Improvement of a cement rotary kiln performance using artificial neural network

Aghdasinia, Hassan; Hosseini, Seyed Sharif; Hamedi, Jafar

doi:10.1007/s12652-020-02501-1

Cited by 9 publications

(4 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the homogenization effect in the rotary kiln is not very significant due to the following reasons [ 26 , 27 ]: Material Layer Thickness: A thicker material layer reduces the effective contact and mixing between different regions inside the kiln, particularly affecting the exchange between the central and peripheral materials, limiting the achievement of homogeneous mixing; Differences in Material Flow ability: Differences in the physical properties of the material, such as particle size, density, and shape, result in varying flowability within the kiln. These differences hinder uniform material distribution and mixing; Limited Mechanical Stirring: Although the rotation of the kiln promotes axial and radial movement of the material, this stirring is relatively mild and insufficient to achieve the high-efficiency homogenization comparable to specialized mixing equipment.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Evaluation and Analysis of Cement Raw Meal Homogenization Characteristics Based on Simulated Equipment Models

Cao,

Zhou

2024

Materials

View full text Add to dashboard Cite

In recent years, the variability in the composition of cement raw materials has increasingly impacted the quality of cement products. However, there has been relatively little research on the homogenization effects of equipment in the cement production process. Existing studies mainly focus on the primary functions of equipment, such as the grinding efficiency of ball mills, the thermal decomposition in cyclone preheaters, and the thermal decomposition in rotary kilns. This study selected four typical pieces of equipment with significant homogenization functions for an in-depth investigation: ball mills, pneumatic homogenizing silos, cyclone preheaters, and rotary kilns. To assess the homogenization efficacy of each apparatus, scaled-down models of these devices were constructed and subjected to simulated experiments. To improve experimental efficiency and realistically simulate actual production conditions in a laboratory setting, this study used the uniformity of the electrical capacitance of mixed powders instead of compositional uniformity to analyze homogenization effects. The test material in the experiment consisted of a mixture of raw meal from a cement factory with a high dielectric constant and Fe3O4 powder. The parallel plate capacitance method was employed to ascertain the capacitance value of the mixed powder prior to and subsequent to treatment by each equipment model. The fluctuation of the input and output curves was analyzed, and the standard deviation (S), coefficient of variation (R), and homogenization multiplier (H) were calculated in order to evaluate the homogenization effect of each equipment model on the raw meal. The findings of the study indicated that the pneumatic homogenizer exhibited an exemplary homogenization effect, followed by the ball mill. For the ball mill, a higher proportion of small balls in the gradation can significantly enhance the homogenization effect without considering the grinding efficiency. The five-stage cyclone preheater also has a better homogenization effect, while the rotary kiln has a less significant homogenization effect on raw meal. Finally, the raw meal processed by each equipment model was used for clinker calcination and the preparation of cement mortar samples. After curing for three days, the compressive and flexural strengths of the samples were tested, thereby indirectly verifying the homogenization effect of each equipment model on the raw meal. This study helps to understand the homogenization process of raw materials by equipment in cement production and provides certain reference and data support for equipment selection, operation optimization, and quality control in the cement production process.

show abstract

Section: Resultsmentioning

confidence: 99%

“…However, the homogenization effect in the rotary kiln is not very significant due to the following reasons [26,27]:…”

Section: Compressive and Flexural Strength Analysismentioning

confidence: 99%

Evaluation and Analysis of Cement Raw Meal Homogenization Characteristics Based on Simulated Equipment Models

Cao,

Zhou

2024

Materials

View full text Add to dashboard Cite

show abstract

“…Therefore, the Lagrange multiplier τ vanishes during the derivation process. Then, let β and ξ also vanish according to (5), and the following formula can be obtained:…”

Section: The Mkelm Algorithmmentioning

confidence: 99%

“…When the fCaO content is higher than the standard range, the cement clinker is unqualified. On the other hand, when it is lower than the standard range, the clinker is over-burning and the energy consumption increases [5].…”

Section: Introductionmentioning

confidence: 99%

Cholesky Factorization Based Online Sequential Multiple Kernel Extreme Learning Machine Algorithm for a Cement Clinker Free Lime Content Prediction Model

2021

View full text Add to dashboard Cite

Aiming at the difficulty in real-time measuring and the long offline measurement cycle for the content of cement clinker free lime (fCaO), it is very important to build an online prediction model for fCaO content. In this work, on the basis of Cholesky factorization, the online sequential multiple kernel extreme learning machine algorithm (COS-MKELM) is proposed. The LDLT form Cholesky factorization of the matrix is introduced to avoid the large operation amount of inverse matrix calculation. In addition, the stored initial information is utilized to realize online model identification. Then, three regression datasets are used to test the performance of the COS-MKELM algorithm. Finally, an online prediction model for fCaO content is built based on COS-MKELM. Experimental results demonstrate that the fCaO content model improves the performance in terms of learning efficiency, regression accuracy, and generalization ability. In addition, the online prediction model can be corrected in real-time when the production conditions of cement clinker change.

show abstract