The silicon content of hot metal is a key index for the determination of blast furnace status, and accurate prediction of the silicon content of hot metal is crucial for blast furnace ironmaking. ...First, 10992 sets of blast furnace data obtained from the site of an iron and steel enterprise were preprocessed. Then, 22 important feature parameters related to the silicon content of hot metal were screened by feature engineering. Finally, the hyperparameters of the Gradient Boosting Decision Tree (GBDT) algorithm model were optimized with the help of the Optuna framework, and the Optuna-GBDT model was established to predict the silicon content of hot metal. The experimental results show that compared with the Bayesian algorithm and the traditional stochastic search method, the Optuna framework can achieve better hyperparameter optimization with fewer iterations and smaller errors.The Optuna-GBDT model performs better in predicting the silicon content of hot metal compared with the optimized Random Forest (RF), Decision Tree and AdaBoost models, and the prediction results are basically in line with the actual values, with the mean absolute error (MAE) of 0.0094, the root mean square error (RMSE) of 0.0152, and the coefficient of determination (R2) of 0.975.The experimental results verified the validity and feasibility of establishing the Optuna-GBDT model to predict the silicon content of hot metal, which provides a reliable tool for iron and steel enterprises and helps to optimize the ironmaking process, improve production efficiency and product quality.
Micron-sized iron particles are promising carbon-free fuels. Efforts have been made to understand the combustion process of pure iron particles. However, it is not well-established how important are ...the impurities and their influence on combustion. The ignition and combustion characteristics of iron particles with 6.18 wt.% silicon were studied both by online optical diagnostics and offline scanning electron microscope (SEM) and X-ray Diffraction (XRD) analysis in this work. It is found that the ignition delay time is proportional to dn with n=1.23∼1.56, indicating that the oxidation reaction is unlikely solely limited by internal ionic diffusion before ignition. Compared with pure iron particles, the silicon-containing iron particle has a lower peak temperature and less oxidized combustion products. The intensity-rising time in the first intensity peak stage scales (1/XO2)n with n=0.80or1.38, which implies an external diffusion controlled combustion regime. Silicon in the oxide layer likely reduces the internal diffusion rate of oxygen, which becomes a rate-limiting step after the first intensity peak. Meanwhile, the surface tension also decreases due to the silicon content, which may facilitate the gas bubble nucleation and burst. The particle could partially change back to the external diffusion regime when the oxide layer is broken by the bubble expansion. This mechanism allows the reaction rate to increase and particle temperature to rise again. This explanation is verified by plenty of holes in the combustion products as well as the fact that the rising time in the large peak stage is proportional to (1/XO2)n with n=0.37or0.32. With the increase in the temperature of the ambient gas flow, evaporation was observed. The high ambient temperature is hypothesized to be a key factor to trigger the evaporation of silica.
Lodging has been a limiting factor for the achievement of high grain yield in rice (Oryza sativa L.) production especially under high nitrogen input. But little is known about the effects of nitrogen ...fertilizer management on lodging and the potentials for improving lodging resistance in rice by nitrogen management.
The objective of this study was to evaluate the ability of lodging resistance of rice plants under different nitrogen managements.
Based on a two-year experiment, we investigated lodging incidence in the field and traits associated with lodging of two rice cultivars with contrasting lodging susceptibility. Four fertilization schemes were established with different ratios of urea to controlled-release nitrogen fertilizer (CRNF), i.e., control (CK), local farmers’ practices with split nitrogen application of common urea (100 % urea, CU), 100 % CRNF was applied once as basal fertilizer (CRNF), and the combined application of 70 % CRNF and 30 % urea as basal fertilizer (CRNF-CU). We studied morphological traits, anatomical structure, and biochemical components related to the ability of lodging resistance in rice.
Our results show that at high yielding levels with high nitrogen inputs, the lodging resistance was highest in the CRNF-CU treatment, and followed by CU and CRNF treatments. The lodging index (LI, susceptibility to lodging) could be decreased by 10.52 % and 24.63 %, when compared CRNF-CU treatment with CU and CRNF treatments, respectively. These significant differences in LI were attributed to variations in multiple parameters, i.e., silicon content (SiC), cellulose content (CC), lignin content (LC), number of large vascular bundles (NLVB), number of small vascular bundles (NSVB), sclerenchyma cell thickness (SECT), etc., of which, silicon deposition in the culm was the most important contributor to enhance lodging resistance. In the CRNF-CU treatment, the relatively lower soil N content during the period of internode development could be beneficial for plant silicon uptake, contributing to lodging resistance.
