This page has only limited features, please log in for full access.

Dr. Stefano Dettori
Scuola Superiore Sant'Anna

Basic Info


Research Keywords & Expertise

0 Machine Learning
0 Model Predictive Control
0 Process Control
0 Control systems
0 Nonlinear Control

Honors and Awards

The user has no records in this section


Career Timeline

The user has no records in this section.


Short Biography

The user biography is not available.
Following
Followers
Co Authors
The list of users this user is following is empty.
Following: 0 users

Feed

Journal article
Published: 02 July 2021 in Energies
Reads 0
Downloads 0

The current flexibility of the energy market requires operating steam turbines that have challenging operation requirements such as variable steam conditions and higher number of startups. This article proposes an advanced control system based on the Nonlinear Model Predictive Control (NMPC) technique, which allows to speed up the start-up of steam turbines and increase the energy produced while maintaining rotor stress as a constraint variable. A soft sensor for the online calculation of rotor stress is presented together with the steam turbine control logic. Then, we present how the computational cost of the controller was contained by reducing the order of the formulation of the optimization problem, adjusting the scheduling of the optimizer routine, and tuning the parameters of the controller itself. The performance of the control system has been compared with respect to the PI Controller architecture fed by the soft sensor results and with standard pre-calculated curves. The control architecture was evaluated in a simulation exploiting actual data from a Concentrated Solar Power Plant. The NMPC technique shows an increase in performance, with respect to the custom PI control application, and encouraging results.

ACS Style

Stefano Dettori; Alessandro Maddaloni; Filippo Galli; Valentina Colla; Federico Bucciarelli; Damaso Checcacci; Annamaria Signorini. Steam Turbine Rotor Stress Control through Nonlinear Model Predictive Control. Energies 2021, 14, 3998 .

AMA Style

Stefano Dettori, Alessandro Maddaloni, Filippo Galli, Valentina Colla, Federico Bucciarelli, Damaso Checcacci, Annamaria Signorini. Steam Turbine Rotor Stress Control through Nonlinear Model Predictive Control. Energies. 2021; 14 (13):3998.

Chicago/Turabian Style

Stefano Dettori; Alessandro Maddaloni; Filippo Galli; Valentina Colla; Federico Bucciarelli; Damaso Checcacci; Annamaria Signorini. 2021. "Steam Turbine Rotor Stress Control through Nonlinear Model Predictive Control." Energies 14, no. 13: 3998.

Journal article
Published: 18 May 2021 in Energies
Reads 0
Downloads 0

The steel industry is among the highest carbon-emitting industrial sectors. Since the steel production process is already exhaustively optimized, alternative routes are sought in order to increase carbon efficiency and reduce these emissions. During steel production, three main carbon-containing off-gases are generated: blast furnace gas, coke oven gas and basic oxygen furnace gas. In the present work, the addition of renewable hydrogen by electrolysis to those steelworks off-gases is studied for the production of methane and methanol. Different case scenarios are investigated using AspenPlusTM flowsheet simulations, which differ on the end-product, the feedstock flowrates and on the production of power. Each case study is evaluated in terms of hydrogen and electrolysis requirements, carbon conversion, hydrogen consumption, and product yields. The findings of this study showed that the electrolysis requirements surpass the energy content of the steelwork’s feedstock. However, for the methanol synthesis cases, substantial improvements can be achieved if recycling a significant amount of the residual hydrogen.

ACS Style

Michael Bampaou; Kyriakos Panopoulos; Panos Seferlis; Spyridon Voutetakis; Ismael Matino; Alice Petrucciani; Antonella Zaccara; Valentina Colla; Stefano Dettori; Teresa Annunziata Branca; Vincenzo Iannino. Integration of Renewable Hydrogen Production in Steelworks Off-Gases for the Synthesis of Methanol and Methane. Energies 2021, 14, 2904 .

AMA Style

Michael Bampaou, Kyriakos Panopoulos, Panos Seferlis, Spyridon Voutetakis, Ismael Matino, Alice Petrucciani, Antonella Zaccara, Valentina Colla, Stefano Dettori, Teresa Annunziata Branca, Vincenzo Iannino. Integration of Renewable Hydrogen Production in Steelworks Off-Gases for the Synthesis of Methanol and Methane. Energies. 2021; 14 (10):2904.

Chicago/Turabian Style

Michael Bampaou; Kyriakos Panopoulos; Panos Seferlis; Spyridon Voutetakis; Ismael Matino; Alice Petrucciani; Antonella Zaccara; Valentina Colla; Stefano Dettori; Teresa Annunziata Branca; Vincenzo Iannino. 2021. "Integration of Renewable Hydrogen Production in Steelworks Off-Gases for the Synthesis of Methanol and Methane." Energies 14, no. 10: 2904.

