Chalmers Open Digital Repository

Välkommen till Chalmers öppna digitala arkiv!

Här hittar du:

  • Studentarbeten utgivna på lärosätet, såväl kandidatarbeten som examensarbeten på grund- och masternivå
  • Digitala specialsamlingar, som t ex Chalmers modellkammare
  • Utvalda projektrapporter
 

Enheter i Chalmers ODR

Välj en enhet för att se alla samlingar.

Senast inlagda

Post
Energy consumption prediction for electric buses using machine learning
(2024) Wise, Antonia; Chalmers tekniska högskola / Institutionen för arkitektur och samhällsbyggnadsteknik (ACE); Chalmers tekniska högskola / Institutionen för arkitektur och samhällsbyggnadsteknik (ACE); Gao, Kun; Gao, Kun
With the increased adoption of electric buses, understanding their energy consumption (EC) has become crucial. For stakeholders such as city planners and bus company owners, having accurate predictions of energy consumption is essential for effective planning and resource allocation. Thus, identifying the relevant data to be collected for accurate predictions is of high importance. Machine learning models have emerged as the most promising tools for predicting energy consumption, offering the precision and reliability needed by stakeholders. Hence, this report aims to forecast energy consumption in electric buses by finding the important features in energy consumption and then exploring a suitable machine learning technique for the given data. Additionally, the report compares the selected model of Multilayered Perceptron Nueral Network (MLPNN) with two other models and assesses the impact of temporal factors on energy consumption predictions. To achieve this purpose, first, feature selection is conducted using correlation analysis and multicollinearity checks via the Variance Inflation Factor (VIF). The base MLPNN model is constructed using the Keras library in Python, with hyperparameter optimisation performed using GridSearch from the sklearn library. Afterward, the performance of the MLPNN model is compared to that of two other models: Random Forest (RF) and Extreme Gradient Boosting (XGB), using standard metrics such as Mean Square Error (MSE) and Mean Absolute Error (MAE). Feature importance is evaluated for each model, with the MLPNN model assessed using SHapley Additive exPlanations (SHAP). Temporal effects on features are also analysed. The features deployed in the model are: ’total mileage’, ’speed’, ’AC switch’, ’outside temperature’, ’inside temperature’, ’run mileage’, ’run duration’, ’bus ID’ and ’time category’. The optimal hyperparameters for the MLPNN model are: batch size of 20, 100 epochs, Stochastic Gradient Descent (SGD) optimizer, Rectified Linear Unit (ReLU) activation function, learning rate of 0.01, 2 hidden layers, 32 neurons per layer, and no regularisation. The evaluation shows that the MLPNN model, using the selected features and optimised hyperparameters, does not outperform the RF and XGB models in terms of MAE and MSE. Feature importance analysis reveals that while MLPNN provides stable importance measures, RF and XGB models are dominated by a single feature: a run mileage (the Euclidean distance between the origin and destination of trips) of over 50%. And secondly, run duration with 20%. SHAP analysis suggests that Run duration and run mileage are most significant for MLPNN as well. When examining the temporal impact on features, no features are impacted by time, contrary to initial expectations that speed would show a substantial temporal effect. The study concludes that the MLPNN model, as constructed, is not significantly better than simpler models in predicting the energy consumption of electric buses for the given dataset. However, there is potential for improvement with additional features or more training data. Future research should explore the inclusion of other relevant features and larger datasets to enhance model performance.
Post
Towards Benchmarking Time Series Analysis with Process-Based Groundwater Models. The Case of Hydrogeological Impacts of Tunnel Construction
(2024) Lilja, Erik; Zander, Zackarias; Chalmers tekniska högskola / Institutionen för arkitektur och samhällsbyggnadsteknik (ACE); Chalmers tekniska högskola / Institutionen för arkitektur och samhällsbyggnadsteknik (ACE); Rosén, Lars; Haaf, Ezra
This thesis evaluates time series modelling for investigating groundwater impacts due to tunnelling in an urban environment based on a process-based, benchmark groundwater model. The Haga site in Gothenburg, Sweden, as part of the Västlänken infrastructure project was used as case study area. Utilizing datasets from various sources, including climate data from SMHI, head observations from the Haga site, and MODFLOW simulations. The study employs MODFLOW simulations and time series analysis to simulate and evaluate GW dynamics. Through Python-based transfer function noise modelling (TFN) using the Pastas package, the study constructs time series models to assess potential tunnel leakage and its impact on GW levels. The thesis emphasizes the importance of accurate data collection and precise modelling techniques to correctly calibrate the model to show the effects on GW systems. The calibration of the MODFLOW model showed good correlation with observed groundwater data, but urban complexities and model limitations caused discrepancies. Refinements, such as improved calibration techniques and improving the representation of groundwater recharge, could enhance model accuracy. The TFN models demonstrated strong performance, especially with added stress data of tunnel leakage. This indicates that the ability of TFN models to investigate groundwater impacts can be benchmarked with a groundwater flow model. However, this study also highlighted challenges due to data scarcity, leading to mismatches between groundwater observations and simulations with the benchmark model, which in future studies could be addressed with more advanced calibration and integration techniques. Future research should focus on refining these models and investigating the skill of TFN models when more groundwater impacts are present.
Post
Improving traffic safety for pedestrians and cyclists at signalized intersections: A study of the traffic signal system in Gothenburg
