Key Takeaways & Executive Findings
- •• The FA–IPSO–SVM model achieves high prediction accuracy for converter endpoint carbon content, with hit rates up to 98.74% within ±0.02% error. • Factor analysis effectively reduces data dimensionality while preserving predictive performance, outperforming several existing methods. • Input parameters are systematically classified into high, medium, and low influence categories based on their impact on prediction accuracy, aiding feature selection. • The study addresses a gap by analyzing the influence of input parameters, not just improving model algorithms, providing practical guidance for industrial applications.
Abstract
The endpoint carbon content in the converter is critical for the quality of steel products, and accurately predicting this parameter is an effective way to reduce alloy consumption and improve smelting efficiency. However, most scholars currently focus on modifying methods to enhance model accuracy, while overlooking the extent to which input parameters influence accuracy. To address this issue, in this study, a prediction model for the endpoint carbon content in the converter was developed using factor analysis (FA) and support vector machine (SVM) optimized by improved particle swarm optimization (IPSO). Analysis of the factors influencing the endpoint carbon content during the converter smelting process led to the identification of 21 input parameters. Subsequently, FA was used to reduce the dimensionality of the data and applied to the prediction model. The results demonstrate that the performance of the FA–IPSO–SVM model surpasses several existing methods, such as twin support vector regression and support vector machine. The model achieves hit rates of 89.59%, 96.21%, and 98.74% within error ranges of ±0.01%, ±0.015%, and ±0.02%, respectively. Finally, based on the prediction results obtained by sequentially removing input parameters, the parameters were classified into high influence (5%–7%), medium influence (2%–5%), and low influence (0–2%) categories according to their varying degrees of impact on prediction accuracy. This classification provides a reference for selecting input parameters in future prediction models for endpoint carbon content.
1. Introduction
Precise control of carbon content is a critical aspect of the converter steelmaking process. Excessively high endpoint carbon content reduces the FeO content in the slag [1], whereas excessively low endpoint carbon content leads to over-oxidation of the molten steel and increases the deoxidation requirements in subsequent processes. In most Chinese enterprises, the management of this process typically employs a model of human−machine collaboration, but the proportion of human factors still remains relatively high. Techniques such as catch carbon practice, carbon pick-up practice, and high-carbon turndown practice are commonly employed to regulate the endpoint carbon content, which requires a high level of technical expertise from operators. However, manual judgment errors often lead to deviations in the endpoint carbon content, resulting in unnecessary resource and energy consumption. As a result, relying mainly on manual experience is insufficient to meet the demands of modern production [2–4].
With the continuous advancement of artificial intelligence technology, significant progress has been achieved in the intelligent transformation of the steel industry [5]. The development of converter endpoint prediction models has greatly enhanced the efficiency and quality of smelting processes. Currently, extensive research has been conducted on predicting endpoint carbon content in converters. For example, Zhang et al. [6] developed a converter carbon content prediction model by combining affinity propagation clustering with radial basis function networks to predict the endpoint carbon content of Q235B steel. This model offered a promising method for endpoint carbon content prediction. The model achieved a hit rate of 93.75% when the error range was within ±0.025%. Similarly, Liu et al. [7] established a prediction model for the endpoint carbon content of HRB4Nb-8 steel using the t-distributed stochastic neighbor embedding (t-SNE), particle swarm optimization (PSO), and back-propagation (BP) network. Their model achieved a hit rate of 98% when the error range was within ±0.02%. Compared with manual control, these models significantly improved prediction accuracy.
In practical production scheduling, steel grade transitions occur frequently, necessitating a broader application scope for endpoint prediction models. Li et al. [8] proposed a prediction model for endpoint carbon content in converters by integrating the BP network with a nonlinear least squares algorithm. While the model achieved a hit rate of 80% within an error range of ±0.025%, its performance was suboptimal when processing large-scale data, and its hit rate remained relatively low. To enhance hit efficiency and model applicability for large-scale data, further studies were conducted. Liu et al. [9] applied ...
Loading authentic research manuscript (Pages 1–5)...
Lihua Zhao, Shuai Yang, Yongzhao Xu, Zhongliang Wang, Xin Liu, Yanping Bao (2025). Factor analysis and machine learning for predicting endpoint carbon content in converter steelmaking. Int. Journal of Minerals, Metallurgy and Materials (矿物冶金与材料学报). https://doi.org/10.1007/s12613-025-3145-3
Research & Educational Purpose Only:The translations, structured abstracts, analytical annotations, and data reports provided by SinoTechIntel are intended exclusively for academic research, internal corporate R&D, and educational benchmarking. They do not constitute formal engineering, chemical safety, legal, or professional advice.
Copyright & Intellectual Property Notice: Original copyright of the underlying source articles and experimental data remains with the respective authors, institutions, and original publishing journals. SinoTechIntel claims intellectual property only over its proprietary translations, analytical syntheses, and AEO structured enhancements in accordance with international fair use and academic citation principles.
