Blast Furnace Ironmaking Process Research Articles

Woody biomass waste derivatives in decarbonised blast furnace ironmaking process

Modern ironmaking process relies significantly on fossil-related fuels, which ultimately results in the enormous CO2 emitted into the atmosphere. Biomass of plant origin, as a carbon-neutral energy source, has been considered as an alternative to fossil-based reducing agents such as coke. This study aims to investigate the potential of three woody biomass waste derivatives produced from biomass waste pyrolysis and gasification, namely charcoal, bio-oil, and bio-syngas, as the reducing agents in blast furnace. A model based on heat and mass balance and Gibbs free energy minimisation is proposed to simulate an ironmaking process with assistance of these derivatives. The effects of specific composition of biomass waste derivatives on process operation, CO2 emissions, and coke replacement are explored. Also the effects of H2-rich gas produced from biomass waste gasification on the blast furnace operation are estimated. Results indicate that reactions of woody biomass waste derivatives in blast furnace are complex and greatly dependent on composition. When charcoal has a higher carbon content, lower CO2 concentration is found from the top gas. The higher content of hydrogen in bio-oil will inhibit further reduction in CO2 emissions. Bio-syngas with H2/CO ratio of 1.3 proves to have a remarkable potential to reduce CO2 emissions. From the aspects of available biomass waste resources across the world, woody biomass waste derivatives as reducing agents are more suitable for countries with the limited pig iron production. This study provides a reference on the future of moving forward the decarbonised ironmaking by using woody biomass waste derivatives.

Deep Learning of Partially Labeled Data for Quality Prediction Based on Stacked Target-Related Laplacian Autoencoder.

Partially labeled data, which is common in industrial processes due to the low sampling rate of quality variables, remains an important challenge in soft sensor applications. In order to exploit the information from partially labeled data, a target-related Laplacian autoencoder (TLapAE) is proposed in this work. In TLapAE, a novel target-related Laplacian regularizer is developed, which aims to extract structure-preserving and quality-related features by preserving the feature-target mapping according to the local geometrical structure of the data. In addition, stacked TLapAE (STLapAE) is further constructed to extract deep feature representations of the data by hierarchically stacking TLapAE blocks. For model training, backward propagation equations are derived based on matrix calculus techniques to update the model parameters of the proposed TLapAE. The effectiveness of the proposed STLapAE is evaluated using the butane content prediction case in a debutanizer column, the silicon content prediction case in a blast furnace (BF) ironmaking process, and the ethane concentration prediction case in an ethylene fractionator. The results show that the proposed TLapAE model has significantly improved prediction accuracy compared to soft sensors using only labeled data and other partially labeled data modeling methods.

Blast Furnace Ironmaking Process Monitoring With Time-Constrained Global and Local Nonlinear Analytic Stationary Subspace Analysis

Blast Furnace Ironmaking Process Monitoring With Time-Constrained Global and Local Nonlinear Analytic Stationary Subspace Analysis

Pretrained Language–Knowledge Graph Model Benefits Both Knowledge Graph Completion and Industrial Tasks: Taking the Blast Furnace Ironmaking Process as an Example

Industrial knowledge graphs (IKGs) have received widespread attention from researchers in recent years; they are intuitive to humans and can be understood and processed by machines. However, how to update the entity triples in the graph based on the continuous production data to cover as much knowledge as possible, while applying a KG to meet the needs of different industrial tasks, are two difficulties. This paper proposes a two-stage model construction strategy to benefit both knowledge graph completion and industrial tasks. Firstly, this paper summarizes the specific forms of multi-source data in industry and provides processing methods for each type of data. The core is to vectorize the data and align it conceptually, thereby achieving the fusion modeling of multi-source data. Secondly, this paper defines two interrelated subtasks to construct a pretrained language–knowledge graph model based on multi-task learning. At the same time, considering the dynamic characteristics of the production process, a dynamic expert network structure is adopted for different tasks combined with the pretrained model. In the knowledge completion task, the proposed model achieved an accuracy of 91.25%, while in the self-healing control task of a blast furnace, the proposed model reduced the incorrect actions rate to 0 and completed self-healing control for low stockline fault in 278 min. The proposed framework has achieved satisfactory results in experiments, which verifies the effectiveness of introducing knowledge into industry.

