A hybrid knowledge- and data-driven method for diagnosing abnormal energy efficiency in blast furnaces

Blast furnace (BF) is the main method of modern iron-making. Ensuring the stability of the BF conditions can effectively improve the quality and output of iron and steel. However, operations of BF depend on mainly human experience, which causes two problems: (1) human experience is not objective and is difficult to inherit and learn and (2) it is difficult to acquire knowledge that contains time information among multiple variables in BF. To address these problems, a data-driven method is proposed. In this article, we propose a novel and efficient algorithm for discovering underlying knowledge in the form of temporal association rules (TARs) in BF iron-making data. First, a new TAR mining framework is proposed for mining temporal frequent patterns. Then, a novel TAR mining algorithm is proposed for mining underlying, up-to-date, and effective knowledge in the form of TARs. Finally, considering the updating of the BF database, a rule updating method is proposed that is based on the algorithm that is proposed in this article. Our extensive experiments demonstrate the satisfactory performance of the proposed algorithm in discovering TARs in comparison with the state-of-the-art algorithms. Experiments on BF iron-making data have demonstrated the superior performance and practicability of the proposed method.

Global climate change has become the focus of national attention and iron and steel enterprises, which have the feature of high energy consumption and high emissions, have an extremely significant influence on global climate change in Chinese modern industrialization process. The technology of blast furnace low-temperature heat source refrigeration for cooling dehumidifying uses huge amount of waste heat during blast furnace iron making process as the driving force of absorption refrigerator, and then the cooling capacity of preparation is used to reduce the moisture in blast furnace blowing to make the air humidity reduce to optimum value required for the operation, so as to save coke and increase the output. This article takes a certain Chinese large-scale blast furnace as an example, and has determined the technological process of using hot blast stove gas as a driving heat of absorption refrigerator to dehumidify blast furnace. We have determined the optimal outlet air humidity range by establishing system energy consumption model in different blast humidity. We select a certain iron and steel enterprise’s 450 m3 blast furnace and analyze the energy and economy efficiency after using dehumidifying blast system and calculate the equipment’s investment recovery period. The results show that in Liaoning Province when the blast humidity is about 8 g/m3, the system has the best energy economy efficiency and can save 3.06 kgce/t compared with the traditional technological process, and the equipment investment recovery period is 1.8 years, Reasonably use a large number of low temperature waste heat and reduced heat emissions has a significant impact on energy conservation and emissions reduction and climate change.

Manufacturing steel requires extremely challenging industrial processes. In particular, predicting the exact time instance of opening and closing tap-holes in a blast furnace has a great influence on steel production efficiency and operating cost, in addition to human safety. However, currently predicting the time to open and close tap-holes of the blast furnace still highly relies on manual human expertise and labor. Also, most of the prior research is limited to indirectly model the level of liquids in the hearth, using complex mathematical models or classical machine learning approaches. In this paper, we use a data-driven deep learning method to more accurately predict the remaining time to close each tap-hole in a blast furnace and develop an AI-enabled automated advisory system to reduce manual human efforts as well as operation cost. We develop a multivariate time series forecasting algorithm using Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) models to more accurately predict the opening and closing time for the Pohang Iron and Steel Company (POSCO) blast furnace. In particular, we use and validate data from one of the largest operating furnaces in the world to develop our system. Our proposed Skip-dense CNN (S-CNN) model achieves more than 90% accuracy within ±30 minutes tolerance, compared to other LSTM baseline models. Our S-CNN model has been successfully deployed at a large-scale blast furnace of POSCO since January 2018 and has achieved similar accuracy. And we even exceeded the reported human performance in a real operational environment.

While the inner profile of a blast furnace (BF) follows general standardization, its specific design remains largely experience-based. BF process modeling and optimization offer a systematic and cost-effective approach to studying the effects of key variables, including material properties, BF geometry, and operational conditions, providing valuable insights for BF design and control. In this work, a 3D BF process model was employed to investigate the design rules for BF geometry in the 1000 to 5000 m3 volume range. First, under fixed operating conditions, the optimal BF geometry for each volume was identified by minimizing total energy consumption. The results show that the method employed in this study can quantitatively replicate well-established industrial trends related to BF volume. Secondly, an analysis of transport phenomena within a furnace provided a rationale for these geometric trends. Lastly, it is shown that the optimum BF profile is also affected by the preset geometric constraints, even under the same operating conditions. Therefore, customized BF design may be required to better align with varying production needs.

