• Energy Research
• Open Access close
• Restricted close
• Open Source close
• English close
• Applied Energy close

Predicting the temperature, pressure, and permeability at depth is crucial for understanding natural-state geothermal systems. As direct observations of these quantities are limited to well locations, a reliable method-ology that predicts the spatial distribution of the quantities from well observations is required. In this study, we developed a physics-informed neural network (PINN), which constrains predictions to satisfy conservation of mass and energy, for predicting spatial distributions of temperature, pressure, and permeability of natural-state hydrothermal systems. We assessed the characteristics of the proposed method by applying it to 2D synthetic models of geothermal systems. Our results showed that the PINN outperformed the conventional neural network in terms of prediction accuracy. Among the PINN-predicted quantities, the errors in the predicted temperatures in the unexplored regions were significantly reduced. Furthermore, we confirmed that the predictions decreased the loss of the conservation laws. Thus, our PINN approach guarantees physical plausibility, which has been impossible using existing machine learning approaches. As permeability investigations in geothermal wells are often limited, we also demonstrate that the resistivity model obtained using the magnetotelluric method is effective in supplementing permeability observations and improving its prediction accuracy. This study demonstrated for the first time the usefulness of the PINN to a geothermal energy problem.

Predicting the temperature, pressure, and permeability at depth is crucial for understanding natural-state geothermal systems. As direct observations of these quantities are limited to well locations, a reliable method-ology that predicts the spatial distribution of the quantities from well observations is required. In this study, we developed a physics-informed neural network (PINN), which constrains predictions to satisfy conservation of mass and energy, for predicting spatial distributions of temperature, pressure, and permeability of natural-state hydrothermal systems. We assessed the characteristics of the proposed method by applying it to 2D synthetic models of geothermal systems. Our results showed that the PINN outperformed the conventional neural network in terms of prediction accuracy. Among the PINN-predicted quantities, the errors in the predicted temperatures in the unexplored regions were significantly reduced. Furthermore, we confirmed that the predictions decreased the loss of the conservation laws. Thus, our PINN approach guarantees physical plausibility, which has been impossible using existing machine learning approaches. As permeability investigations in geothermal wells are often limited, we also demonstrate that the resistivity model obtained using the magnetotelluric method is effective in supplementing permeability observations and improving its prediction accuracy. This study demonstrated for the first time the usefulness of the PINN to a geothermal energy problem.

The possibility of electric vehicles to technically replace internal combustion engine vehicles and to deliver economic benefits mainly depends on the battery and the charging infrastructure as well as on annual mileage (utilizing the lower variable costs of electric vehicles). Current studies on electric vehicles’ total cost of ownership often neglect two important factors that influence the investment decision and operational costs: firstly, the trade-off between battery and charging capacity; secondly the uncertainty in energy consumption. This paper proposes a two-stage stochastic program that minimizes the total cost of ownership of a commercial electric vehicle under uncertain energy consumption and available charging times induced by mobility patterns and outside temperature. The optimization program is solved by sample average approximation based on mobility and temperature scenarios. A hidden Markov model is introduced to predict mobility demand scenarios. Three scenario reduction heuristics are applied to reduce computational effort while keeping a high-quality approximation. The proposed framework is tested in a case study of the home nursing service. The results show the large influence of the uncertain mobility patterns on the optimal solution. In the case study, the total cost of ownership can be reduced by up to 3.9% by including the trade-off between battery and charging capacity. The introduction of variable energy prices can lower energy costs by 31.6% but does not influence the investment decision in this case study. Overall, this study provides valuable insights for real applications to determine the techno-economic optimal electric vehicle and charging infrastructure configuration.

The possibility of electric vehicles to technically replace internal combustion engine vehicles and to deliver economic benefits mainly depends on the battery and the charging infrastructure as well as on annual mileage (utilizing the lower variable costs of electric vehicles). Current studies on electric vehicles’ total cost of ownership often neglect two important factors that influence the investment decision and operational costs: firstly, the trade-off between battery and charging capacity; secondly the uncertainty in energy consumption. This paper proposes a two-stage stochastic program that minimizes the total cost of ownership of a commercial electric vehicle under uncertain energy consumption and available charging times induced by mobility patterns and outside temperature. The optimization program is solved by sample average approximation based on mobility and temperature scenarios. A hidden Markov model is introduced to predict mobility demand scenarios. Three scenario reduction heuristics are applied to reduce computational effort while keeping a high-quality approximation. The proposed framework is tested in a case study of the home nursing service. The results show the large influence of the uncertain mobility patterns on the optimal solution. In the case study, the total cost of ownership can be reduced by up to 3.9% by including the trade-off between battery and charging capacity. The introduction of variable energy prices can lower energy costs by 31.6% but does not influence the investment decision in this case study. Overall, this study provides valuable insights for real applications to determine the techno-economic optimal electric vehicle and charging infrastructure configuration.