Recycling Blast Furnace Dust as Raw Material in Iron-Making

A large amount of dust is formed as one of the primary by-products during the blast furnace ironmaking process. Iron and carbon are mainly compositions in the dust. Blast furnace dust (BFD) is cycled to protect the environment and recover valuable components. In this study, BFD is used pelletization process with iron ore concentration for raw materials charging to the iron-making furnace. The mixture of BFD and iron ore (30; 40; 50 by mass %) with 2 % bentonite as a binder was used for making pellets. The produced pellets were tested drop strength and fired at 1200 °C for 30 minutes in the atmosphere environment. Fired pellets were examined compressive strength and reduced at 900; 1000; 1100 °C in 30 minutes. Mechanical, porosity and reduction degree properties of reduced pellets were analysed. The results show that green strength and compressive strength are acceptable values. Good porosity is observed when using a high amount of BFD so that it gives a high degree of reduction. XRD, SEM were used for characterization. Iron whiskers were observed in the sample, which was reduced at 1000 °C. It is clearly shown that the pellets using BFD are appropriated for charging to blast furnace as raw materials.

Development of Mass–Energy Balance Model Based on a New Process of RSF with Hy-O-CR

At present, blast furnace (BF) ironmaking is still the main process for producing hot metal in China and around the world. Under the constraint of the global goal of “double carbon”, it is urgent to carry out hydrogen metallurgical innovation for the existing BF ironmaking process with higher carbon emissions. In recent years, BF technology with hydrogen enrichment and pure oxygen has made some progress, effectively reducing carbon emissions of hot metal per tons, but it is still unable to break through the technical bottleneck of emission reduction of more than 30%. In view of this, the authors put forward an ironmaking technology of a reduction smelting furnace (RSF) that is hydrogen-rich and utilizes pure oxygen and carbon recycle (Hy-O-CR), which breaks through the technical defect of traditional BF emission reduction of less than 30% by reshaping the furnace. Firstly, the construction process of the mass and energy balance model for two main unit modules in the new process (RSF with Hy-O-CR and top gas cycle) is introduced, and then the parameter optimization under specific scenario conditions is analyzed, and the influence mechanism of several key variables on the parameters in the furnace is obtained. Finally, the emission of CO2 in the whole process is explored in the case of two typical operating parameters. The results show that after using CCUS technology, the minimum value of direct CO2 emission is 215.93 kg/tHM, which is as high as 84.58% compared with the traditional BF process. Even if the removed CO2 is counted in carbon emissions, the minimum value of direct or indirect carbon emissions is 729.85 kg/tHM, and the proportion of emission reduction can reach 47.87%. The research results show that the reconstruction of Hy-O-CR technology can change the ratio of direct reduction and indirect reduction, which greatly breaks through the emission limit of the traditional BF and provides a new reference for hydrogen metallurgy technology and a basis for further study of the optimization of RSF size.

Evidence reasoning-based alarm method for silicon content in blast furnace hot metal using unbalanced monitoring samples

Silicon content monitoring and alarm based on data-driven methods is an essential approach to ensure product quality and smelting status in the blast furnace ironmaking process. However, due to the frequent fluctuation of production process, the sample data of silicon content usually shows obvious imbalance characteristics, i.e., less abnormal samples and more normal samples, posing great challenge to alarm task. In this case, this paper develops a novel data-driven alarm method based on the evidence reasoning (ER) rule. First, a normalization method of likelihood probability is given to construct the offline referential evidence matrix (REM) for characterizing the imbalanced sample distributions. Second, the online sample matches with the REM to generate the corresponding alarm evidence, and then the iterative ER fusion strategy is proposed to combine the historical and current evidence. Finally, the alarm decision can be made according to the fusion results. The integration of current and historical information helps to reduce the false alarms/missed alarms caused by the imbalanced samples and frequent state switches. The proposed ER rule-based monitoring approach is tested on real industrial data and comparison results with conventional methods like filtering and delay timer show that it has better comprehensive performance.

Data-Driven Joint Fault Diagnosis Based on RMK-ASSA and DBSKNet for Blast Furnace Iron-Making Process

