• Energy Research

Due their high efficiency, even at partial load and on small size units, fuel cell stacks are suitable for distributed power generation networks,. However, power drawn by single phase grids contains a low frequency oscillation that generates a large ripple on the stack output current. Such a current ripple is able to shorten the fuel cell lifetime, to worsen the stack efficiency and to reduce the available peak power. Therefore, passive and active current ripple reduction techniques have been proposed in the past exploiting bulky electrolytic capacitor banks or expensive active filters. In the proposed paper a new approach is suggested where an active filter is integrated into the converter, without introducing extra power devices. According to the proposed approach the size of the electrolytic capacitor bank can be largely reduced, thus improving the reliability, while lowering costs and size.

Due their high efficiency, even at partial load and on small size units, fuel cell stacks are suitable for distributed power generation networks,. However, power drawn by single phase grids contains a low frequency oscillation that generates a large ripple on the stack output current. Such a current ripple is able to shorten the fuel cell lifetime, to worsen the stack efficiency and to reduce the available peak power. Therefore, passive and active current ripple reduction techniques have been proposed in the past exploiting bulky electrolytic capacitor banks or expensive active filters. In the proposed paper a new approach is suggested where an active filter is integrated into the converter, without introducing extra power devices. According to the proposed approach the size of the electrolytic capacitor bank can be largely reduced, thus improving the reliability, while lowering costs and size.

Solid oxide fuel cells (SOFC) could facilitate the green energy transition as they can produce high-temperature heat and electricity while emitting only water when supplied with hydrogen. Additionally, when operated with natural gas, these systems demonstrate higher thermoelectric efficiency compared to traditional microturbines or alternative engines. Within this context, although digitalisation has facilitated the acquisition of extensive data for precise modelling and optimal management of fuel cells, there remains a significant gap in developing digital twins that effectively achieve these objectives in real-world applications. Existing research predominantly focuses on the use of machine learning algorithms to predict the degradation of fuel cell components and to optimally design and theoretically operate these systems. In light of this, the presented study focuses on developing digital twin-oriented models that predict the efficiency of a commercial gas-fed solid oxide fuel cell under various operational conditions. This study uses data gathered from an experimental setup, which was employed to train various machine learning models, including artificial neural networks, random forests, and gradient boosting regressors. Preliminary findings demonstrate that the random forest model excels, achieving an R2 score exceeding 0.98 and a mean squared error of 0.14 in estimating electric efficiency. These outcomes could validate the potential of machine learning algorithms to support fuel cell integration into energy management systems capable of improving efficiency, pushing the transition towards sustainable energy solutions.

Solid oxide fuel cells (SOFC) could facilitate the green energy transition as they can produce high-temperature heat and electricity while emitting only water when supplied with hydrogen. Additionally, when operated with natural gas, these systems demonstrate higher thermoelectric efficiency compared to traditional microturbines or alternative engines. Within this context, although digitalisation has facilitated the acquisition of extensive data for precise modelling and optimal management of fuel cells, there remains a significant gap in developing digital twins that effectively achieve these objectives in real-world applications. Existing research predominantly focuses on the use of machine learning algorithms to predict the degradation of fuel cell components and to optimally design and theoretically operate these systems. In light of this, the presented study focuses on developing digital twin-oriented models that predict the efficiency of a commercial gas-fed solid oxide fuel cell under various operational conditions. This study uses data gathered from an experimental setup, which was employed to train various machine learning models, including artificial neural networks, random forests, and gradient boosting regressors. Preliminary findings demonstrate that the random forest model excels, achieving an R2 score exceeding 0.98 and a mean squared error of 0.14 in estimating electric efficiency. These outcomes could validate the potential of machine learning algorithms to support fuel cell integration into energy management systems capable of improving efficiency, pushing the transition towards sustainable energy solutions.

Fuel cell systems, especially those fed with hydrogen, have reached considerable performance targets in laboratory conditions with constant loads and conservative environmental conditions. However, a check of the potential of such systems in real conditions is necessary, particularly in terms of varying electrical and thermal loads and of more severe climatic conditions. To determine the state of the art of such technology and to develop systems capable of supporting future national energy scenarios within the PNR-FISR project, "Polymeric electrolytes and ceramic fuel cells: demonstration of systems and development of new materials," the development of fuel cell systems ranging from 1 to 5kW of power and based on either solid polymer (PEMFC) or solid oxide (SOFC) technology are in progress. In this paper, the demonstration of a pre-commercial PEMFC system fed with hydrogen and developed in cooperation with NUVERA is described. The system has been developed in order to determine its limits and capacity in relation to start-up time, response time, consumption, efficiency, reliability, etc. It has currently reached 1000 working hours of continuous performance with variable loads that simulate those of a typical residential dwelling.

Fuel cell systems, especially those fed with hydrogen, have reached considerable performance targets in laboratory conditions with constant loads and conservative environmental conditions. However, a check of the potential of such systems in real conditions is necessary, particularly in terms of varying electrical and thermal loads and of more severe climatic conditions. To determine the state of the art of such technology and to develop systems capable of supporting future national energy scenarios within the PNR-FISR project, "Polymeric electrolytes and ceramic fuel cells: demonstration of systems and development of new materials," the development of fuel cell systems ranging from 1 to 5kW of power and based on either solid polymer (PEMFC) or solid oxide (SOFC) technology are in progress. In this paper, the demonstration of a pre-commercial PEMFC system fed with hydrogen and developed in cooperation with NUVERA is described. The system has been developed in order to determine its limits and capacity in relation to start-up time, response time, consumption, efficiency, reliability, etc. It has currently reached 1000 working hours of continuous performance with variable loads that simulate those of a typical residential dwelling.

Climate Change is a priority, due to the large variety of implications and importance that it may cause in the next decades. In this context, the building sector is a significant contributor to greenhouse gas emissions. For this reason, buildings should be designed in such a way that they are responsible for fewer GHG emissions.