Prediction of coal ash fusion temperatures using computational intelligence based models

Tambe, Sanjeev S.; Naniwadekar, Makarand; Tiwary, Shishir; Mukherjee, Ashis K.; Das, Tarit Baran

doi:10.1007/s40789-018-0213-6

Cited by 18 publications

(10 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another direction of research is the use of machine learning methods to predict AFTs [11,[20][21][22][23][24][25][26][27][28][29]. The most frequently techniques used were artificial neural networks (ANNs) and support vector machine (SVM).…”

Section: Standard:iso Pn-iso 540:2001 Descriptionmentioning

confidence: 99%

An Interpretable Extreme Gradient Boosting Model to Predict Ash Fusion Temperatures

2020

View full text Add to dashboard Cite

The hemispherical temperature (HT) is the most important indicator representing ash fusion temperatures (AFTs) in the Polish industry to assess the suitability of coal for combustion as well as gasification purposes. It is important, for safe operation and energy saving, to know or to be able to predict value of this parameter. In this study a non-linear model predicting the HT value, based on ash oxides content for 360 coal samples from the Upper Silesian Coal Basin, was developed. The proposed model was established using the machine learning method—extreme gradient boosting (XGBoost) regressor. An important feature of models based on the XGBoost algorithm is the ability to determine the impact of individual input parameters on the predicted value using the feature importance (FI) technique. This method allowed the determination of ash oxides having the greatest impact on the projected HT. Then, the partial dependence plots (PDP) technique was used to visualize the effect of individual oxides on the predicted value. The results indicate that proposed model could estimate value of HT with high accuracy. The coefficient of determination (R2) of the prediction has reached satisfactory value of 0.88.

show abstract

Section: Standard:iso Pn-iso 540:2001 Descriptionmentioning

confidence: 99%

An Interpretable Extreme Gradient Boosting Model to Predict Ash Fusion Temperatures

2020

View full text Add to dashboard Cite

show abstract

“… Many studies have been conducted to predict the melting characteristic temperature of coal ash. Tambe et al used a computational intelligence model to estimate the coal ash melting temperature and obtained good results. Using the GWOSVM model, Xiao et al predicted the DT of coal ash and indicated that the model has a specific prediction accuracy.…”

Section: Introductionmentioning

confidence: 99%

“…A variety of extremely complicated and nonlinear phenomena can be modeled and studied using artificial neural networks (ANN), which are effective modeling and investigation methods. While having a pretty good level of prediction accuracy, some current AFT prediction models consider coal from various geographic regions . The models are complicated, costly, and time-consuming to test since they depend on a large number of predictors (input variables).…”

Section: Introductionmentioning

confidence: 99%

Effects of Proximate Analysis on Coal Ash Fusion Temperatures: An Application of Artificial Neural Network

Onifade,

Lawal,

Bada

et al. 2023

ACS Omega

View full text Add to dashboard Cite

The temperature at which coal ash melts has a significant impact on the operation of a coal-fired boiler. The coal ash fusion temperature (AFT) is determined by its chemical composition, although the relationship between the two varies. Therefore, it is important to have mathematical models that can reliably predict the coal AFTs when designing coal-based processes based on their coal ash chemistry and proximate analysis. A computational intelligence model based on the interrelationships between coal properties and AFTs was used to predict the AFTs of the coal investigated. A model that integrates the ash, volatile matter, fixed carbon contents, and ash chemistry as input and the AFT [softening temperature, deformation temperature, hemispherical temperature, and flow temperature] as an output provided the best indicators to predict AFTs. The findings from the models indicate (a) a method for determining the AFTs from the coal properties; (b) a reliable technique to calculate the AFTs by varying the proximate analysis; and (c) a better understanding of the impact, significance, and interactions of coal properties regarding the thermal properties of coal ash. This study creates a predictive model that is easy to use, computer-efficient, and highly accurate in predicting coal AFTs based on their ash chemistry and proximate analysis data.

show abstract

“…To improve the viscosity–temperature characteristics of the coal ash, blending is a promising method , by which the high-melting-point mullite and quartz are transformed into the low-melting-point eutectics . Many researchers have established various models to find an empirical or statistical correlation between the ash fusion temperatures and ash composition. − Sasi et al devised the prediction model using two approaches, namely, a thermodynamic approach using the ChemApp subroutine and a purely data-driven approach using artificial neural networks, obtaining a conclusion that a combination of these two approaches provided an efficient and reliable way toward the industrial application …”

Section: Introductionmentioning

confidence: 99%

Melting Characteristics of Coal Ash and Properties of Fly Ash to Understand the Slag Formation in the Shell Gasifier

Wang

Cheng

et al. 2021

ACS Omega

View full text Add to dashboard Cite

The flow temperature (FT) of the coal ash from the Liuqiao no. 2 mine in North Anhui Province (C00) is too high (∼1520 °C) to fit the Shell gasifier due to its relatively high content of SiO 2 and Al 2 O 3 . To solve this problem, a series of coals were blended with C00 with different ratios, and the relations between FT and the ash composition were investigated. The coal ash was analyzed by X-ray diffraction, Fourier transform infrared (FTIR) spectroscopy, and scanning electron microscopy−EDX to elucidate the mechanism of the improved ash fusion performance and the slag formation in the waste heat boiler of the gasifier. It is shown that FT is relevant to the coal ash compositions as well as the structures formed at high temperatures. The existence of alkaline oxides (CaO, MgO, and Fe 2 O 3 ) decreases the coal ash FT to a low level. The FT can decrease to <1350 °C to cater to the Shell gasifier by blending C00 and C03 with a mass ratio of 4:6 owing to the plentiful alkaline oxides in C03. The FTIR results indicate that the high flow temperature of C00 is attributed to the formation of mullite at high temperatures. The coal blending with various ratios changes the compositions of CaO, MgO, and Fe 2 O 3 , which can form some low-melting-point eutectic compounds with SiO 2 and Al 2 O 3 under high temperatures, inhibit the formation of mullite, and thus decrease the ash FT. The coal ash FT was found to have a good linear relation with the ash compositions, which can sever as a reference to the coal blending. According to the model parameters, it is shown that Mg has the most significant promoting effect on the decrease in FT of the coal ash. The caking tendency of fly ash increases with the rising Ca content and an excessive Ca-based fluxing agent used in the coal blending will lead to the aggregation of the Ca-rich clasts around the fly ash particle, resulting in the plugging of the waste heat boiler in the gasifier. Therefore, the Mg-based fluxing agent is more promising to improve the ash fusion performance and reduce the caking tendency of the coal fly ash.

show abstract

Prediction of coal ash fusion temperatures using computational intelligence based models

Cited by 18 publications

References 40 publications

An Interpretable Extreme Gradient Boosting Model to Predict Ash Fusion Temperatures

An Interpretable Extreme Gradient Boosting Model to Predict Ash Fusion Temperatures

Effects of Proximate Analysis on Coal Ash Fusion Temperatures: An Application of Artificial Neural Network

Melting Characteristics of Coal Ash and Properties of Fly Ash to Understand the Slag Formation in the Shell Gasifier

Contact Info

Product

Resources

About