A deep learning approach for prediction of syngas lower heating value from CFB gasifier in Aspen plus®

Kartal, Furkan; Özveren, Uğur

doi:10.1016/j.energy.2020.118457

Cited by 58 publications

(17 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In chemical engineering, supervised learning methods (mainly regressionbased methods) are the widely used, in areas such as absorption [13], sludge treatment [14], reactor modelling [15], etc. ML regression methods reported in literature involves the use of linear regression [12], decision tree [16], Support Vector Regressions (SVR) [17], Artificial Neural Network (ANN) [18] etc. The wide application of these techniques in catalysis has recently been reported by Takahashi et al [19].…”

Section: Machine Learning Methods Are Typically Approached Asmentioning

confidence: 99%

Multi-output machine learning models for kinetic data evaluation : A Fischer–Tropsch synthesis case study

Chakkingal

Janssens

Poissonnier

et al. 2022

Chemical Engineering Journal

View full text Add to dashboard Cite

Section: Machine Learning Methods Are Typically Approached Asmentioning

confidence: 99%

Multi-output machine learning models for kinetic data evaluation : A Fischer–Tropsch synthesis case study

Chakkingal

Janssens

Poissonnier

et al. 2022

Chemical Engineering Journal

View full text Add to dashboard Cite

“…Unlike the model that works based on the chemical equilibrium in the real case, conversion rates of the reaction depend on the kinetics and residence time. This situation was discussed by some researchers who studied it with the equilibrium model [26,[37][38][39]. Hereby, the validation of the downdraft gasifier model was completed successfully, and the newly developed model was found to be reasonably acceptable.…”

Section: Model Validationmentioning

confidence: 99%

Investigation of Microalgae Gasification Under Steam Atmosphere in Downdraft Gasifier by Using Aspen Plus®

KEKİK

Özveren

2022

Eskişehir Technical University Journal of Science and Technology a - Applied Sciences and Engineering

Self Cite

View full text Add to dashboard Cite

Energy production is facing the environmental and economic issues due to growing population and uncertainties about the fossil fuels. These concerns prompt the researchers to find widely available and renewable alternative such as biomass instead of the fossil fuels. Microalgae is one of the promising biofuels owing to its rapid growth speed and higher calorific value. Steam gasification is an alternative way converting biomass to syngas with higher H2 and lower CO2 content compared with the other thermochemical conversion processes. In the present work, the downdraft gasifier model was developed by using Aspen Plus® program that has the capability to investigate the performance of microalgae gasification. Before the performance evaluation of the gasification, validation of the model successfully completed and exit gas compositions of H2, CO2, CO and CH4 were found very close for experimental study and the developed model. Effects of the main parameters of the process such as steam/biomass ratio and gasification temperature were assessed on the syngas composition and higher heating value (HHV) of syngas. The obtained results were stated that the increment in the temperature showed great effect on the H2 and CO compositions of syngas, they increased from 50.72% to 56.47% and 28.11% to 28.84% respectively. The simulation results also illustrated that the rising of the S/B ratio was favored the steam related reactions and increased the H2 content in syngas. However decreasing trend of the CH4 caused reducing of the HHV of syngas as a function of temperature and steam as well.

show abstract

“…Both models shown in Figure 3 contain an input layer, a hidden layer or layers, and an output layer. When ANNs contain more than one hidden layer they are referred to as deep neural networks (DNNs) [73]. Beyond this basic description of neural networks in Figure 3, details about various neural network architectures can be found in previous studies [74].…”

Section: Ann Models With Gasificationmentioning

confidence: 99%

Artificial Neural Networks and Gradient Boosted Machines Used for Regression to Evaluate Gasification Processes: A Review

Sedej¹,

Mbonimpa²,

Sleight³

et al. 2022

JEPT

View full text Add to dashboard Cite

Waste-to-Energy technologies have the potential to dramatically improve both the natural and human environment. One type of waste-to-energy technology that has been successful is gasification. There are numerous types of gasification processes and in order to drive understanding and the optimization of these systems, traditional approaches like computational fluid dynamics software have been utilized to model these systems. The modern advent of machine learning models has allowed for accurate and computationally efficient predictions for gasification systems that are informed by numerous experimental and numerical solutions. Two types of machine learning models that have been widely used to solve for quantitative variables that are of predictive interest in gasification systems are gradient boosted machines and artificial neural networks. In this article, the reviewed literature used either gradient boosted machines or artificial neural networks to successfully model gasification systems. The review of such literature allows for a comparison in machine learning model architecture and resultant accuracy as well as an insight into what parameters are being used to inform the models and to make predictions.

show abstract

A deep learning approach for prediction of syngas lower heating value from CFB gasifier in Aspen plus®

Cited by 58 publications

References 68 publications

Multi-output machine learning models for kinetic data evaluation : A Fischer–Tropsch synthesis case study

Multi-output machine learning models for kinetic data evaluation : A Fischer–Tropsch synthesis case study

Investigation of Microalgae Gasification Under Steam Atmosphere in Downdraft Gasifier by Using Aspen Plus®

Artificial Neural Networks and Gradient Boosted Machines Used for Regression to Evaluate Gasification Processes: A Review

Contact Info

Product

Resources

About