The main method of modern ironmaking is blast furnace ironmaking, which is a very complex nonlinear dynamic process with complex physical-chemical coupling. The hot metal is the final product of blast furnace, and its silicon content not only reflects the quality of hot metal but also characterizes the operation status of the blast furnace, so its accurate prediction is very important for the operation of the blast furnace. Given the bottleneck problem in the application of the existing prediction model of hot metal silicon content in the blast furnace, this article proposed a novel data-driven modeling method. First, a nonlinear Takagi–Sugeno (T–S) fuzzy model is constructed for the hot metal silicon content to completely capture the nonlinear dynamics of the blast furnace process. Then, considering the doubts of blast furnace operators about the predicted results of the model, the Bayesian method is used to identify the consequent parameters of the fuzzy model to obtain the probability output, to present the credibility of the predicted results. Furthermore, to improve the robustness of the fuzzy model to the initial fuzzy rules, the sparse priori is adopted to construct a compact fuzzy model with strong generalization performance, in which the key fuzzy rules were screened out. In addition, two optimization methods are derived for each of the above models. Finally, the validity of the proposed methods is verified by the test of actual blast furnace data.

Steady thermal performance of a blast furnace determining its productivity and specific fuel consumption for one ton of hot metal depends on many factors. One of the main factors is the use of blast heated up to a high temperature. A continuous supply of hot blast to the blast furnace is provided by operation of the system consisting of three or four regenerative hot stoves. Energy efficiency of thermal performance of blast heating equipment significantly affects the technical and economic features of blast furnace smelting. In the total consumption of fuel equivalent, the share of thermal resources for blast heating is 10–12%. The hot blast stoves consume up to 30–35% of blast furnace gas. At present, most blast furnaces use hot blast at the temperature of 1150–1250°C; blast furnaces use hot blast stoves of different designs: stoves with an internal combustion chamber, stoves with an external combustion chamber, and top combustion or shaftless stoves (Kalugin design). The analysis of different thermal conditions in stoves has shown that Kalugin shaftless stoves are the most advanced and promising stoves in terms of energy efficiency and minimum environmental impact. The tendency for increased hot blast temperature was implemented in Kalugin stoves by means of energy efficiency improvement through the recovery of thermal energy of combustion products which are formed during checkerwork heating. The use of this energy in heat pipes for heating blast furnace gas and air supplied to the stove pre-chamber has resulted in an increase of the blast temperature and reduction of the BF gas consumption for heating. Moreover, the specific coke consumption for iron smelting was also reduced. These findings have been confirmed by heat balance analysis and by experience of commercial stove operation.

Techno-economic and environmental impact analysis of tuyere injection of hot reducing gas from low-rank coal gasification in blast furnace

The world production of hot metal and pig iron in 2012 reached 1.3 billion tons. More than 500 million tons of metallurgical coke produced from 650 million tons of expensive coking coals was consumed in blast furnaces to achieve this production goal. Metallurgical coke is a major contributor to the production costs of hot metal and pig iron, typically making up to 48–52% of the hot metal operating cost. Because of this, the reduction in metallurgical coke consumption was always a major goal for blast furnace operators. Supplemental fuels, especially in the form of a combined blast, are typically used to reduce coke consumption in a blast furnace. The major types of combined blast and supplemental fuels are as follows: oxygen enrichment, natural gas, oil and pulverized coal injection. The replacement coefficients of coke by these supplement fuels depend on the fuel quality, the arrangement of the injection process and adjustments in the blast furnace operating practice to optimize heat and mass transfer processes, metallic yield, gas dynamics and material movement. The fundamentals of the blast furnace process to achieve a highly efficient operation of the blast furnace with combined blast are discussed in this paper. The methodology of this research and development work is based on the theory of heat transfer in a blast furnace combined with local and overall heat and mass balances, the analysis of temperature distribution and material and gas movement. As a result, the maximum achievable replacement coefficients and reduction in the operating cost of hot metal were estimated alongside the

Most of world steel in 2018 has been produced from virgin iron ore via the blast furnace (BF)—basic oxygen furnace route. Therewith the BF is one of the most important unit processes in worldwide steel making. Among others, energy efficiency of the BF is dependent on coke reactivity. Coke gasification occurs via solution‐loss reactions either with CO2 or H2O. Herein, the gasification of coke is studied in CO–CO2–H2–H2O–N2 atmosphere simulating the BF conditions. The simulated atmospheres are based on the measurements from an actual BF. This research studies the effect of the composition of the BF atmosphere representing conditions near the wall as well as at the center and influence of the H2O content on coke gasification under simulated BF conditions. It is found that the location plays a role in coke gasification: wall atmosphere yields higher coke gasification compared with center. Dynamic tests show that introduction of H2 and H2O in gas atmosphere fastens coke gasification by +119% at temperature range between 800 and 1200 °C in wall conditions. When H2O is present in gas atmosphere, the mass loss of coke is also greater in both wall and center conditions.

