In steel enterprises, the design of energy systems mainly depends on experience and lacks systematic optimization methods. Therefore, it is of great significance to propose an overall optimization design method for the energy system of steel enterprises. In this paper, a linear model is proposed to select the energy conversion equipment types and distribute energy sources with the aim of maximizing the economic benefits of an energy system. In the model, the choice of energy conversion technology and the distribution of energy source are considered comprehensively. For the S steel plant, the case analysis results show that under the condition of keeping the original energy conversion equipment unchanged and optimizing the distribution of energy source, the economic benefits of the energy system can be increased by 15.77 CNY/t steel, and under the conditions of optimizing the distribution schemes of the energy conversion equipment types and energy sources, the economic benefits of the energy system can be increased by 180.26 CNY/t steel. In addition, the effects of different energy conversion equipment configurations, different energy sources prices and different pollution cost standards on the steel plant energy economic benefits were analyzed.

Crane scheduling tasks in steelworks are a matter of uncertainty scheduling with certain probability distribution pattern. To better schedule tasks with this feature, this paper proposes a Dynamic Area Allocation (DAA)-based crane scheduling model according to the following steps. First, Bayesian network, according to the time sequence of crane transportation tasks, is constructed. Then, conditional probability for each network node on the basis of actual crane operating data is calculated for getting the corresponding time–space probability distribution, and then obtaining the spatial distribution by superposing of all crane transportation tasks in the space domain at certain time. At last, tasks are assigned to cranes based on their spatial distribution and the equal probability partition. Simulation testing on the scheduling model is carried out using practical crane transportation tasks in steelworks. Results show that the model based on the dynamic area allocation, with its scheduling period of 15 min, can greatly shorten transportation time and reduce times of collision resulted from crane interference, after compared with the current widely used crane scheduling programme based on the fixed area allocation (FAA).

Top-bottom combined blowing converter steelmaking involves complex thermodynamic and kinetic processes, and predictive modeling has long been a key focus in steelmaking research. This paper proposes a kinetic process prediction model with on-site applicability. Based on actual production data, machine learning models (BP neural network, random forest, XGBoost) are employed to predict Tapping Steel Oxygen (TSO) content, which is then used as input for the kinetic model. An optimized theoretical decarburization kinetic model is selected and validated against measured Tapping Steel Carbon (TSC) data. The key innovation lies in the integration of converter control parameters into the kinetic model through a data-driven cyclic iteration algorithm. Comparison of prediction accuracy before and after integration shows that the model’s TSC prediction within the range [−0.2, +0.2] improves by 6.26%. This work presents a novel approach for enhancing kinetic models via control parameter integration, offering effective guidance for real-time monitoring and optimization in converter steelmaking.