CFD-based reduced-order modeling of fluidized-bed biomass fast pyrolysis using artificial neural network

Zhong, Hanbin; Xiong, Qingang; Yin, Li; Zhang, Juntao; Zhu, Yu; Liang, Shuxiu; Niu, Ben; Zhang, Xinyu

doi:10.1016/j.renene.2020.01.057

Cited by 79 publications

(36 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An ANN is a computational model based on the mode of learning of biological neurons in the human brain 25. An ANN contains a series of layers of connected nodes named artificial neurons 26. The general concepts of ANNs have been explained elsewhere 27.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Multiple‐Output Artificial Neural Network to Estimate Solid Cycle Times in Conical Spouted Beds

et al. 2021

View full text Add to dashboard Cite

Knowledge of cycle times is essential to design spouted beds. Although experiments for determining cycle times are time‐consuming, there is hardly any mechanistic or empirical model for their prediction. Two types of artificial neural networks, namely, single‐ and multiple‐output ones, have been developed to estimate particle cycle times in conical spouted beds. They provide satisfactory cycle time predictions under different configurations. A comparison of single‐output neural networks with multiple‐output ones proves that, although the former fit slightly better the experimental data, the latter provide a reasonable prediction of all cycle times, and therefore, only one neural network is sufficient for their prediction. The maximum cycle is the one of highest sensitivity to all the parameters analyzed.

show abstract

Section: Methodsmentioning

confidence: 99%

“…Among all the available types of ANNs, the feedforward one was selected, as it has been widely used in the field of chemical engineering 26 and is suitable for nonlinear systems 28, 29. The tan‐sigmoid activation function was applied due to its nonlinear nature and the fact that it has been widely employed as a fast activation function.…”

Section: Methodsmentioning

confidence: 99%

Multiple‐Output Artificial Neural Network to Estimate Solid Cycle Times in Conical Spouted Beds

et al. 2021

View full text Add to dashboard Cite

show abstract

“…3) (Xiong et al 2018). The physicochemical interactions among cellulose, hemicellulose, and lignin are responsible for shielding the cellulose from isolation (Hassan et al 2020;Zhong et al 2020). The multistage procedure for the isolation of cellulose nanoparticles from biomass is acquired in two steps.…”

Section: Isolation Of the Cellulose Nanoparticlesmentioning

confidence: 99%

Renewable cellulosic nanocomposites for food packaging to avoid fossil fuel plastic pollution: a review

et al. 2020

View full text Add to dashboard Cite

The extensive use of petroleum-based synthetic and non-biodegradable materials for packaging applications has caused severe environmental damage. The rising demand for sustainable packaging materials has encouraged scientists to explore abundant unconventional materials. For instance, cellulose, extracted from lignocellulosic biomass, has gained attention owing to its ecological and biodegradable nature. This article reviews the extraction of cellulose nanoparticles from conventional and non-conventional lignocellulosic biomass, and the preparation of cellulosic nanocomposites for food packaging. Cellulosic nanocomposites exhibit exceptional mechanical, biodegradation, optical and barrier properties, which are attributed to the nanoscale structure and the high specific surface area, of 533 m2 g−1, of cellulose. The mechanical properties of composites improve with the content of cellulose nanoparticles, yet an excessive amount induces agglomeration and, in turn, poor mechanical properties. Addition of cellulose nanoparticles increases tensile properties by about 42%. Barrier properties of the composites are reinforced by cellulose nanoparticles; for instance, the water vapor permeability decreased by 28% in the presence of 5 wt% cellulose nanoparticles. Moreover, 1 wt% addition of filler decreased the oxygen transmission rate by 21%. We also discuss the eco-design process, designing principles and challenges.

show abstract

“…Reduced-order models have been developed in many areas of engineering, such as circuits (e.g., [1][2][3][4]), power systems (e.g., [5][6][7]), electromagnetics (e.g., [8][9][10]), fluid mechanics (e.g., [11][12][13]), nonlinear structural mechanics and earthquake engineering (e.g., [14]), nonlinear hydraulic fracturing problems (e.g., [15]), etc., to cite a few. Deep-learning artificial neural networks have been introduced to build on more traditional model-order reduction methods, such as the Proper Orthogonal Decomposition (POD), 1 to increase computational efficiency [16][17][18][19][20][21].…”

Section: Introductionmentioning

confidence: 99%

Model Reduction by Generalized Falk Method for Efficient Field-Circuit Simulations

Vu‐Quoc¹,

Zhai²,

Ngo³

2021

Computer Modeling in Engineering &Amp; Sciences

View full text Add to dashboard Cite

CFD-based reduced-order modeling of fluidized-bed biomass fast pyrolysis using artificial neural network

Cited by 79 publications

References 37 publications

Multiple‐Output Artificial Neural Network to Estimate Solid Cycle Times in Conical Spouted Beds

Multiple‐Output Artificial Neural Network to Estimate Solid Cycle Times in Conical Spouted Beds

Renewable cellulosic nanocomposites for food packaging to avoid fossil fuel plastic pollution: a review

Model Reduction by Generalized Falk Method for Efficient Field-Circuit Simulations

Contact Info

Product

Resources

About