS of plant A increased by 4.6% for the period of September to November 2019. The multi-process collaborative operation level was improved with fewer adjustments and interruptions in casting.

Internet of Things and artificial intelligence technology are the key elements of the intelligent construction of iron and steel production warehouse. This paper puts forward a whole set of intelligent scheme for bar warehouse crane for the guidance of metallurgical process engineering, including cluster rapid self-awareness technology of the smart crane, precise self-executing technique of crane with rigid-flexible hybrid structure, multi-body system kinematics model of the smart crane sling and the swing characteristics model at different azimuth, anti-swing control technology based on the optimization objective function, the vehicle model recognition system based on lidar, and the clustering crane dynamic scheduling method based on multi-agent reinforcement learning. The complete intelligent logistics system of the bar warehouse has changed the original operation mode of the warehouse area and realized the unmanned operation and intelligent scheduling of the crane, which is of great significance for improving the production efficiency, reducing the production cost, and improving the product quality.

The production process of iron and steel is accompanied by a large amount of energy production and consumption. Optimal scheduling and utilization of these energies within energy systems are crucial to realize a reduction in the cost, energy use, and CO₂ emissions. However, it is difficult to model and schedule energy usage within steel works because different types of energy and devices are involved. The energy hub (EH), as a universal modeling frame, is widely used in multi-energy systems to improve its efficiency, flexibility, and reliability. This paper proposed an efficient multi-layer model based on the EH concept, which is designed to systematically model the energy system and schedule energy within steelworks to meet the energy demand. Besides, to simulate the actual working conditions of the energy devices, the method of fitting the curve is used to describe the efficiency of the energy devices. Moreover, to evaluate the applicability of the proposed model, a case study is conducted to minimize both the economic operation cost and CO₂ emissions. The optimal results demonstrated that the model is suitable for energy systems within steel works. Further, the economic operation cost decreased by 3.41%, and CO₂ emissions decreased by approximately 3.67%.

Steel production involves the transfer and transformation of material and energy at different levels, structures, and scales, and this process incurs substantial information in the material and energy dimensions. Given the black-box feature of iron and steel production processes, process visualization plays an important role and inevitably benefits parameter correction, technical support decision-making, personnel training, and other aspects of the steel metallurgy industry. The technological characteristics of the entire process in the steel industry were analyzed in this study, a visualization technology route based on virtual reality (VR) was built, and the important components of visual simulation system for steel industry and the important technical points needed to realize the system were proposed. On the foundation, a visual simulation model for the process scheduling of the iron and steel enterprise raw materials’ field, slab, and hot rolling processes was built, and a visualization simulation platform of the iron and steel metallurgy plant-wide process, including ironmaking, steelmaking, hot rolling, and cold rolling, was developed. Lastly, the effectiveness of platform was illustrated by practical application.