Energy efficiency in industrial facilities - Improvements on energy transformation and data analysis

During these years of my Ph.D. studies the main aim of the research work was to improve the efficiency on energy generation into industrial facilities. Novelties are proposed both on the devices used for energy generation and on energy consumption data analytics. In the first part of the thesis, Solid Oxide Fuel Cell (SOFC) and Reversible Solid Oxide Cell (RSOC) are proposed: these technologies have many advantages such as high efficiency on energy generation, heat available at high temperature, and modularity. A new heat recovery for a modular micro-cogeneration system based on SOFC is presented with the main goal of improving the efficiency of an air source heat pump with unused heat of fuel cell exhausted gases. The novelty of the system proposed is that exhaust gases after the fuel cell are firstly used to heat water and/or used to produce steam, then they are mixed with the external air to feed the evaporator of the heat pump with the aim of increasing energy efficiency of the latter. This system configuration decreases the possibility of freezing of the evaporator as well, which is one of the drawbacks for air source heat pump in climates where temperature close to 0 °C and high humidity could occur. Results show that the performance of the air source heat pump increases considerably during cold season for climates with high relative humidity and for users with high electric power demand. As previously cited, not only SOFC but also RSOC are deeply analysed in the thesis to define innovative energy generation system with the possibility of varying H/P ratio to match energy generation and demand in order to avoid mismatching and, consequently, integration system with a lower system. The aim is to define a modular system where each RSOC module can be switched between energy generation mode (fuel consumption to produce electricity and heat) and energy consumption (electricity and heat are consumed to produce hydrogen, working as Solid Oxide Electrolysis Cells) to vary overall H/P of the overall system. Hydrogen is a sub-product of the system and can be used for many purposes such as fuel and/or for transport sector. Then a re-vamping of the energy generation system of a paper mill by means of RSOCS is proposed and analysed: a real industrial facility, based in Italy with a production capacity of 60000 t/y of paper, is used as case study. Even if the complexity of the system increases, results show that saving between 2% and 6% occurs. Hydrogen generation is assessed, comparing the RSOC integrated system with PEM electrolysis, in terms of both primary energy and economics. Results exhibit significant primary energy and good economic performance on hydrogen production with the novel system proposed. In the thesis novelties are proposed not only on energy system “hardware” (component for energy generation) but also on “software”. In the second part of the thesis, artificial intelligence and machine learning methods are analysed to perform analytics on energy consumption data and consequently to improve performances on energy generation and operation strategy. A study on how cluster analysis could be applied to analyse energy demand data is depicted. The aim of the method is to design cogeneration systems that suit more efficiently energy demand profiles, choosing the correct type of cogeneration technology, operation strategy and, if they are necessary, energy storages. A case study of a wood industry that requires low temperature heat to dry wood into steam-powered kilns that already uses cogeneration is proposed to apply the methodology in order to design and measure improvements. An alternative cogeneration system is designed and proposed, thermodynamics benchmarks are defined to evaluate differences between as-is and alternative scenarios. Results show that the proposed innovative method allows to choose a more suitable cogeneration technology compared to the adopted one, giving suggestions on the operation strategy in order to decrease energy losses and, consequently, primary energy consumption. Finally, clustering is suggested for short-term forecasting of energy demand in industrial facilities. A model based on clustering and kNN is proposed to find similar pattern of consumption, to identify average consumption profiles, and then to use them to forecast consumption data. Novelties on model parameters definition such as data normalisation and clustering hyperparameters are presented to improve its accuracy. The model is then applied to the energy dataset of the wood industry previously cited. Analysis on the parameters and the results of the model are performed, showing a forecast of electricity demand with an error of 3%.