Blast furnace iron-making process (BFIP) is one of the most critical procedures in the iron and steel industry where timely detection and accurate classification of faults have always been of core focus. However, the coupling effects of system’s nonlinear and nonstationary characteristics often cause process consistent underlying information to be buried, allowing accurate extraction to be a significant challenge. This also complicates the development of BFIP fault diagnosis model. Therefore, we propose a novel data-driven joint fault diagnosis strategy that employs regularized mutual kernel analytic stationary subspace analysis (RMK-ASSA) and deep broad stationary kernel network (DBSKNet) to eliminate this interference. To develop this method, we first construct an RMK-ASSA approach to address the poor modeling accuracy caused by standard analytic stationary subspace analysis (ASSA)’s inability to handle complex process nonlinearity. Global and local kernels are utilized to account for multiple nonlinearities in BFIP data. The weight of different nonlinear data is calculated by regularized principal component analysis, and the main information is imported into ASSA to obtain more robust and accurate modeling results by eliminating the interference of redundant noise. Subsequently, we design a DBSKNet-based classifier to implement the fault diagnosis task. This network further considers the nonlinearity by boosting kernel structure in depth and width while distinguishing the respective contributions of different kernels to fault diagnosis results. Finally, a double-layer loop parameter optimization algorithm is used for optimizing. Simulated cases and practical BFIP tests validate that RMK-ASSA eliminates the negative impact caused by nonstationary data and that the proposed joint fault diagnosis strategy outperforms other methods. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —BFIP’s nonlinear and nonstationary coupling properties pose unique challenges in eliminating distractions, constructing fault classifiers and accurately detecting process anomalies. To tackle these challenges, this paper proposes a joint fault diagnosis strategy based on RMK-ASSA and DBSKNet. RMK-ASSA effectively estimates nonlinear consistent features, while DBSKNet mines rich deep nonlinear information, accurately distinguishing variations in BFIP data under different working conditions. Experimental results demonstrate that this data-driven strategy can perform high-quality fault diagnosis, enabling field engineers to execute operations efficiently.

A Cooperative Silicon Content Dynamic Prediction Method With Variable Time Delay Estimation in the Blast Furnace Ironmaking Process

Online assessment of the molten iron quality of a blast furnace ironmaking process strongly depends on reliable measurement of silicon content (Si). This article proposes a novel cooperative strategy to train the data-driven prediction model and estimate variable time delay (VTD) values. First, a dynamic deep network that stacks denoising autoencoders (D-SDAE) with the ability to describe process nonlinearity and time-varying is designed for Si estimation. Then, time delay between the process variables and Si, which may disrupt the data distribution pattern (i.e., the real input-output relationship), is recovered in the modeling process. It is an overlooked data feature that occurs due to material transportation times, installation location and the analysis period of sampling equipment. The VTD values are considered to be the parameters of the D-SDAE model and obtained in the training process by the proposed double-scale collaborative search particle swarm optimization algorithm. The effectiveness of the proposed VTD-based D-SDAE model is validated in a numerical simulation and an industrial ironmaking plant, and a marked improvement in the prediction performance is achieved when VTD information is considered.

Numerical study of the feasibility of injecting CO2-containing off-gas in an ironmaking blast furnace

The injection of CO2-containing blast furnace top gas (BFTG) to replace reducing gas partially in an ironmaking blast furnace (BF) is a promising approach to achieve carbon neutralisation while potentially maintaining or improving BF performance. However, the feasible injection operating strategy for using CO2-containing BFTG and its effects on in-furnace phenomena are not well understood. In this study, a multi-fluid industrial-scale BF model with a tuyere injection submodel is developed to investigate the impacts of injecting CO2-containing BFTG at the BF tuyere on the in-furnace phenomena in terms of gas flow, temperature field, iron oxides distribution, and BF performance. The results show that: the maximum reducing gas replacement ratio by BFTG is ∼ 15 %, and a further increase leads to an unacceptable flame temperature. As more reducing gas is replaced by the BFTG, the start temperature of the intensified reduction for hematite and magnetite increases while those for wustite and iron decreases; the indirect reduction of iron oxides is improved in 1073–1273 K. The coke rate is increased by around 0.87 kg-coke/tHM with every 1 % reducing gas replaced by the BFTG. The top CO2 emission rate is decreased. This work provides a cost-effective tool to understand the flow-thermal-chemical behaviours inside a BF when CO2-containing gases are recycled in the BF ironmaking process.

Multichannel Dynamic Graph Convolutional Network-Based Fault Diagnosis and Its Application in Blast Furnace Ironmaking Process

Multichannel Dynamic Graph Convolutional Network-Based Fault Diagnosis and Its Application in Blast Furnace Ironmaking Process

Fault Detection-Based Multiple Local Manifold Learning and Its Application to Blast Furnace Ironmaking Process

Process safety plays a vital role in the modern process industry. To prevent undesired accidents caused by malfunctions or other disturbances in complex industrial processes, considerable attention has been paid to data-driven fault detection techniques. To explore the underlying manifold structure, manifold learning methods including Laplacian eigenmaps, locally linear embedding, and Hessian eigenmaps have been utilized in data-driven fault detection. However, only the partial local structure information is extracted from the aforementioned methods. This paper proposes fused local manifold learning (FLML), which synthesizes the typical manifold learning methods to find the underlying manifold structure from different angles. A more comprehensive local structure is discovered under a unified framework by constructing an objection optimization function for process data dimension reduction. The proposed method takes advantage of different manifold learning methods. Based on the proposed dimension reduction method, a new data-driven fault detection method is developed. Hotelling’s T2 and Q statistics are established for the purpose of fault detection. Experiments on an industrial benchmark Tennessee Eastman process whose average MDR and average FAR of FLML T2 are 7.58% and 0.21% and a real blast furnace ironmaking process whose MDR and FAR of FLML T2 are 2.80% and 0.00% are carried out to demonstrate the superiority and effectiveness of the proposed method.