Frequently Asked Questions
What is the main objective of this study?
The main objective is to develop a prediction model for endpoint carbon content in converter steelmaking using factor analysis and an improved particle swarm optimization-support vector machine (IPSO-SVM), and to analyze the influence of input parameters on prediction accuracy.
How does the FA-IPSO-SVM model perform compared to other methods?
The FA-IPSO-SVM model outperforms existing methods such as twin support vector regression and standard support vector machine, achieving hit rates of 89.59%, 96.21%, and 98.74% within error ranges of ±0.01%, ±0.015%, and ±0.02%, respectively.
What is the significance of classifying input parameters?
Classifying input parameters into high, medium, and low influence categories helps in selecting the most relevant features for future prediction models, potentially reducing complexity and improving efficiency.
How many input parameters were identified and how were they processed?
A total of 21 input parameters were identified from the converter smelting process. Factor analysis was used to reduce the dimensionality of the data before feeding into the prediction model.
What are the practical implications of this research?
The research provides a more accurate and efficient method for predicting endpoint carbon content, which can help reduce alloy consumption, improve smelting efficiency, and support intelligent manufacturing in the steel industry.
Related Technical Papers & Translations
Direct Repair of the Crystal Structure and Coating Surface of Spent LiFePO4 Materials Enables Superfast Li-Ion Migration
The rapid accumulation of spent LiFePO4 (LFP) cathodes from retired lithium-ion batteries necessitates the development of effective and environmental-friendly recycling strategies. In this context, direct regeneration has emerged as a promising approach for reclaiming LFP cathode materials, offering a streamlined pathway to restore their electrochemical functionality. We report an integrated regeneration protocol that simultaneously repairs the degraded crystal structure and reconstructs the damaged carbon coating in spent LFP. The regenerated cathode material had superfast lithium-ion diffusion kinetics and a stable cathode–electrolyte interface, giving a remarkable rate capability with specific capacities of 122 mAh g−1 at 5C and 106 mAh g−1 at 10C (1C = 170 mA g−1). It also maintained capacities of 110.7 mAh g−1 (5C) and 84.1 mAh g−1 (10C) after 400 cycles. It could be used in harsh environments and could be stably cycled at subzero temperatures (−10 and −20 °C) and in solid-state electrolyte batteries. Life cycle assessment combined with economic evaluation using the EverBatt model reveals that this direct regeneration approach has high economic and environmental benefits.
Oxide Semiconductor for Advanced Memory Architectures: Atomic Layer Deposition, Key Requirement and Challenges
Oxide semiconductors (OSs), introduced by the Hosono group in the early 2000s, have evolved from display backplane materials to promising candidates for advanced memory and logic devices. The exceptionally low leakage current of OSs and compatibility with three-dimensional (3D) architectures have recently sparked renewed interest in their use in semiconductor applications. This review begins by exploring the unique material properties of OSs, which fundamentally originate from their distinct electronic band structure. Subsequently, we focus on atomic layer deposition (ALD), a core technique for growing excellent OS films, covering both basic and advanced processes compatible with 3D scaling. The basic surface reaction mechanisms—adsorption and reaction—and their roles in film growth are introduced. Furthermore, material design strategies, such as cation selection, crystallinity control, anion doping, and heterostructure engineering, are discussed. We also highlight challenges in memory applications, including contact resistance, hydrogen instability, and lack of p-type materials, and discuss the feasibility of ALD-grown OSs as potential solutions. Lastly, we provide an outlook on the role of ALD-grown OSs in memory technologies. This review bridges material fundamentals and device-level requirements, offering a comprehensive perspective on the potential of ALD-driven OSs for next-generation semiconductor memory devices.
Laser powder bed fusion of biodegradable Zn-4Cu alloy: Processing, microstructure and properties
Zn's natural degradability and biocompatibility make it a promising candidate for implants, however, its mechanical properties remain insufficient for bone applications. In this study, the performance of Zn was enhanced by developing Zn-Cu alloys via laser powder bed fusion (LPBF). Optimal LPBF parameters for forming stable tracks were achieved by adjusting laser power and scanning speed. Under optimized conditions of 100 W and 100 mm/s, high-density (99.58%) Zn-Cu alloys with improved hardness (68.2HV) and yield strength (160 MPa) were achieved. These improvements are attributed to solid solution strengthening, segregation strengthening, and grain refinement. The Zn-Cu alloys also demonstrated favorable degradation behavior, with a rate of 0.16 mm/year. This degradation is primarily driven by micro-galvanic corrosion between the CuZn5 phase and Zn matrix, along with refined grains and increased grain boundary density. This work demonstrates a viable strategy for fabricating Zn-based implants with enhanced structural integrity and mechanical performance via LPBF.