High blast temperature is one of the important technical characteristics of modern blast furnace (BF), which is also an important technical approach for the green development of ironmaking. Increase blast temperature can improve and promote the BF operation smooth and stable, reduce coke rate, fuel consumption and CO2 emission. Top combustion hot blast stove technology has been applied in Shougang Jingtang’s 5500 m3 BF for 8 years. Under the condition of burning single BF gas, high efficiency energy conversion and over 1250 °C high blast temperature have achieved. The combustion and heat transformation process were researched by numerical simulation technology to optimize the structure design. The high efficiency annular ceramic burner and checker brick were developed and applied, the flue gas waste heat was recovered and reused to preheat the combustion air and gas. Prominent achievement of high blast temperature under the condition single BF gas burning has been realized.

Hybrid event-, mechanism- and data-driven prediction of blast furnace gas generation

Blast furnace ironmaking plays an important role in modern industry and the development of the economy. A reasonable ingredient scheme is crucial for energy efficiency and emission reduction in blast furnace production. Determining the right blast furnace ingredients is a complicated process; therefore, this study examines the optimization of the ingredient ratio. In this paper a model of the blast furnace ingredients is established by considering cost of per ton iron, CO2 emissions, and the theoretical coke ratio as the objective functions; ingredient parameters, process parameters, main and by-product parameters as variables; and the blast furnace smelting theory and equilibrium equation as constraints. Then, the model is solved by using an improved grey wolf optimization algorithm and an improved multi-objective grey wolf optimization algorithm. Using the data collected from the steel mill, the conclusion is that multi-objective optimization can consider the indexes of each target, so that the values of all the targets are excellent; we also compared the multi-objective solution results with the original production scheme of the steel mill, and we found that using the blast furnace ingredient scheme optimized in this study can reduce the cost of iron per ton, CO2 emissions per ton, and the theoretical coke ratio in blast furnace production by 350 CNY/t, 1000 kg/t, and 20 kg/t, respectively, compared with the original production plan. Thus, steel mill decision makers can choose the blast furnace ingredients according to different business strategies and the actual needs of steel mills can be better met.

Pellet property requirements for future blast-furnace operations and other new ironmaking processes

The development of blowers is inextricably linked with the stages of the history of technology and blast furnace production. The amount of blast is one of the main parameters of cast iron production, determining the size and performance of the blast furnace. Consideration of the issues of changing the design and drive of blowers starts from the natural draft and wedged leather bellows. The use of a horse-drawn drive or a water co-scaffold made it possible to increase the amount of air supplied to the furnace. The important event in the development of blowers was the advent of a steam engine, which made it possible to ensure industrial steel production in the middle of the XIX century. A fundamental change in the design of blowers occurred during the transition from reciprocating machines to centrifugal machines ‒ turboblowers powered by a steam turbine drive. Various design solutions of blowers of the transition period of the beginning of the XX century are considered, on the example of the technical equipment of the blower station of the Donetsk Metallurgical Plant (the plant of the Novorossiysk Society). Modern blower machine designs and characteristics are shown. It is noted that the cessation of the increase in the volume of created blast furnaces is associated with the achievement of the capacity limit of blowers. It is noted that in a number of cases, on the basis of technical and economic calculations, the possibility of obtaining a higher level of energy efficiency of the process of supplying blast to a blast furnace is substantiated when gas-tubine installations operating on blast-furnace gas are used to drive a turboblower. Some increase in the efficiency of the blast furnace process can be obtained, by considering the operation of a complex of devices: a turbo blower, an air heater, an air piping system.

Operational optimisation of the blast furnace (BF) is significant in facilitating smooth operation and reducing the production cost. Operation indicators are pivotal parameters used to measure operating status and reflect the quality of molten iron of the BF. In this study, a data-driven method for the prediction of production indicators is proposed by a novel fuzzy neural network of Takagi-Sugeno with bat algorithm (BA-TS-FNN). In practice, a BF usually works under varying operating conditions due to internal or external factors, redundant features with high dimensionally lead to poor computation time and prediction performance. To solve this problem, mutual information is applied to enhance understanding of the data. Considering that the standard TS-FNN cannot commendably cope with rapid convergence, local optimal, and sensitivity to initial weight problems during learning the prediction model, a bat optimisation algorithm is proposed to search global optimal parameters and improve the convergence rate. Finally, the probability density function (PDF) of modelling error is estimated by the kernel density estimation (KDE) as a criterion to measure the performance of the method. Experiments with industrial data from BF have demonstrated that the proposed method produces higher estimating accuracy than other modelling methods.