Examensarbeten för masterexamen
Länka till denna samling:
Browse
Senast publicerade
Visar 1 - 5 av 1408
- PostDeep learning methods for naturalness evaluation of forests based on canopy height model(2024) Bauner, Andreas; Chalmers tekniska högskola / Institutionen för mekanik och maritima vetenskaper; Chalmers University of Technology / Department of Mechanics and Maritime Sciences; Della Vedova, Marco L; Della Vedova, Marco LForest evaluation has historically been done through field surveys by experts from national forest agencies or from forestry companies. This is costly manual labor that consumes a lot of time. A solution could be to use remote sensing ecological data and automate the naturalness evaluation of forests with the use of computers. The aim of this thesis is to develop a machine learning model that could help automate naturalness evaluation of forests. The remote sensing data is in the form of a Canopy Height Model (CHM), that is height of trees obtained from airborne laser-scanning. Ground truth data for forest naturalness is given in the form of annotated, georeferenced polygons. The study area is limited to a 50×50 km2 area north-east of the city of Jönköping in Sweden. After applying different processing steps on the data, it is then used for training a convolutional neural network, based on U-Nets, on this semantic segmentation task. The evaluation of the model shows good results, achieving an accuracy of 94.1% on the test set. This performance is competitive with currently used models for related tasks and shows the feasibility of using machine learning in the relatively new field of automated naturalness evaluation of forests.
- PostOptimization of Server Room HVAC Systems for Energy Efficiency. Leveraging CFD and AI-Driven Techniques(2024) Carlsson, John; Chalmers tekniska högskola / Institutionen för mekanik och maritima vetenskaper; Chalmers University of Technology / Department of Mechanics and Maritime Sciences; Nilsson, Håkan; Löseth, OlaThe increasing demand for energy efficiency in server rooms and Heating, Ventilation & Air Conditioning (HVAC) systems necessitates advanced optimization techniques to reduce energy consumption while maintaining thermal stability. This thesis focuses on holistic energy optimization of a server room’s HVAC system by optimizing the room’s geometry and HVAC parameters using computational methods such as CFD and machine learning models, including an Artificial Neural Network (ANN). The study employs a range of meta heuristic optimization algorithms, including Genetic Algorithm (GA), Simulated Annealing (SA), Particle Swarm Optimization (PSO), and Differential Evolution (DE), to identify the best configuration for reducing energy usage. The goal of the optimization process is to maximize the inflow air temperature and minimize the mass flow while ensuring that the average room temperature does not exceed 28°C. The project was conducted at a worst case scenario, when the outside air temperature is 30 degrees Celsius and the server room is running on maximum capacity, generating waste heat of 72kW. A Latin Hypercube Sampling (LHS) method was employed to capture the underlying differential equations behavior throughout the high-dimensional parameter space, and a neural network was trained on this sample data to predict room temperature. Particle Swarm Optimization was used in order to find the optimal parameters for minimal energy consumption. The results demonstrate that the proposed optimization techniques can significantly enhance the energy efficiency of HVAC systems in server rooms at a worse case scenario. By adjusting the inflow temperature and air mass flow, a reduction in cooling energy consumption of up to 22.69% was achieved. Future work could include hybrid optimization approaches to further improve system performance and the application of multi-objective optimization to accommodate varying operational phases.