Combining urea and controlled release nitrogen fertilizer could enhance lodging resistance of rice at high yielding levels.
This study provides useful information for how to enhance lodging resistance in rice with combined application of urea and controlled release nitrogen fertilizer at high yielding levels.
•Combining urea and controlled release nitrogen fertilizer enhances lodging resistance.•Silicon deposition in the culm is crucial for lodging resistance•The lodging resistance is influenced by the soil nitrogen contents during the elongation of internodes.
•Oxidation behavior of AlCoCrFeNiSix high entropy alloys at 1100℃ was investigated.•Microstructure of the alloys changed from single BCC to BCC + Silicide with addtion of Si.•Si0.2 alloy exhibited ...best oxidation resistance due to formation of single and compact Al2O3 scale after 200 h oxidation.•Excessive Si addition imposed an adverse affect on the oxidation resistance of the alloys.
AlCoCrFeNiSix high-entropy alloys containing different Si contents (x = 0, 0.2, 0.5, 0.8, 1.0 in molar ratio) were prepared by vacuum arc-melting. The microstructure and oxidation behavior of these alloys at 1100℃ for 200 h were investigated. After adding Si, the alloys mainly consist of BCC and Si-rich precipitates, and both the size and quantity of the Si-rich precipitates increase with increase in the Si content. A suitable content of Si in the alloys improves the oxidation resistance for promoting the formation of a dense single Al2O3 scale, while excessive Si imposes an adverse effect by forming easy-peeling scales composed of Al2O3 outer layer and mixed oxides inner layer. Formation and failure mechanisms of the oxide scales on these alloys during oxidation have been discussed.
We evaluate how the heterogeneity of the precursor may affect pyrolysis and CO2 gasification behavior aimed at activated carbon applications. Barley straw, ground and classified into five size ...ranges, is characterized by non-isothermal thermogravimetry tests at various heating rates. Fixed carbon and volatile matter contents decrease with particle size. Also, the finest fraction is enriched in minerals by exogenous contamination and accumulation of silicon-rich leaves. Faster pyrolysis kinetics are found for small sizes, caused by their higher alkali contents and heat-mass transfer rates. Char-CO2 gasification conversion rates show an unexpected behavior, not previously reported. Higher reactivity is found for the finest fraction, decreasing significantly at temperatures beyond 750 °C. The high alkali content of the finest fraction promotes the catalytic effect of minerals on gasification reactivity at lower temperatures, hindering the reaction at higher temperatures by forming low-melting-point potassium silicates. Results help improve pretreatment strategies to enhance activated carbon quality.
Display omitted
•A wide size distribution and heterogeneity of barley straw after milling is observed.•Inorganic content is significantly increased as the particle size is reduced.•High Si content is detected in SEM-EDX images of particles coming from barley leaves.•Char gasification rate is higher for the finest fraction below 750 °C by catalytic effects.•Char gasification rate decreases at T >750°C for particle sizes <0.15 mm by the Si/K influence.
In the blast furnace ironmaking process, accurate prediction of silicon content in molten iron is of great significance for maintaining stable furnace conditions, improving hot metal quality, and ...reducing energy consumption. However, most of the current research works employ linear correlation coefficient methods to select input features in modeling, which may not fully take the nonlinear and coupling relationships between features into account. Therefore, this article considers the input feature selection issue of silicon content prediction model from a new perspective and proposes a multiobjective evolutionary nonlinear ensemble learning model with evolutionary feature selection mechanism (MOENE-EFS), in which extreme learning machine is adopted as the base learner. MOENE-EFS takes the input feature scheme of each base learner as well as their network structure and parameters as decision variables and proposes a modified nondominated sorting differential evolution algorithm to optimize two conflicting objectives, i.e., accuracy and diversity of base learners, simultaneously. Through the optimization, a set of Pareto optimal base learners with high accuracy and strong diversity can be obtained. Moreover, different from the linear ensemble methods commonly used in classical evolutionary ensemble learning, this article proposes a nonlinear ensemble method to combine the obtained base learners based on differential evolution. Experimental results indicate that the two proposed strategies, i.e., evolutionary feature selection and nonlinear ensemble, are very effective in improving the accuracy and stability of the prediction model. MOENE-EFS also outperforms the other prediction models in both benchmark data and practical industrial data. Furthermore, analysis on the input features of all Pareto optimal base learners shows that the evolutionary feature selection is capable of selecting essential features and is consistent with human experience, which indicates it is a promising method to deal with the input feature selection issue in silicon content prediction.