Increasing energy demand and its correlation with global warming underscore the urgency of exploring renewable energy sources, particularly solar power. This requirement is even more pronounced for mid- and high-rise buildings characterized by substantial energy consumption, necessitating the identification of optimal locations for solar panel installations. The purpose of this study is to develop an autonomously adjusted solar photovoltaic (PV) system for integration with solar shading louvers (adjustable PV louver system). Because the system can automatically adjust the angle of the solar PV panels by tracking the movement of the sun, electricity generation can be enhanced. To evaluate the performance of the adjustable PV louver system, we measured the amount of electricity generation with prototype model and developed a numerical analysis model for power generation calculations and a heating and cooling load calculation model. The major obtained findings are as follows: (1) Compared with a stationary PV louver system with fixed angles, actual measurement result shows that the adjustable vertical PV louver system exhibited a notable 7.3% improvement in daily electricity generation, whereas the adjustable horizontal PV louver system demonstrated an even more significant increase of 9.3%. (2) A parametric study involving the number of louvers was conducted to evaluate the influence of the shadows on each louver. The results showed that despite the presence of shadows between louvers, maintaining the number of louvers required to cover the window width resulted in improved electricity generation. (3) Heating and cooling load calculation for an office building in Japan shows that installing the adjustable horizontal PV louver system on window surfaces consumes the least amount of electricity.

Increasing energy demand and its correlation with global warming underscore the urgency of exploring renewable energy sources, particularly solar power. This requirement is even more pronounced for mid- and high-rise buildings characterized by substantial energy consumption, necessitating the identification of optimal locations for solar panel installations. The purpose of this study is to develop an autonomously adjusted solar photovoltaic (PV) system for integration with solar shading louvers (adjustable PV louver system). Because the system can automatically adjust the angle of the solar PV panels by tracking the movement of the sun, electricity generation can be enhanced. To evaluate the performance of the adjustable PV louver system, we measured the amount of electricity generation with prototype model and developed a numerical analysis model for power generation calculations and a heating and cooling load calculation model. The major obtained findings are as follows: (1) Compared with a stationary PV louver system with fixed angles, actual measurement result shows that the adjustable vertical PV louver system exhibited a notable 7.3% improvement in daily electricity generation, whereas the adjustable horizontal PV louver system demonstrated an even more significant increase of 9.3%. (2) A parametric study involving the number of louvers was conducted to evaluate the influence of the shadows on each louver. The results showed that despite the presence of shadows between louvers, maintaining the number of louvers required to cover the window width resulted in improved electricity generation. (3) Heating and cooling load calculation for an office building in Japan shows that installing the adjustable horizontal PV louver system on window surfaces consumes the least amount of electricity.

The recent trend to design more efficient and versatile ships has increased the variety in hybrid propulsion and power supply architectures. In order to improve performance with these architectures, intelligent control strategies are required, while mostly conventional control strategies are applied currently. First, this paper classifies ship propulsion topologies into mechanical, electrical and hybrid propulsion, and power supply topologies into combustion, electrochemical, stored and hybrid power supply. Then, we review developments in propulsion and power supply systems and their control strategies, to subsequently discuss opportunities and challenges for these systems and the associated control. We conclude that hybrid architectures with advanced control strategies can reduce fuel consumption and emissions up to 10–35%, while improving noise, maintainability, manoeuvrability and comfort. Subsequently, the paper summarises the benefits and drawbacks, and trends in application of propulsion and power supply technologies, and it reviews the applicability and benefits of promising advanced control strategies. Finally, the paper analyses which control strategies can improve performance of hybrid systems for future smart and autonomous ships and concludes that a combination of torque, angle of attack, and Model Predictive Control with dynamic settings could improve performance of future smart and more autonomous ships. Ship Design, Production and Operations Transport Engineering and Logistics Marine and Transport Technology