- PostAerodynamics investigations and optimization of a simplified pick-up truck with wind tunnel and CFD testing(2024) Yathiraj, Karthik; Chaithanya, Pavan; Chalmers tekniska högskola / Institutionen för mekanik och maritima vetenskaper; Chalmers University of Technology / Department of Mechanics and Maritime Sciences; Vdovin, Alexey; Vdovin, AlexeyThis master’s thesis presents a comprehensive study on the aerodynamics and optimization of a simplified generic pick-up truck model through combined wind tunnel testing and computational fluid dynamics (CFD) simulations in StarCCM+. The primary objective is to understand and investigate the aerodynamic behavior of the generic pickup truck and design new attachments for the pickup truck on the trailer. Based on existing knowledge, design optimization techniques were used to find design changes that could reduce aerodynamic drag. A flat underbody, a closed grill gap, and various rear attachments were among the changes made to the truck’s shape. A comprehensive study and cross-validation of the suggested aerodynamic improvements were made possible by the combination of wind tunnel testing and CFD. The ANSA software was used to optimize the CAD model. 3D printing was later used to create a 1/10 scaled-down model of the generic pickup truck, along with three distinct attachments called Flat back, Hatch back, and Fastback. Later tested the 3D printed model in Chalmers University of Technology’s wind tunnel in Sweden. Drag forces were captured with the aid of wind tunnel experiments. These experimental findings served as a standard by which to validate the CFD models. The airflow surrounding the vehicle was then simulated using extensive CFD analyses using the StarCCM+ software. The findings presented in this paper are the outcome of research and comprehension of the vehicle’s aerodynamic behavior. They also show enhancements in the pickup truck’s aerodynamic performance, with the quick back attachment lowering the drag coefficient. In addition to highlighting the potential for significant fuel and pollution reductions in pick-up trucks through aerodynamic optimization, this work shows how well experimental and computational methodologies may be used for aerodynamic investigations.
- PostAssessing the influence of show, don’t tell principle on external human-machine interfaces across cultures(2024) Saha, Shouvanik; Chalmers tekniska högskola / Institutionen för mekanik och maritima vetenskaper; Chalmers University of Technology / Department of Mechanics and Maritime Sciences; Benderius, Ola; Benderius, OlaTogether with the shift towards green renewable energy sources, the automotive industry is currently witnessing a rapid advancement in the context of autonomous vehicle technology. In this setting, the way in which the autonomous vehicle interacts with the vulnerable road users will be indispensable both in terms of safety and acceptance. Therefore, understanding the societal perceptions and cultural influences on the external human-machine interfaces (eHMIs) has become significant. This research investigates the intersection of social constructivism and the show, don’t tell principle within the context of eHMIs for autonomous vehicles. Grounded in the hypothesis of social constructivism and technological insights from the show, don’t tell principle, the study aims to analyse the alignment between the current theoretical frameworks and the practical design solutions. Specifically, it explores how cultural factors impact the acceptance and effectiveness of eHMIs among pedestrians. In order to achieve autonomous driving with minimal or zero human intervention, seamless integration of these vehicles into complex urban traffic is required. This research suggests that the development of culturally sensitive design solutions may facilitate the harmonious co-existence of autonomous vehicles and vulnerable road users in urban landscapes.
- PostA Method for Determining Feasibility of Electrification of Small Fishing Vessels: Developed Using Operational Data from Two Fishing Vessels in Kosterhavet National Park(2024) Barman, Aditya; Sörfeldt, Arvid; Chalmers tekniska högskola / Institutionen för mekanik och maritima vetenskaper; Chalmers University of Technology / Department of Mechanics and Maritime Sciences; Schreuder, Martin; Schreuder, Martin; Olsson, Fredrik; Sanchez-Heres, LuisAll European industries are facing a big shift away from their dependency on fossil fuels as a result of the European Green Deal. Currently, there is no clear plan available for small fishing vessels to make that shift. The purpose of this thesis was to develop a simple and intuitive method for stakeholders to evaluate the feasibility of electrifying small fishing vessels. It was developed using mostly publicly available operational data of two fishing vessels, combined with a regulatory, environmental, and economic analysis of the two vessels. The results of the analysis where compiled into a method implemented as an excel sheet. The resulting method is applicable to most small Swedish fishing vessels. Applying the method to the two case vessels, it was found that the technical and environmental aspects of feasibility are straight forward to evaluate and the chance of electrification being feasible is good. However, the regulatory and economic aspects are less straight forward and need more thought and effort put in by the user. Furthermore, it was found that being able to use grants from Klimatklivet to electrify small fishing vessels is unlikely. This is because the investment tends to become profitable before the environmental performance is good enough. Finally, it was concluded that electrification will play an important role in the transition away from the use of traditional fossil fuels in the fishing fleet.