| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

Search the digital library catalog Help

Query: search in
search in
search in
search in
* old and bologna study programme


1 - 10 / 22
First pagePrevious page123Next pageLast page
1D battery electric vehicle thermal management system calibration and simulation based on measurements : magistrsko delo
Manja Umbreht, 2024, master's thesis

Abstract: Electric vehicles are developing at an increased rate due to electrification trends and are trying to achieve the comfort level of existing vehicles with internal combustion engines. In this thesis, we considered a battery electric vehicle, with which measurements were carried out. We created a complete vehicle model in GT Suite software based on available measurements and vehicle data. The model was used to simulate measured test cases. We described the calibration procedure of standalone models and the assembly of a complete thermal model of the entire vehicle. At the end we compared three simulated test cases with vehicle measurements. We concluded that the developed vehicle simulation model behavior fits well to the measured vehicle.
Keywords: 1D CFD, VTMS, energy consumption, measurements, battery electric vehicle
Published in DKUM: 22.04.2024; Views: 124; Downloads: 0
.pdf Full text (6,01 MB)

A Survey on the State-of-the-Art and Future Trends of Multilevel Inverters in BEVs
Alenka Hren, Mitja Truntič, Franc Mihalič, 2023, review article

Abstract: All electric vehicles are the only way to decarbonize transport quickly and substantially. Although multilevel inverters have already been used in some transportation modes, they are rarely used in road transportation, especially in light-duty passenger BEVs. With the transition to a high 800-V DC link to extend the driving range and enable extreme fast charging, the possibility of using multilevel inverters in commercial light-duty passenger BEVs becomes feasible. Higher efficiency, higher power density, better waveform quality, lower switching frequency, the possibility of using low-rated switches, and inherent fault tolerance are known advantages of multilevel inverters that make them an efficient option for replacing 2-level inverters in high DC link passenger BEVs. This paper discusses high DC link voltage benefits in light-duty passenger BEVs, presents the state-of-the-art of different conventional multilevel inverter topologies used in BEVs, and compares them with conventional 2-level inverters from different aspects and limitations. Based on commercial upper-class passengers’ BEV data and a review of multilevel inverters on the market, future trends and possible research areas are identified.
Keywords: multilevel inverters, MLI, electric vehicle, EV, passengers’ battery electric vehicle, BEV, extreme fast charging, XFC, higher voltage batteries, WBG semiconductors
Published in DKUM: 26.03.2024; Views: 217; Downloads: 18
.pdf Full text (2,07 MB)
This document has many files! More...

UAV Thermal Imaging for Unexploded Ordnance Detection by Using Deep Learning
Milan Bajić, Jr., Božidar Potočnik, 2023, original scientific article

Abstract: A few promising solutions for thermal imaging Unexploded Ordnance (UXO) detection were proposed after the start of the military conflict in Ukraine in 2014. At the same time, most of the landmine clearance protocols and practices are based on old, 20th-century technologies. More than 60 countries worldwide are still affected by explosive remnants of war, and new areas are contaminated almost every day. To date, no automated solutions exist for surface UXO detection by using thermal imaging. One of the reasons is also that there are no publicly available data. This research bridges both gaps by introducing an automated UXO detection method, and by publishing thermal imaging data. During a project in Bosnia and Herzegovina in 2019, an organisation, Norwegian People's Aid, collected data about unexploded ordnances and made them available for this research. Thermal images with a size of 720 x 480 pixels were collected by using an Unmanned Aerial Vehicle at a height of 3 m, thus achieving a very small Ground Sampling Distance (GSD). One of the goals of our research was also to verify if the explosive war remnants' detection accuracy could be improved further by using Convolutional Neural Networks (CNN). We have experimented with various existing modern CNN architectures for object identification, whereat the YOLOv5 model was selected as the most promising for retraining. An eleven-class object detection problem was solved primarily in this study. Our data were annotated semi-manually. Five versions of the YOLOv5 model, fine-tuned with a grid-search, were trained end-to-end on randomly selected 640 training and 80 validation images from our dataset. The trained models were verified on the remaining 88 images from our dataset. Objects from each of the eleven classes were identified with more than 90% probability, whereat the Mean Average Precision (mAP) at a 0.5 threshold was 99.5%, and the mAP at thresholds from 0.5 to 0.95 was 87.0% up to 90.5%, depending on the model's complexity. Our results are comparable to the state-of-the-art, whereat these object detection methods have been tested on other similar small datasets with thermal images. Our study is one of the few in the field of Automated UXO detection by using thermal images, and the first that solves the problem of identifying more than one class of objects. On the other hand, publicly available thermal images with a relatively small GSD will enable and stimulate the development of new detection algorithms, where our method and results can serve as a baseline. Only really accurate automatic UXO detection solutions will help to solve one of the least explored worldwide life-threatening problems.
Keywords: unmanned aerial vehicle, unexploded ordnance, thermal imaging, UXOTi_NPA dataset, convolutional neural networks, deep learning
Published in DKUM: 12.02.2024; Views: 267; Downloads: 17
.pdf Full text (16,94 MB)
This document has many files! More...

