Neural network approximation of iron oxide reduction process

Wiltowski, Tomasz; Piotrowski, Krzysztof; Lorethova, Hana; Stonawski, Lubor; Mondal, Kanchan; Lalvani, Shashi B.

doi:10.1016/j.cep.2004.08.007

Cited by 23 publications

(13 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…According to Yu et al [27], this phenomenon is due to the reaction rate governed by gas diffusion through the sample. In addition, the iron layer formed around the unreacted core can hamper the diffusion for both the reducing gas into the pellet and the products formed outward pellet [28,29].…”

Section: Kinetic Investigationmentioning

confidence: 98%

Synthetic zinc ferrite reduction by means of mixtures containing hydrogen and carbon monoxide

Junca

Oliveira

Restivo

et al. 2015

J Therm Anal Calorim

View full text Add to dashboard Cite

Solid waste generation is one of the main problems in the steelmaking process. One of the most problematic waste products is the electric arc furnace dust, which is a by-product rich in iron and zinc and is present as zincite (zinc oxide) or franklinite (zinc ferrite). This work focuses on the reduction kinetics of synthetic zinc ferrite by gases containing hydrogen and carbon monoxide. This process was examined via forced stepwise isothermal analysis. The test was conducted at temperatures ranging from 500 to 950°C. Reduction of zinc was accomplished using a mixture of hydrogen and carbon monoxide in order to simulate reformed natural gas. The results indicated that reduction of zinc ferrite occurred in two stages (550-750°C and 800-900°C). The first stage was characterized by iron oxide reduction, where a mix control between nucleation and diffusion was determined. The apparent activation energy obtained was 71.5 kJ mol -1 . The second stage was characterized by zinc oxide reduction, where the controlling mechanism was identified as a mixed control between diffusion and phase boundary reaction. The apparent activation energy was 135.5 kJ mol -1 . The formation of a dense layer of metallic iron around the unreacted core may have caused the apparent activation energy to increase.

show abstract

Section: Kinetic Investigationmentioning

confidence: 98%

Synthetic zinc ferrite reduction by means of mixtures containing hydrogen and carbon monoxide

Junca

Oliveira

Restivo

et al. 2015

J Therm Anal Calorim

View full text Add to dashboard Cite

show abstract

“…The output of i -th neuron in ( L + 1)-th layer is denoted as

. This value is comprised of a specific constant value called bias

, and N L signals from previous layers, amplified or weakened by the corresponding coefficients, called weights

[ 19 ]:

…”

Section: Technical Details Behind Annsmentioning

confidence: 99%

“…Thanks to these properties, the neural networks have found their use in vastly different fields, e.g., image classification [ 10 ], predicting combustion instability [ 11 ], or impact sensitivity of energetic materials [ 12 ]. Although ANNs have been extensively applied in chemical engineering since the 1990s [ 13 , 14 , 15 ], their usage in thermal analysis has commenced later [ 9 , 16 ], and most of the studies emerged only recently [ 17 , 18 , 19 , 20 , 21 ]. The present review aims to summarize such studies and to assess some future prospects.…”

Section: Introductionmentioning

confidence: 99%

Artificial Neural Networks for Pyrolysis, Thermal Analysis, and Thermokinetic Studies: The Status Quo

Muravyev

Luciano²,

Ornaghi

et al. 2021

Molecules

View full text Add to dashboard Cite

Artificial neural networks (ANNs) are a method of machine learning (ML) that is now widely used in physics, chemistry, and material science. ANN can learn from data to identify nonlinear trends and give accurate predictions. ML methods, and ANNs in particular, have already demonstrated their worth in solving various chemical engineering problems, but applications in pyrolysis, thermal analysis, and, especially, thermokinetic studies are still in an initiatory stage. The present article gives a critical overview and summary of the available literature on applying ANNs in the field of pyrolysis, thermal analysis, and thermokinetic studies. More than 100 papers from these research areas are surveyed. Some approaches from the broad field of chemical engineering are discussed as the venues for possible transfer to the field of pyrolysis and thermal analysis studies in general. It is stressed that the current thermokinetic applications of ANNs are yet to evolve significantly to reach the capabilities of the existing isoconversional and model-fitting methods.

show abstract

“…Monitoring systems can be realized through measurement devices and soft sensors (SSs), i.e. models able to produce reliable real-time estimates of unmeasured data based on available operational data [1][2][3][4][5][6][7][8][9]. SSs have been used in chemical engineering for modeling [10], fault diagnosis [11] and "what-if" analysis [12], just to give few examples.…”

Section: Introductionmentioning

confidence: 99%

Stacking approaches for the design of soft sensors using small data set

Bella

Graziani

Napoli

et al. 2008

2008 16th Mediterranean Conference on Control and Automation

View full text Add to dashboard Cite

In this paper a number of approaches to design a soft sensor for an industrial plant in case of small data set are compared. In particular different strategies to aggregate suboptimal models obtained by bootstrapped neural networks and noise injection are considered. An industrial case of study, consisting in the estimation of the T95% of a Thermal Cracking Unit (TCU) of a refinery in Sicily is considered to evaluate the performance of the different approaches.

show abstract

Neural network approximation of iron oxide reduction process

Cited by 23 publications

References 41 publications

Synthetic zinc ferrite reduction by means of mixtures containing hydrogen and carbon monoxide

Synthetic zinc ferrite reduction by means of mixtures containing hydrogen and carbon monoxide

Artificial Neural Networks for Pyrolysis, Thermal Analysis, and Thermokinetic Studies: The Status Quo

Stacking approaches for the design of soft sensors using small data set

Contact Info

Product

Resources

About