Journal article
Published: 16 April 2021 in Neural Computing and Applications
Reads 0
Downloads 0

This article presents the application of a recent neural network topology known as the deep echo state network to the prediction and modeling of strongly nonlinear systems typical of the process industry. The article analyzes the results by introducing a comparison with one of the most common and efficient topologies, the long short-term memories, in order to highlight the strengths and weaknesses of a reservoir computing approach compared to one currently considered as a standard of recurrent neural network. As benchmark application, two specific processes common in the integrated steelworks are selected, with the purpose of forecasting the future energy exchanges and transformations. The procedures of training, validation and test are based on data analysis, outlier detection and reconciliation and variable selection starting from real field industrial data. The analysis of results shows the effectiveness of deep echo state networks and their strong forecasting capabilities with respect to standard recurrent methodologies both in terms of training procedures and accuracy.

ACS Style

Stefano Dettori; Ismael Matino; Valentina Colla; Ramon Speets. A Deep Learning-based approach for forecasting off-gas production and consumption in the blast furnace. Neural Computing and Applications 2021, 1 -13.

AMA Style

Stefano Dettori, Ismael Matino, Valentina Colla, Ramon Speets. A Deep Learning-based approach for forecasting off-gas production and consumption in the blast furnace. Neural Computing and Applications. 2021; ():1-13.

Chicago/Turabian Style

Stefano Dettori; Ismael Matino; Valentina Colla; Ramon Speets. 2021. "A Deep Learning-based approach for forecasting off-gas production and consumption in the blast furnace." Neural Computing and Applications , no. : 1-13.

Journal article
Published: 16 April 2021
Reads 0
Downloads 0

This article presents the application of a recent neural network topology known as the deep echo state network to the prediction and modeling of strongly nonlinear systems typical of the process industry. The article analyzes the results by introducing a comparison with one of the most common and efficient topologies, the long short-term memories, in order to highlight the strengths and weaknesses of a reservoir computing approach compared to one currently considered as a standard of recurrent neural network. As benchmark application, two specific processes common in the integrated steelworks are selected, with the purpose of forecasting the future energy exchanges and transformations. The procedures of training, validation and test are based on data analysis, outlier detection and reconciliation and variable selection starting from real field industrial data. The analysis of results shows the effectiveness of deep echo state networks and their strong forecasting capabilities with respect to standard recurrent methodologies both in terms of training procedures and accuracy. The online version contains supplementary material available at 10.1007/s00521-021-05984-x.

ACS Style

Stefano Dettori; Ismael Matino; Valentina Colla; Ramon Speets. A Deep Learning-based approach for forecasting off-gas production and consumption in the blast furnace. 2021, 1 -13.

AMA Style

Stefano Dettori, Ismael Matino, Valentina Colla, Ramon Speets. A Deep Learning-based approach for forecasting off-gas production and consumption in the blast furnace. . 2021; ():1-13.

Chicago/Turabian Style

Stefano Dettori; Ismael Matino; Valentina Colla; Ramon Speets. 2021. "A Deep Learning-based approach for forecasting off-gas production and consumption in the blast furnace." , no. : 1-13.

Conference paper
Published: 05 February 2021 in Advances in Intelligent Systems and Computing
Reads 0
Downloads 0

Within integrated steelworks, several sub-processes produce off-gases, which are suitable for reuse as energy sources for other internal processes as well as for the production of energy. An adequate and optimal distribution of these gases among their users allows valorizing at best their energy content by minimizing the need to both burn them through torches due to storage issues and to acquire natural gas to satisfy the internal energetic demand. To this purpose, the volume and energetic value of produced gases as well as the demands from internal users must be known in advance, in order to implement model-predictive control strategies aimed at satisfying the demands on the short-medium term based on the production scheduling. Such forecasting knowledge also enhances the capability to react to the variability of the process scheduling as well as to other unforeseen events. The paper depicts an application of Machine Learning-based models to forecast off-gases and further energy carriers productions and demands within integrated steelworks. The forecasting models are integrated into a complex hierarchical control strategy aimed at optimizing the distribution of such gases.

ACS Style

Ismael Matino; Stefano Dettori; Angelo Castellano; Ruben Matino; Claudio Mocci; Marco Vannocci; Alessandro Maddaloni; Valentina Colla; Andreas Wolff. Machine Learning-Based Models for Supporting Optimal Exploitation of Process Off-Gases in Integrated Steelworks. Advances in Intelligent Systems and Computing 2021, 104 -118.

AMA Style

Ismael Matino, Stefano Dettori, Angelo Castellano, Ruben Matino, Claudio Mocci, Marco Vannocci, Alessandro Maddaloni, Valentina Colla, Andreas Wolff. Machine Learning-Based Models for Supporting Optimal Exploitation of Process Off-Gases in Integrated Steelworks. Advances in Intelligent Systems and Computing. 2021; ():104-118.