Research on vehicle re-identification algorithm based on fusion attention method
Peng Chen, Shuang Liu, Simon Kolmanič, 2023, original scientific article

Abstract: The specific task of vehicle re-identification is how to quickly and correctly match the same vehicle in different scenarios. In order to solve the problem of inter-class similarity and environmental interference in vehicle images in complex scenes, one fusion attention method is put forward based on the idea of obtaining the distinguishing features of details-the mechanism for the vehicle re-identification method. First, the vehicle image is preprocessed to restore the image's attributes better. Then, the processed image is sent to ResNet50 to extract the features of the second and third layers, respectively. Then, the feature fusion is carried out through the two-layer attention mechanism for a network model. This model can better focus on local detail features, and global features are constructed and named SDLAU-Reid. In the training process, a data augmentation strategy of random erasure is adopted to improve the robustness. The experimental results show that the mAP and rank-k indicators of the model on VeRi-776 and the VehicleID are better than the results of the existing vehicle re-identification algorithms, which verifies the algorithm's effectiveness.
Keywords: vehicle re-identification, attention mechanism, key-point, local feature, feature fusion
Published in DKUM: 06.02.2024; Views: 288; Downloads: 16
.pdf Full text (5,28 MB)
This document has many files! More...

Sensitivity Analysis of Hybrid Powertrain Pre-calibration Algorithms : magistrsko delo
Simon Šegula, 2023, master's thesis

Abstract: Currently, meeting the new fuel consumption and emissions standards is the biggest challenge in the automotive industry. One of the solutions is hybridization of the vehicle’s powertrain. This brings with it larger complexity of the vehicle control unit and its pre-calibration. This thesis explores gear shift map and load point shift map, which are two pre-calibration maps included in the vehicle control unit. More specifically it delves in to how the pre-calibration maps are created and how changing their parameters impacts the fuel consumption of the vehicle. Algorithms and optimization simulations were created and performed using AVL’s tool called the Powertrain system optimizer (PSO) which was created within the MATLAB software.
Keywords: Hybrid electric vehicle, Hybrid powertrain, Gear shift map, Load point shift map, Pre-calibration.
Published in DKUM: 23.11.2023; Views: 347; Downloads: 0

Measurements of the characteristics of an electric motor for an electric vehicle's drive
Klemen Srpčič, Gregor Srpčič, 2021, original scientific article

Abstract: This paper aims to present the performance and measurement results of a load test performed on a brushless DC motor built into the wheel of a solar-powered vehicle. A brushless DC motor's theoretical background and operation are presented at the beginning of the paper. The article covers the technical specification of the solar-powered vehicle and the inbuilt brushless DC motor. The measurements were performed with the described equipment at the Institute of Energy Technology, Faculty of Energy Technology, University of Maribor. Due to the unique design of the measured electric motor, it was also necessary to make a special housing, which was intended for connecting the electric motor to the test bench. The article concludes with an analysis of the measurement results in comparison with the data provided by the electric motor manufacturer.
Keywords: electric vehicles, electric motor, brushless DC motor, solar-powered vehicle
Published in DKUM: 13.11.2023; Views: 328; Downloads: 11
.pdf Full text (2,44 MB)
This document has many files! More...