(2024) Daebes, Abrar; Ly , Terrie; Chalmers tekniska högskola / Institutionen för arkitektur och samhällsbyggnadsteknik (ACE); Chalmers tekniska högskola / Institutionen för arkitektur och samhällsbyggnadsteknik (ACE); Wu, Jiaming; Wu, Jiaming
It is more important than ever to work towards a sustainable society. The transportation sector has a big potential to contribute to a greener environment. Transport modes such as walking and cycling have been promoted as sustainable options for transportation and have become a challenge for many cities to increase their use. One of the cities is Gothenburg. Gothenburg has adopted many policies and programs to achieve a more accessible city for pedestrians and cyclists. This master’s thesis studies how the current traffic system relating to traffic signals works in Gothenburg and identifies traffic safety problems for vulnerable road users at signalized intersections. The result obtained from this master’s thesis shows a need for a more effective technological solution for the traffic signal system. There are some inconsistencies between the goals stated in supporting documents and implementations. The guidelines need to be clearer and more consistent to avoid conflicting interpretations. Much information is not up to date, such as information on the LHOVRA strategy. Therefore, the current documents and implementations need to be reviewed and updated regularly based on feedback and results. Additionally, this study suggests speed limit measures, clearer road markings, and leaning rails for cyclists to improve traffic safety for pedestrians and cyclists. Further research on different detection methods is recommended for continuing the work on improving traffic safety in Gothenburg.
Post
Bus Priority Signal Design and Control at Unconventional Intersections: A Simulation-Based Study in Jönköping
(2024) Alshibly, Hayder; Mezher, Mohammad; Chalmers tekniska högskola / Institutionen för arkitektur och samhällsbyggnadsteknik (ACE); Chalmers tekniska högskola / Institutionen för arkitektur och samhällsbyggnadsteknik (ACE); Wu, Jiaming; Wu, Jiaming
This thesis evaluates the efficacy of traffic management strategies at the Museirondellen and Södra Strandgatan intersections in Jönköping, Sweden, emphasizing bus prioritization and geometric design modifications. Due to their significant traffic volumes and complex designs, these intersections pose key challenges in terms of congestion and safety. Advanced traffic simulation tools are employed to assess current conditions and to explore the impacts of proposed geometric changes under various traffic scenarios, including increases of 10%, 15%, and 20% in traffic volumes. The study incorporates a survey of local drivers to gather firsthand insights into the current traffic issues and perceptions of the proposed changes, complemented by detailed geographical data and signal timing information from local databases. A new intersection design was proposed and tested through simulations, demonstrating its potential to alleviate congestion and enhance public transport efficiency. The research aims to analyze existing traffic inefficiencies, evaluate the effectiveness of bus prioritization, and assess the new geometric design's impact on traffic flow and safety. The findings are intended to provide evidence-based recommendations that could influence urban planning and policy-making in Jönköping and other cities with similar challenges. The significance of this study extends to its approach to integrating bus traffic within urban intersections and optimizing intersection geometries to foster sustainable traffic systems. Expected outcomes include improved urban mobility, enhanced road safety, and actionable insights for future enhancements in traffic management in urban settings.
Post
Can Bus On-demand be Attractive in Suburban Areas: A Case Study in Gothenburg
(2024) Smilevska , Natalie; Wallin, Vera; Chalmers tekniska högskola / Institutionen för arkitektur och samhällsbyggnadsteknik (ACE); Chalmers tekniska högskola / Institutionen för arkitektur och samhällsbyggnadsteknik (ACE); Gao, Kun; Gao, Kun
This master thesis has investigated in how to reduce the use of private cars to travel more sustainably during everyday traveling. The study has focused on bus on demand services to see if it can be a suitable substitute for private cars in suburban areas of Gothenburg. Compared to a normal bus, a bus on-demand is a minibus that can pick up passengers at either a bus stop or a virtual bus stop close to the passenger’s home. Bus on-demand costs the same as a normal bus ticket and ensures that passengers in the same area are picked up with the same minibus. The master thesis has investigated the attitude towards bus on-demand, travel mode choice behavior, and the potential for using bus on-demand in Gothenburg’s suburban areas. This has been done by creating a survey and sending it out to various respondents. In the survey, respondents had to answer which mode of transport they had chosen where time and cost differed. There were four different travel modes, bus on-demand, public transport, shared bicycle/e-scooter, and private car with two different weather scenarios. The results of the survey were applied in Python to obtain coefficients which were then used in probability calculations. The results indicated that individuals are more willing to choose a private car over bus on-demand. This preference can be attributed to the perceived cost-effectiveness and time efficiency of cars. Additionally, respondents’ attitude towards adopting a new travel mode and their existing travel habits significantly influenced their preferences. Several other factors also contributed to this trend. However, bus on-demand have the potential to transform public transportation by providing enhanced flexibility, efficiency, accessibility, and sustainability. Implementation of bus on-demand services is expected to decrease the number of cars in urban areas. Thereby reducing carbon dioxide emissions and contributing to the development of more sustainable urban environments for future generations.