Forecasting blast furnace gas production and demand through echo state neural network-based models: Pave the way to off-gas optimized management

Matino, Ismael; Dettori, Stefano; Colla, Valentina; Weber, Valentine; Salame, Sahar

doi:10.1016/j.apenergy.2019.113578

Cited by 58 publications

(29 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A step ahead in the internal off-gas optimized management was carried out in the project co-funded by the European Union through the Research Fund for Coal and Steel (RFCS), which is entitled "Optimization of the management of the process gases network within the integrated steelworks-GASNET" [17,18,25]. Within this project a Decision Support System (DSS) was developed helping plant managers to optimally exploit process off-gases by minimizing energy wastes and flaring and considering environmental and economic constraints as well as synergies among producers and consumers of gas, heat, electricity, and steam.…”

Section: Introductionmentioning

confidence: 99%

Renewable Hydrogen Production Processes for the Off-Gas Valorization in Integrated Steelworks through Hydrogen Intensified Methane and Methanol Syntheses

Zaccara

Petrucciani

Matino

et al. 2020

Metals

Self Cite

View full text Add to dashboard Cite

Within integrated steelmaking industries significant research efforts are devoted to the efficient use of resources and the reduction of CO2 emissions. Integrated steelworks consume a considerable quantity of raw materials and produce a high amount of by-products, such as off-gases, currently used for the internal production of heat, steam or electricity. These off-gases can be further valorized as feedstock for methane and methanol syntheses, but their hydrogen content is often inadequate to reach high conversions in synthesis processes. The addition of hydrogen is fundamental and a suitable hydrogen production process must be selected to obtain advantages in process economy and sustainability. This paper presents a comparative analysis of different hydrogen production processes from renewable energy, namely polymer electrolyte membrane electrolysis, solid oxide electrolyze cell electrolysis, and biomass gasification. Aspen Plus® V11-based models were developed, and simulations were conducted for sensitivity analyses to acquire useful information related to the process behavior. Advantages and disadvantages for each considered process were highlighted. In addition, the integration of the analyzed hydrogen production methods with methane and methanol syntheses is analyzed through further Aspen Plus®-based simulations. The pros and cons of the different hydrogen production options coupled with methane and methanol syntheses included in steelmaking industries are analyzed.

show abstract

Section: Introductionmentioning

confidence: 99%

Renewable Hydrogen Production Processes for the Off-Gas Valorization in Integrated Steelworks through Hydrogen Intensified Methane and Methanol Syntheses

Zaccara

Petrucciani

Matino

et al. 2020

Metals

Self Cite

View full text Add to dashboard Cite

show abstract

“…GasNet developed a simulation tool of the network of process gas and steam including their generation and flows as well as a multi-level strategy for their optimization. ML-based tools and technologies such as Echo-State and FeedForward Neural Networks, as well as advanced optimization approaches (e.g., Mixed Integer Linear programming) have been used in order to improve energy efficiency and environmental sustainability of the steelmaking processes [64][65][66][67][68]. In SOProd Objected-Oriented Programming (OOP), Python language, LabView, MongoDB, and Optical character recognition are some of the technologies adopted to improve product intelligence and autonomous machine-machine and product-machine communication [69].…”

Section: Past and Ongoing Research Activities Funded By The Researchmentioning

confidence: 99%

The Challenge of Digitalization in the Steel Sector

Branca

Fornai

Colla

et al. 2020

Metals

Self Cite

120

View full text Add to dashboard Cite

Digitalization represents a paramount process started some decades ago, but which received a strong acceleration by Industry 4.0 and now directly impacts all the process and manufacturing sectors. It is expected to allow the European industry to increase its production efficiency and its sustainability. In particular, in the energy-intensive industries, such as the steel industry, digitalization concerns the application of the related technologies to the production processes, focusing on two main often overlapping directions: Advanced tools for the optimization of the production chain and specific technologies for low-carbon and sustainable production. Furthermore, the rapid evolution of the technologies in the steel sector require the continuous update of the skills of the industrial workforce. The present review paper, resulting from a recent study developed inside a Blueprint European project, introduces the context of digitalization and some important definitions in both the European industry and the European iron and steel sector. The current technological transformation is depicted, and the main developments funded by European Research Programs are analyzed. Moreover, the impact of digitalization on the steel industry workforce are considered together with the foreseen economic developments.

show abstract

“…ESN's memory feature was suitable for the highly dynamic industrial processes to be modelled, whose states are strongly dependent from previous ones. In addition, good results were obtained by the authors in the forecasting of similar outputs [11][12][13] and ESNs gave better predictions compared to other methods (e.g. Long Short-Term memory) for the modelling of same nature processes [13].…”

Section: Background On Echo-state Neural Network-based Modelsmentioning

confidence: 99%

Echo-state neural networks forecasting steelworks off-gases for their dispatching in CH4 and CH3OH syntheses reactors

Matino¹,

Dettori²,

Colla³

et al. 2021

ESANN 2021 Proceedings

Self Cite

View full text Add to dashboard Cite

In the era of European Green Deal, steelworks are committed to reduce their CO2 emissions by preserving their competitiveness. One of the options to achieve such aim is the valorization of process off-gases. Methane and Methanol production can be obtained by coupling novel reactors with an advanced control system that dispatches these gases after enrichment with green hydrogen. Knowing in advance the gases availability and composition is fundamental. The paper present Echo State Networks based-models that are applied to this aim and achieve adequate forecasting accuracy also in case of highly dynamic processes.

show abstract

Forecasting blast furnace gas production and demand through echo state neural network-based models: Pave the way to off-gas optimized management

Cited by 58 publications

References 20 publications

Renewable Hydrogen Production Processes for the Off-Gas Valorization in Integrated Steelworks through Hydrogen Intensified Methane and Methanol Syntheses

Renewable Hydrogen Production Processes for the Off-Gas Valorization in Integrated Steelworks through Hydrogen Intensified Methane and Methanol Syntheses

The Challenge of Digitalization in the Steel Sector

Echo-state neural networks forecasting steelworks off-gases for their dispatching in CH4 and CH3OH syntheses reactors

Contact Info

Product

Resources

About