Deep Learning Based Feature Selection and Ensemble Learning for Sintering State Recognition.

Sintering is a commonly used agglomeration process to prepare iron ore fines for blast furnace. The quality of sinter significantly impacts the blast furnace ironmaking process. In the vast majority of sintering plants, the judgment of sintering quality still relies on the intuitive observation of the cross section at sintering machine tail by operators, which is susceptible to the external environment and the experience of operators. In this paper, we propose a new sintering state recognition method using deep learning based feature selection and ensemble learning. First, features from the infrared thermal images of sinter cross section at the tail of the sinterer are extracted based on ResNeXt. Then, to eliminate the irrelevant, redundant and noisy features, an efficient feature selection method based on binary state transition algorithm (BSTA) is proposed to find the truly useful features. Subsequently, an ensemble learning (EL) method based on group decision making (GDM) is proposed to recognize the sintering states. Novel combination strategies considering the varying performance of the base learners are designed to further improve recognition accuracy. Industrial experiments conducted at a steel plant verify the effectiveness and superiority of the proposed method.

Dynamic stationary subspace analysis based on Gaussian mixture models for ironmaking process monitoring

AbstractBlast furnace ironmaking process monitoring is an important and challenging task. Due to the influence of hot blast stove switching and large fluctuations in the quality of raw materials, the measurements of ironmaking processes show obvious non‐stationary characteristics, and in addition, the observed data are also characterized by time‐series dynamic and non‐Gaussian characteristics. In this paper, a dynamic stationary subspace analysis method based on the Gaussian mixture model (DSSA–GMM) is proposed to address the difficulties in blast furnace ironmaking process monitoring. The time‐series dynamic relationship of the data is conducted by introducing a sliding time window. The Gaussian mixture model (GMM) is used to deal with the non‐Gaussian characteristics of the data, and the parameters of the GMMs are estimated using the expectation–maximization algorithm. The stationary projection matrix is obtained by optimizing the Kullback–Leibler (K–L) divergence between GMMs of different periods to realize the stationary subspace separation. Finally, the convex hull of the stationary subspace is established for fault detection, thus realizing the monitoring for non‐stationary and non‐Gaussian dynamic processes. The effectiveness of the DSSA–GMM method is verified by a numerical simulation and a dataset collected from an actual blast furnace ironmaking process.

An unsupervised fault monitoring framework for blast furnace: Information extraction enhanced GRU-GMM-autoencoder

Fault monitoring of the blast furnace ironmaking process (BFIP) is challenging due to the nonlinearity and dynamic characteristics. The lack of fault labels and the existence of outliers further increase the difficulty of fault monitoring. In particular, these outliers are considered normal operations in BFIP. In this case, an unsupervised autoencoder (AE)-based monitoring framework is proposed. Firstly, the gate recurrent unit (GRU) is used as an encoder to adaptively capture the nonlinear dynamic features of data. The extracted features are proved to be directly related to monitoring. Second, the variance constraint of latent variables (LVs) is added to the loss function to enhance the ability of information extraction. Third, an approach that combines AE structure and GMM to deal with outliers is proposed. Based on the probability clustering results of GMM, monitoring thresholds can be calculated adaptively for different samples. Meanwhile, the fault variables can also be located according to the increment of reconstruction error of GRU-AE. Finally, the proposed method is validated by a numerical example and the practical data gathered from the BF of a Chinese steel group. Compared to unsupervised statistical methods and deep learning methods, the proposed algorithm achieves the lowest false alarm rate (FAR) + missing alarm rate (MAR).