The silicon content of hot metal is a key index for the determination of blast furnace status, and accurate prediction of the silicon content of hot metal is crucial for blast furnace ironmaking. ...First, 10992 sets of blast furnace data obtained from the site of an iron and steel enterprise were preprocessed. Then, 22 important feature parameters related to the silicon content of hot metal were screened by feature engineering. Finally, the hyperparameters of the Gradient Boosting Decision Tree (GBDT) algorithm model were optimized with the help of the Optuna framework, and the Optuna-GBDT model was established to predict the silicon content of hot metal. The experimental results show that compared with the Bayesian algorithm and the traditional stochastic search method, the Optuna framework can achieve better hyperparameter optimization with fewer iterations and smaller errors. The Optuna-GBDT model performs better in predicting the silicon content of hot metal compared with the optimized Random Forest (RF), Decision Tree and AdaBoost models, and the prediction results are basically in line with the actual values, with the mean absolute error (MAE) of 0.0094, the root mean square error (RMSE) of 0.0152, and the coefficient of determination (R2) of 0.975. The experimental results verified the validity and feasibility of establishing the Optuna-GBDT model to predict the silicon content of hot metal, which provides a reliable tool for iron and steel enterprises and helps to optimize the ironmaking process, improve production efficiency and product quality.
Ensuring the safe and steady operation of a blast furnace hinges on accurate predictions of silicon content. However, these predictions often fall short, proving unreliable and imprecise, ...particularly in unstable furnace conditions and in the face of substantial data swings. The wide variances and low reliability of silicon concentration predictions make them unsuitable as a reference for daily blast furnace maintenance and adjustments. To counter this engineering challenge, we introduce a novel silicon content prediction technique: the Gated Recurrent Unit Network Quantile Regression (GRUQR). This method amalgamates the Gated Recurrent Unit Network with quantile regression to refine the silicon content prediction model. Our approach first leverages GRUQR to anticipate the silicon content in molten iron across various quantiles. Subsequently, we scrutinize the patterns of silicon content changes and identify the optimal quantile for silicon content under different furnace conditions. We also discuss the reliability of our silicon concentration forecasts and present confidence intervals at various levels. To validate the effectiveness of the proposed GRUQR method, we employ real-world data from a Chinese blast furnace ironmaking process. These prediction results serve as a reliable reference for furnace operators, enabling them to determine the furnace temperature under challenging conditions.
An essential feature of shale is swelling induced by shale–liquid interactions. Shale swelling is an important inducing factor for shale damage that affects shale mechanics. A better understanding of ...the effects of shale swelling on shale mechanics is crucial for drilling and fracturing design. Therefore, the effects of shale swelling on shale damage and shale mechanics were investigated. The results demonstrated that an increase in shale swelling increases shale damage, thus negatively affecting shale mechanics. The compressive strength decreases rapidly with increasing shale swelling. Moreover, the decrease in the elastic modulus is controlled by shale swelling. The elastic modulus of shale reduces by 17.9% when shale swelling is 0.4%, compared to only 3.1% when shale swelling is 0.2%. The effects of shale swelling on the elastic modulus are affected by quartz content and confining pressure. Shale can maintain a high elastic modulus at high quartz content during shale swelling. The correlations of shale swelling and elastic modulus under different quartz contents were established. Based on these research results, a possible reason for casing deformation in the Weirong shale gas field was discussed.
•The effects of shale swelling on shale mechanics was proved.•The effects of shale swelling on the elastic modulus is affected by quartz content.•The correlations of shale swelling and elastic modulus under different quartz content were established.•The effects of shale mechanics on casing deformation based on shale swelling was discovered.
Ensuring the safe and steady operation of a blast furnace hinges on accurate predictions of silicon content. However, these predictions often fall short, proving unreliable and imprecise, ...particularly in unstable furnace conditions and in the face of substantial data swings. The wide variances and low reliability of silicon concentration predictions make them unsuitable as a reference for daily blast furnace maintenance and adjustments. To counter this engineering challenge, we introduce a novel silicon content prediction technique: the Gated Recurrent Unit Network Quantile Regression (GRUQR). This method amalgamates the Gated Recurrent Unit Network with quantile regression to refine the silicon content prediction model. Our approach first leverages GRUQR to anticipate the silicon content in molten iron across various quantiles. Subsequently, we scrutinize the patterns of silicon content changes and identify the optimal quantile for silicon content under different furnace conditions. We also discuss the reliability of our silicon concentration forecasts and present confidence intervals at various levels. To validate the effectiveness of the proposed GRUQR method, we employ real-world data from a Chinese blast furnace ironmaking process. These prediction results serve as a reliable reference for furnace operators, enabling them to determine the furnace temperature under challenging conditions.