Chicago/Turabian Style

Ismael Matino; Stefano Dettori; Angelo Castellano; Ruben Matino; Claudio Mocci; Marco Vannocci; Alessandro Maddaloni; Valentina Colla; Andreas Wolff. 2021. "Machine Learning-Based Models for Supporting Optimal Exploitation of Process Off-Gases in Integrated Steelworks." Advances in Intelligent Systems and Computing , no. : 104-118.

Journal article
Published: 18 November 2020 in Metals
Reads 0
Downloads 0

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.

ACS Style

Antonella Zaccara; Alice Petrucciani; Ismael Matino; Teresa Annunziata Branca; Stefano Dettori; Vincenzo Iannino; Valentina Colla; Michael Bampaou; Kyriakos Panopoulos. Renewable Hydrogen Production Processes for the Off-Gas Valorization in Integrated Steelworks through Hydrogen Intensified Methane and Methanol Syntheses. Metals 2020, 10, 1 .

AMA Style

Antonella Zaccara, Alice Petrucciani, Ismael Matino, Teresa Annunziata Branca, Stefano Dettori, Vincenzo Iannino, Valentina Colla, Michael Bampaou, Kyriakos Panopoulos. Renewable Hydrogen Production Processes for the Off-Gas Valorization in Integrated Steelworks through Hydrogen Intensified Methane and Methanol Syntheses. Metals. 2020; 10 (11):1.

Chicago/Turabian Style

Antonella Zaccara; Alice Petrucciani; Ismael Matino; Teresa Annunziata Branca; Stefano Dettori; Vincenzo Iannino; Valentina Colla; Michael Bampaou; Kyriakos Panopoulos. 2020. "Renewable Hydrogen Production Processes for the Off-Gas Valorization in Integrated Steelworks through Hydrogen Intensified Methane and Methanol Syntheses." Metals 10, no. 11: 1.

Journal article
Published: 01 February 2019 in Energy Procedia
Reads 0
Downloads 0

The paper proposes a methodology for modeling of energy transformation equipment which are commonly found in integrated steelworks, mainly focusing on steam production in the Basic Oxygen Furnace and auxiliary boilers, the electric power production in off-gas expansion turbines and some relevant steam and electricity consumers. The modeling approach is based on standard neural networks and Echo State Networks (ESN) for forecasting the variables of interest. All the models are intended as processes predictors to be used in a hierarchical control strategy based on multi-period and multi-objective optimization techniques and model predictive control. The overall target is the optimization of the re-use of off-gas produced in integrated steelworks by minimizing costs and maximizing revenues. Training and validation of models have been carried out by exploiting real historical data provided by steelmaking companies and have been successful tested.

ACS Style

Stefano Dettori; Ismael Matino; Valentina Colla; Valentine Weber; Sahar Salame. Neural Network-based modeling methodologies for energy transformation equipment in integrated steelworks processes. Energy Procedia 2019, 158, 4061 -4066.

AMA Style

Stefano Dettori, Ismael Matino, Valentina Colla, Valentine Weber, Sahar Salame. Neural Network-based modeling methodologies for energy transformation equipment in integrated steelworks processes. Energy Procedia. 2019; 158 ():4061-4066.

Chicago/Turabian Style

Stefano Dettori; Ismael Matino; Valentina Colla; Valentine Weber; Sahar Salame. 2019. "Neural Network-based modeling methodologies for energy transformation equipment in integrated steelworks processes." Energy Procedia 158, no. : 4061-4066.

Journal article
Published: 01 February 2019 in Energy Procedia
Reads 0
Downloads 0

The paper proposes a Nonlinear Model Predictive Control strategy for the control of steam turbines rotor thermal stresses, which exploits the approximation of the turbine rotor as an infinite cylinder subjected to external convection. The Nonlinear Model Predictive Control allows optimizing the control strategy in the long term, by significantly reducing the machine start-up time during the power up ramp. This study proposes two different control strategies: the former one is based on the control of the Heat Transfer Coefficient, correlated to the inlet valve stroke. The latter one is based on the control of Heat Transfer Coefficient and the boiler steam temperature reference. Both strategies achieve good results in shortening the start-up time. The overall approach is validated and currently under development on Programmable Logic Controller platforms to the aim of code optimization.

ACS Style

S. Dettori; A. Maddaloni; V. Colla; O. Toscanelli; F. Bucciarelli; A. Signorini; D. Checcacci. Nonlinear Model Predictive Control strategy for steam turbine rotor stress. Energy Procedia 2019, 158, 5653 -5658.

AMA Style

S. Dettori, A. Maddaloni, V. Colla, O. Toscanelli, F. Bucciarelli, A. Signorini, D. Checcacci. Nonlinear Model Predictive Control strategy for steam turbine rotor stress. Energy Procedia. 2019; 158 ():5653-5658.

Chicago/Turabian Style

S. Dettori; A. Maddaloni; V. Colla; O. Toscanelli; F. Bucciarelli; A. Signorini; D. Checcacci. 2019. "Nonlinear Model Predictive Control strategy for steam turbine rotor stress." Energy Procedia 158, no. : 5653-5658.