Key Takeaways & Executive Findings
- •• A dual cascade evaluation system integrating subjective and objective weighting methods enables accurate quantitative scoring of blast furnace comprehensive status. • The combined BiLSTM and CatBoost model significantly improves prediction accuracy, reducing mean absolute error by 0.275 and increasing hit rate by 5.65 percentage points on average. • With an error range of ±2.5, the combined model achieves a 91.66% hit rate for next-hour comprehensive status prediction, demonstrating field-ready reliability. • SHAP analysis reveals a linear relationship: a 10°C increase in furnace bottom center temperature raises the comprehensive status score by 0.44, offering actionable operational insights.
Abstract
The comprehensive status of blast furnaces was one of the most important factors affecting their economy, quality, and longevity. The blast furnace comprehensive status had the nature of “black box,” and it was “unpredictable.” In this study, a blast furnace comprehensive status score and prediction method based on a cascade system and a combined model were proposed to address this issue. A dual cascade evaluation system was developed by integrating subjective and objective weighting methods. The analytic hierarchy process, coefficient of variation, entropy weight method, and impart combinatorial games were jointly employed to determine the optimal weight distribution across indicators. Categorized statuses (raw material, gas flow, furnace body, furnace cylinder, and iron–slag) were evaluated. Based on the five categories of the status data, the second cascade was applied to upgrade the quantitative evaluation of the comprehensive status. The weights of the different categories were 0.22, 0.15, 0.22, 0.21, and 0.20, respectively. According to the data analysis, the results of the comprehensive status score closely matched the on-site production logs. Based on the blast furnace smelting period, the maximal information coefficient method was applied to the 100 parameters that were most relevant to the comprehensive status. A combined prediction model for a comprehensive status score was designed using bidirectional long short-term memory (BiLSTM) and categorical boosting (CatBoost). The test results indicated that the combined model reduced the mean absolute error by an average of 0.275 and increased the hit rate by an average of 5.65 percentage points compared to BiLSTM or CatBoost alone. When the error range was ±2.5, the combined model predicted a hit rate of 91.66% for the next hour’s comprehensive status score, and its high accuracy was deemed satisfactory for the field. SHapley Additive exPlanations (SHAP) and regression fitting were applied to analyze the linear quantitative relationship between the key variables and the comprehensive status score. When the furnace bottom center temperature was increased by 10°C, the comprehensive status score increased by 0.44. This method contributes to a more precise management and control of the comprehensive status of the blast furnace on-site.
1. Introduction
The blast furnace status, as a comprehensive indicator, its long-term stability and smooth operation can ensure high efficiency, excellent quality, low consumption, long life, and low carbon emissions during blast furnace smelting [1–3]. The comprehensive status of the blast furnace, as a “concept,” it could not be directly monitored on-site, and no clear definition exists on its assessment [4–6]. Therefore, based on the monitoring data from a blast furnace, a quantitative evaluation of the comprehensive status was completed, and leading-edge artificial intelligence (AI) technology was used to predict the comprehensive status [7–9]. The blast furnace operator could set an operation plan to achieve the goal of stabilizing the furnace conditions according to the comprehensive status at one moment [10–12].
JFE (JFE Steel Corporation), POSCO (Pohang Iron and Steel Co., Ltd.), TKSE (Thyssenkrupp), and Rautaruuki [13–17] were the pioneers in comprehensive status diagnostics for blast furnaces. They developed a theoretical model of an integrated condition based on the material balance, heat balance, and expert knowledge. This model could determine the position of the soft melt zone, material placement index, and direct reduction index. However, the model made several assumptions and the influence of subjective experience was significant. The ability of the model to be promoted and updated requires further improvement. Jiang et al. [18], Li et al. [19], and Shi et al. [20] constructed a thermal status evaluation model based on blast furnace data, as well as a material status identification model. However, they only evaluated the status of specific locations in the blast furnace, and the comprehensive status was not fully considered. Li et al. [21] applied a big data mining method to construct a comprehensive status evaluation model; however, room for improvement in the evaluation system still exists.
In the era of big data, the integration of blast furnace technology and AI has become more closely related, and status prediction models based on machine learning (ML) have become mainstream. Li et al. [22], Liu et al. [23], Li et al. [24], and Shi et al. [25] used the selected blast furnace parameters as input conditions and predicted the hot metal status for the next hour. Zhang et al. [26] and Liu et al. [27] analyzed the time-series changes in blast furnace gas status and constructed a prediction model for the blast furnace.
Loading authentic research manuscript (Pages 1–5)...
Zhen Zhang, Jue Tang, Quan Shi, Mansheng Chu, Mingyu Wang, Zhifeng Zhang (2025). Comprehensive status evaluation and prediction of blast furnace based on cascade system and combined model. Int. Journal of Minerals, Metallurgy and Materials (矿物冶金与材料学报). https://doi.org/10.1007/s12613-025-3179-6
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 contribution of this paper?
The paper proposes a novel dual cascade evaluation system and a combined prediction model (BiLSTM and CatBoost) for accurately assessing and predicting the comprehensive status of blast furnaces, achieving high accuracy and practical applicability.
How is the comprehensive status of a blast furnace evaluated?
The evaluation uses a dual cascade system that integrates subjective and objective weighting methods (AHP, coefficient of variation, entropy weight, and combinatorial games) to determine optimal weights for five categories: raw material, gas flow, furnace body, furnace cylinder, and iron–slag.
What prediction model is used and how accurate is it?
A combined model using BiLSTM and CatBoost is employed. It reduces mean absolute error by 0.275 and increases hit rate by 5.65 percentage points on average compared to individual models. With an error range of ±2.5, it achieves a 91.66% hit rate for next-hour predictions.
What is the significance of the SHAP analysis?
SHAP analysis identifies key variables affecting the comprehensive status score and reveals a linear relationship, such as a 10°C increase in furnace bottom center temperature raising the score by 0.44, providing actionable insights for operators.
How does this method benefit blast furnace operations?
The method enables precise management and control of the comprehensive status, helping operators stabilize furnace conditions, improve efficiency, and reduce emissions.
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.