Properties study of artificial aggregate with high-content recycled concrete powder

With the need for urban development, there is a trend towards constructing large-span and super high-rise buildings. People have placed higher performance requirements on building materials. Therefore, the development of high-strength materials has become one of the current research focuses. Recycled concrete powder (RCP) is the residual powder generated while crushing waste concrete into a recycled aggregate. In order to achieve the low energy consumption resource utilization of RCP solid waste, a large amount of RCP with slag (a by-product of the blast furnace ironmaking process) addition was activated under an alkaline environment to prepare a cementitious material. The effects of RCP/Slag, liquid-solid ratio, Na2O content, and Na2SiO3 modulus on the setting time, compressive strength, and microstructure of alkali-activated high-content RCP-slag cementitious materials (AARCPS) were determined. The results showed that AARCPS had good compressive strength and microstructure; as the RCP content increased, the setting time of the cementitious material gradually prolonged. Based on the research of AARCPS, the mixing ratio was improved, and alkali-activated high-content RCP-slag aggregates (AARCPSA) were prepared. The results showed that with the increase in RCP content, the material fast setting speed and the sticky surface of material balls phenomenon during the aggregate preparation process was improved, and increasing the RCP content from 0% to 50% increased the ball-forming rate by about 14.36%. AARCPSA has good early strength performance, with the compressive strength at 3d reaching 75.18%–90.15% of that at 28d and the compressive strength at 7d reaching 93.85%–99.51% at 28d. The maximum compressive strength at 28d was 8.2 MPa. Increasing the slag and Na2O content in AARCPSA increased aggregate strength and density and decreased water absorption. The increase in RCP content and the decrease in Na2O content increased the peak strain of single particle compression of the aggregate and improved the deformation performance of the aggregate.

A Hybrid Cluster Variational Autoencoder Model for Monitoring the Multimode Blast Furnace System

Efficient monitoring of the blast furnace system is crucial for maintaining high production efficiency and ensuring product quality. This article introduces a hybrid cluster variational autoencoder model for monitoring the blast furnace ironmaking process which exhibits multimode behaviors. In contrast to traditional approaches, this method utilizes neural networks to learn data features and effectively handles the diverse feature types observed in different production modes. Through the utilization of a clustering process within the hidden layer of the variational autoencoder, the proposed technique facilitates efficient fault detection in the context of multimodal blast furnace data. Based on the variational autoencoder model, this study further establishes a unified monitoring index and defines a method for computing the control limits. The application of the model to real blast furnace data reveals its proficiency in accurately identifying faults across diverse modes; compared with the probabilistic principal component analysis based on the local nearest neighbor standardization method and the recursive probabilistic principal component analysis, the model shows a reduction in false positives by up to 10.3% and a substantial reduction of 19.2% in the missed detection rate. This method achieves a remarkable false detection rate of only 0.2% and 0 instances of missed detection.

A Novel Multi-Domain Adaptation-Based Method for Blast Furnace Anomaly Detection

In the steelmaking process, ensuring stable and reliable furnace plays a vital role for guaranteeing production quality of steel products. Traditional methods for detecting furnace anomalies in blast furnaces rely on operator judgment models built upon expert knowledge that can be limited by human experience. Moreover, data generated in blast furnace ironmaking process can be multidimensional, non-Gaussian distributed, and periodical, which can be easily affected by environmental and human factors and thus resulting in low accuracy of anomaly detection. Therefore, an online intelligent framework for detecting furnace anomalies is in high need. In this paper, the authors propose a novel anomaly detection method based on a furnace condition parameter-characterization model, a mining model of periodic patterns in the ironmaking process, and a multi-domain adaptive anomaly detection algorithm. They conduct extensive numerical analysis based on real-world production datasets as well to evaluate the effectiveness and accuracy of the method.

Predictive Modeling and Control Analysis of Fuel Ratio in Blast Furnace Ironmaking Process Based on Machine Learning

Predictive Modeling and Control Analysis of Fuel Ratio in Blast Furnace Ironmaking Process Based on Machine Learning

Intelligent Transfer Optimization for Ironmaking Process With Nonanalytic Constraints

In order to guarantee the smooth operation of the blast furnace ironmaking process, it is essential to consider the constraints for the optimization of this process. Due to the complexity of the process, it is challenging to obtain the description of the constraint functions and quantify the feasibility of solutions, making traditional optimization methods helpless. To address this problem, a transfer optimization framework is proposed that consists of a two-stage generation mapping algorithm, and an improved grey wolf optimizer (GWO) algorithm. The method achieves the transformation from constrained optimization to unconstrained optimization by establishing a proper mapping with distribution- and boundary-sensitive two-stage generation algorithm. Meanwhile, the density-amended GWO algorithm (DAGWO) with adaptive search steps depended on the solution density distribution is applied to locate the optimal solutions. The intelligent transfer optimization method is validated by both numerical tests and practical data, and the results demonstrate the effectiveness of the proposed algorithm.