Estimation of real driving emissions based on data from OBD
Matej Fike, Andrej Predin, 2022, published scientific conference contribution abstract

Keywords: vehicle, diesel engine, exhaust emission levels, real driving emissions
Published in DKUM: 30.10.2023; Views: 326; Downloads: 5
.pdf Full text (14,78 MB)
This document has many files! More...

The impact of plug-in hybrid vehicles in low-voltage distribution systems using a Monte Carlo simulation
Evica Smilkoska, Vasko Zdraveski, Jovica Vuletić, Jordančo Angelov, Mirko Todorovski, 2023, original scientific article

Abstract: The growing presence and randomness of renewable-based Distributed Generation, such as solar, photovoltaic, and wind power, and heavy Plug-in Hybrid Electric Vehicle loads in residential distribution grids result in both a higher degree of imbalance and a wide range of voltage fluctuations. When increasing the number of Plug-in Hybrid Electric Vehicles that are simultaneously charged, the additional unpredicted load may cause several problems to the current grid in terms of voltage deviations, thermal overloads, power losses, increased aging of transformers and lines, decreased quality of supply, and power outages. This paper proposes an approach that models Plug-in Hybrid Electric Vehicles’ behaviour and performs power flow analysis on CIGRE low voltage benchmark grid to investigate the impact on the current distribution grid.
Keywords: plug-in hybrid electric vehicle, power quality, non-deterministic approach, voltage deviations, power losses, distribution systems
Published in DKUM: 11.10.2023; Views: 396; Downloads: 5
.pdf Full text (6,44 MB)
This document has many files! More...

Cost and performance comparison of tier-captive SBS/RS with a novel AVS/RS/ML
Banu Y. Ekren, Tone Lerher, Melis Küçükyaşar, Boris Jerman, 2023, original scientific article

Abstract: This paper introduces a novel autonomous vehicle-based storage and retrieval system that utilizes movable lifts (AVS/RS/ML), proposed as an alternative to the tier-captive shuttle-based storage and retrieval system (SBS/RS). The newly proposed system aims to provide an affordable solution with highly utilised AGVs, that can also perform operations out of warehouse. The performance of this novel system is compared with the equivalent tier-captive SBS/RS warehouse design, where each shuttle is dedicated in a specific tier in that design. The comparison is based on the initial system investments costs, throughput rates, and average utilisation of lifts/MLs in the system. Collision prevention rules are also applied to AVS/RS/ML, and its performance is tested through simulation. The results show that the tier-captive SBS/SR system becomes cost-efficient under high throughput rate requirements, while the AVS/RS/ML technology is preferred for relatively moderate and low process rate requirements. The unit-cost per month performance metric of AVS/RS/ML is less sensitive to an increase in number of tiers in the system, compared to the tier-captive SBS/RS case, indicating that AVS/RS/ML may be promising for high-tier warehouse system designs.
Keywords: warehouse design, warehousing systems, materials handling, novel autonomous vehicle-based storage and retrieval system, movable lifts
Published in DKUM: 23.06.2023; Views: 306; Downloads: 19
.pdf Full text (1,14 MB)
This document has many files! More...

The use of intelligent transport systems in the operation of driving schools : master's thesis
Nikola Božinić, 2022, master's thesis

Abstract: The aim of the master's thesis was to conduct research on the use of intelligent transport systems in the current training of future drivers and their knowledge of the content and also knowledge of the content of employees in teh field of training of future drivers The current methods of driver training in individual countries are presented, with a more detailed description of their implementation and the method of testing the acquired knowledge. At the same time, the survey was conducted in the Republic of Croatia and the information on how well people are generally familiar with the knowledge of intelligent transport systems, how they apply them and what do they consider as usable intelligent systems were collected. The research was also conducted among employees in the field of training of future drivers, also in the Republic of Croatia, where were obtained on what changes employees believe have to be done, or how changes in the automotive industry could affect their work, such as is the phenomenon of autonomous driving. After that, a comparison of driver training nowadays wth the proposal of future training with the use of intelligent transport systems is presented.
Keywords: novice drivers, traffic safety, driving education, intelligent vehicle systems, autonomous driving
Published in DKUM: 29.08.2022; Views: 460; Downloads: 39
.pdf Full text (4,33 MB)

Search done in 1.94 sec.
Back to top
Logos of partners University of Maribor University of Ljubljana University of Primorska University of Nova Gorica