In order to study in depth the differences in basic characteristics between iron ore fines commonly used by a steel company, and guide the sintering performance plant to choose the best ore allocation method, experimental studies on the basic characteristics of seven iron ore powders of three sizes were carried out using micro-sintering equipment, mainly including assimilation properties, liquid phase fluidity, and bonding phase strength. The results of the research showed that with the increase of the iron ore powder particle size, the assimilation of the seven iron ore powders showed an overall decreasing trend, deteriorating fluidity and decreasing bonding phase strength. Among them, the overall fluidity of iron ore powder A was poor, and the fluidity of iron ore powder B varied greatly between different particle grades, and the fluidity of iron ore powder C was more balanced and its bonding phase strength was high, while the overall bonding phase strength of iron ore powders B and E was low. The results of the study provide a theoretical basis for optimal ore allocation in sintering plants.
Special protective clothing should have a certain thermal insulation and protective effect in the production in front of the blast furnace. In order to study the design of special protective clothing for blast furnace foreman, its temperature distribution and internal thickness structure are deeply analyzed. First, based on the existing experimental data, combined with heat transfer and the Fourier law theory, a one-dimensional unsteady heat conduction equation is established. Using the explicit finite difference solution algorithm, the distribution law of the temperature of each fabric layer with time is obtained and the error analysis is performed. The error result is 0.42877%, which shows that the numerical solution is stable and convergent. Then, through the intelligent optimization model of a simulated annealing ant colony (SA-ACO), compared with the single ant colony algorithm (ACO) and a simulated annealing algorithm (SA), it avoids falling into the local optimal solution, reversely solves the optimal thickness of two layers of protective clothing in front of the blast furnace, improves the convergence speed of optimization, and verifies the reliability of the model with a sensitivity test. Finally, this paper actually solves the problem of the protective clothing design and mathematical intelligent model in front of the blast furnace and combines it with numerical simulation software to realize the numerical simulation of temperature distribution and thickness optimization of special protective clothing in front of the blast furnace, so as to provide theoretical guidance for enterprise blast furnace production and development of special protective clothing.
Long-term ecological restoration can restore aquatic ecosystems to a certain extent and alleviate the crisis of freshwater fish biodiversity. In order to explore the fish community distribution patterns and key factors after ecological restoration and the health status of the watershed, fish and environmental data were collected from 39 sampling points in the Hun River Basin in the spring and autumn of 2021. A total of 51 fish species belonging to 11 families and 37 genera were collected during the survey, and the dominant species were Rhynchocypris lagowskii, Zacco platypus, Carassius auratus and Pseudorasbora parva. Compared with the results of past studies, the number of fish species has increased. The study found that the distribution of fish along the longitudinal gradient of the watershed showed obvious spatial differences and was divided into two groups. The results of canonical correspondence analysis (CCA) showed that agricultural land, urban land and grassland were the key factors for the spatial variation in fish communities in the Hun River Basin. The results of the F-IBI evaluation showed that the health status of the Hun River was fair or above fair, among which healthy, good, fair, poor and bad points accounted for 5.13%, 30.77%, 33.33%, 25.64% and 5.13%, respectively. The upper and middle reaches of the Hun River Basin were in better health, while the lower reaches were in poorer health, which was mainly affected by the intensity of human activities in different regions. This study will help watershed managers to make targeted restoration and protection measures for different regions.
In order to obtain better prediction results, this paper combines improved complete ensemble EMD (ICEEMDAN) and the whale algorithm of multi-objective optimization (MOWOA) to improve the bidirectional gated recurrent unit (BIGRU), which makes full use of original complex stock price time series data and improves the hyperparameters of the BIGRU network. To address the problem that BIGRU cannot make full use of the stationary data, the original sequence data are processed using the ICEEMDAN decomposition algorithm to derive the non-stationary and stationary parts of the data and modeled with the BIGRU and the autoregressive integrated moving average model (ARIMA), respectively. The modeling process introduces a whale algorithm for multi-objective optimization, which improves the probability of finding the best combination of parameter vectors. The R2, MAPE, MSE, MAE, and RMSE values of the BIGRU algorithm, ICEEMDAN-BIGRU algorithm, MOWOA-BIGRU algorithm, and the improved algorithm were compared. An average improvement of 14.4% over the original algorithm’s goodness-of-fit value will greatly improve the accuracy of stock price predictions.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.