23 December 2024 in IEEE Transactions on Industrial Informatics
The prediction of sintering quality indicators is essential for the automation of the ironmaking process. However, various challenges, including variable time delays and relatively weak correlations, present difficulties in achieving precise modeling of the sintering process. To address these challenges, we introduce a novel method based on the nonuniform time delay embedding technique for predicting sintering quality indicators. First, we construct input variables with different compensated time delays. Second, we develop a low-dimensional approximation of the joint mutual information criterion to search the optimal variables and time delays. This approach effectively leverages valuable information from process variables while minimizing irrelevant information. Next, we implement a hybrid modeling technique that combines extreme gradient boosting and support vector regression to predict sintering quality indicators, allowing for adaptation to various operating conditions. Finally, we validate the effectiveness of our proposed method using real production data, specifically focusing on FeO content.
25 June 2025 in IEEE Transactions on Instrumentation and Measurement
Lack of crucial state data is a common problem in processing industries, particularly in iron-making. Real-time measurements are often infeasible in harsh conditions such as high temperatures and heavy dust. In practice, technical experts rely on manual observations to make estimates; however, this knowledge is difficult to formalize and quantify. To date, few studies have effectively addressed these two challenges in a unified manner, hindering progress in data acquisition and process optimization. In this paper, a novel Knowledge-Informed method that integrates a Multi-source fusion model with an Ensemble Network (KIMEN) is proposed to predict a key chemical indicator in the industry, the FeO content. Firstly, an sParts-Pair Comparing Sorting (s-PCS) strategy was introduced for knowledge solidification. Furthermore, a knowledge-informed image processing scheme was proposed. In cases of data scarcity, we proposed a two-layer cascaded structure combining Gradient Boosting Decision Tree (GBDT) and Gated Recurrent Unit (GRU), which functions as an ensemble recurrent network. When applied to the Guangxi Liuzhou Iron & Steel (Group) Company, the method demonstrates improved prediction performance and practical effectiveness. Experimental results show that the proposed KIMEN outperforms some conventional methods and state-of-the-art approaches. Ablation studies, small-scale experiments, and transfer learning experiments further validate the advantages of our method.
4 August 2025 in IEEE Transactions on Instrumentation and Measurement
The prediction of molten iron silicon content ([Si]) is crucial for blast furnace operation. Nowadays, neural networks are emerging as the most advanced model for [Si] prediction tasks. However, the time-varying nature of the blast furnace system makes it difficult for neural networks to maintain long-term prediction accuracy. Besides, the practical implementation of the neural network model counters the problem of irregularly sampled data due to manual intervention. To solve the above issue, we proposed a novel continual learning-based hybrid update scheme for our specially designed neural network model to perform long-term prediction tasks, together with a residual time-embedding layer to model the irregularly sampled time series. The hybrid update mechanism improves the plasticity of individual model components, thereby enhancing the model’s capability to track changes in system dynamics over time. Among these components, the time embedding layer transforms irregular timestamp information into a frequency-domain representation, enabling effective alignment and similarity computation. This design improves the model’s ability to process irregularly sampled time-series data. Finally, we validate our proposed method with 4-year operation data from #2 blast furnace of Liuzhou Steel in China. Experiments show that only our method can maintain high prediction accuracy for the 4-year range while facing regularly sampled raw industrial.
24 December 2025 in IEEE Transactions on Automation Science and Engineering
Designing safety-critical controllers for the blast furnace is crucial yet challenging due to its complex inherent dynamics. Recent advances in reinforcement learning (RL) have shown promise in designing effective controllers for complex industrial systems. However, direct application of RL control to an on-site blast furnace is hindered by stringent safety requirements and model discrepancies. To address these challenges, this paper presents a duo-stage RL-based safety-critical control framework (DRLSC Framework) that integrates safety-critical offline pretraining and an online agent transfer mechanism for long-term safe control of the blast furnace. An offline pretraining algorithm is designed to provide an adequate initial policy for online control, which consists of a data-driven blast furnace environment and a Soft Actor-Critic (SAC) agent. The offline stage incorporates a neural control barrier function (NCBF) to guarantee system state safety, which is trained jointly with the RL agent. During the online stage, a transfer mechanism facilitates rapid agent adaptation to the actual system dynamics, mitigating performance degradation arising from model discrepancies. Finally, silicon content ([Si]) tracking control experiments are carried out using a real dataset obtained from the #2 blast furnace of Liuzhou Steel in China. Compared with model-predictive-control-based methods, our DRLSC Framework can decrease the long-term tracking error by 50.21% when facing simulation discrepancy and maintain state safety continuously.
1 January 2026 in IET Signal Processing
On‐site monitoring of iron oxide (FeO) content is crucial for ensuring product quality in the steel sintering process. However, the harsh sintering environment, characterized by nonperiodicity, high dust levels, heavy smoke, and high‐temperature steam, severely degrades the quality of images captured at the sintering machine tail, thereby impacting the accuracy of FeO content prediction. Existing methods for keyframe extraction and image enhancement often rely on benchmark clear images or fail to address the unique challenges of the sintering environment, such as nonperiodic operational uncertainties and low‐light conditions. To overcome these limitations, this paper proposes a novel temporal statistics and heuristic priors‐based perceptual enhancement (THPE) framework. The proposed framework integrates an innovative dual‐analysis strategy for keyframe extraction and perceptual enhancement. Gaussian statistical modeling and time‐series analysis are employed to accurately extract key information from videos, enabling robust handling of the nonperiodic and uncertain nature of the sintering process and ensuring reliable information capture. Furthermore, for some harsh sintering environments, the heuristic priors based perceptual enhancement approach is introduced, which incorporates the frequency‐domain adjustment model (FDAM), atmospheric scattering model (ASM), and contrast‐based model (CBM). This design enables effective low‐light noise modeling and image enhancement without reliance on benchmark images. Experimental results demonstrate that the proposed framework can effectively improve the accuracy of keyframe extraction, enhance perceptual quality, and improve the prediction accuracy of FeO in sintering.