A hybrid intelligent model to predict the hydrogen concentration in the producer gas from a downdraft gasifier

Aguado, Roque; Casteleiro‐Roca, José‐Luis; Vera, David; Calvo-Rolle, José Luís

doi:10.1016/j.ijhydene.2022.04.174

Cited by 8 publications

(5 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Predictive modeling of biomass gasification processes using ML methods has been extensively investigated in recent years due to their low modeling costs, diverse modeling forms, and accurate prediction results. − For instance, Kim et al constructed three ML models, including Random Forest (RF), Support Vector Machine (SVM), and Artificial Neural Network (ANN), to predict syngas composition distribution and lower heating value in fluidized bed biomass gasification . Aguado et al integrated hybrid ML models to predict the hydrogen concentration in a downdraft fixed-bed biomass gasifier and used the model as a virtual sensor to calibrate or replace the actual sensor . Mutlu et al used a multicriteria ML approach to predict the hydrogen-rich syngas distribution and provided theoretical guidance for the biomass-coal cogasification reaction .…”

Section: Introductionmentioning

confidence: 99%

“…18 Aguado et al integrated hybrid ML models to predict the hydrogen concentration in a downdraft fixed-bed biomass gasifier and used the model as a virtual sensor to calibrate or replace the actual sensor. 19 Mutlu et al used a multicriteria ML approach to predict the hydrogen-rich syngas distribution and provided theoretical guidance for the biomass-coal cogasification reaction. 20 Serrano et al verified the variation pattern of tar content with equivalence ratio and temperature by comparing it with experimental results based on the ANN tar prediction model.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Disentangled Representation Aided Physics-Informed Neural Network for Predicting Syngas Compositions of Biomass Gasification

Ren,

Wu,

Weng

et al. 2024

Energy Fuels

View full text Add to dashboard Cite

Machine learning (ML) has been extensively studied and applied in the biomass gasification field currently. However, insufficient experimental data tends to cause a mismatch between the ML model and physical mechanism, particularly for the feedstocks that do not appear in the training data set, becoming a significant challenge in creating credible ML models for biomass gasification. Therefore, this study proposes a disentangled representation-aided physics-informed neural network method, briefly called DR-PINN, to predict biomass gasification syngas components. First, the DR-PINN extracts the latent variables to represent the feedstock properties through disentangled representation learning and generates synthetic samples in the gasificationrelated latent variable space to cover a full range of feedstock types. Then, DR-PINN employs inequality constraints to embed a priori monotonic relationships into the model training loss function. Finally, experimental and synthetic samples are simultaneously considered in the model training process to realize the synergy and complementarity of actual data information and existing physical knowledge using an evolutionary algorithm. As a result, DR-PINN shows good prediction performance (the feedstocks within the training data set: R 2 ≈ 0.96, root-mean-square error (RMSE) ≈ 1.7; the feedstocks outside the training data set: R 2 ≈ 0.81, RMSE ≈ 3). Moreover, even with the feedstocks outside the training data set, the DR-PINN model can strictly abide by the prior physical monotonic relationships, with the physical consistency degree equal to 1. Overall, the proposed DR-PINN demonstrates superior generalization and interpretability compared to other methods, such as RF, GBR, SVM, ANN, and PINN.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Disentangled Representation Aided Physics-Informed Neural Network for Predicting Syngas Compositions of Biomass Gasification

Ren,

Wu,

Weng

et al. 2024

Energy Fuels

View full text Add to dashboard Cite

show abstract

“…Additionally, biomass gasification represents a significant promising renewable source of hydrogen, a novel alternative power storage method that is anticipated to be crucial for the development of a sustainable energy future 5 . Gasification is one of the best thermochemical conversion technologies for converting biomass into gaseous fuel by partly oxidizing it 6 .…”

Section: Introductionmentioning

confidence: 99%

“…4 Additionally, biomass gasification represents a significant promising renewable source of hydrogen, a novel alternative power storage method that is anticipated to be crucial for the development of a sustainable energy future. 5 Gasification is one of the best thermochemical conversion technologies for converting biomass into gaseous fuel by partly oxidizing it. 6 The carbonaceous feedstock must be converted into gaseous fuel using a gasifying agent through a sequence of exothermic (heat-producing) and endothermic (heat-requiring) chemical processes.…”

mentioning

confidence: 99%

Techno‐economic viability analysis of a downdraft gasification system for hydrogen production from date molasses waste in Iraq

Malik Abbas,

Dakhel Alhassany,

Vera

et al. 2023

Biofuels Bioprod Bioref

Self Cite

View full text Add to dashboard Cite

In the current study, a fixed‐bed downdraft gasifier was used, in addition to gas cleaning and treatment units, to evaluate hydrogen production from the waste from a date molasses factory. Date pits and pomace were gasified at a temperature of 800°C with oxygen‐rich air and standard air as the gasifying agents. Simulations were performed using the Cycle‐Tempo simulation tool. The impact of many process parameters (air–fuel ratio, gasification temperature, moisture content, oxygen concentration and temperature of the water–gas shift) on gas composition was investigated. The economic evaluation of hydrogen production is also discussed in this paper. Depending on the operating conditions, the results indicate that gasification of biomass in oxygen‐rich air improves hydrogen yield compared with air gasification of biomass. Over the range of operating conditions examined, the maximum hydrogen production reached 45.86% for pits and 35.81% for pomace from gasification with oxygen‐rich air while the H2 content reached 36.71 and 28.72% respectively for air gasification of pits and pomace. The cost analysis for the date waste gasification unit showed that the hydrogen production cost is $3/kg for date pits and $4/kg for pomace. The production of hydrogen from date molasses manufacturing waste helps to lessen reliance on fossil fuels and is an environmentally beneficial alternative source of renewable energy.

show abstract

“…A hybrid AI approach is remarkably satisfied, with a 0.134% mean prediction error to predict the hydrogen concentration in a downdraft fixed-bed gasifier [89].…”

mentioning

confidence: 99%

Biomass Gasification and Applied Intelligent Retrieval in Modeling

Meena,

Kumar,

Chaturvedi

et al. 2023

Energies

View full text Add to dashboard Cite

Gasification technology often requires the use of modeling approaches to incorporate several intermediate reactions in a complex nature. These traditional models are occasionally impractical and often challenging to bring reliable relations between performing parameters. Hence, this study outlined the solutions to overcome the challenges in modeling approaches. The use of machine learning (ML) methods is essential and a promising integration to add intelligent retrieval to traditional modeling approaches of gasification technology. Regarding this, this study charted applied ML-based artificial intelligence in the field of gasification research. This study includes a summary of applied ML algorithms, including neural network, support vector, decision tree, random forest, and gradient boosting, and their performance evaluations for gasification technologies.

show abstract

A hybrid intelligent model to predict the hydrogen concentration in the producer gas from a downdraft gasifier

Cited by 8 publications

References 50 publications

Disentangled Representation Aided Physics-Informed Neural Network for Predicting Syngas Compositions of Biomass Gasification

Disentangled Representation Aided Physics-Informed Neural Network for Predicting Syngas Compositions of Biomass Gasification

Techno‐economic viability analysis of a downdraft gasification system for hydrogen production from date molasses waste in Iraq

Biomass Gasification and Applied Intelligent Retrieval in Modeling

Contact Info

Product

Resources

About