Details

Razvoj metodologije za analizo vpliva vozniškega vedenja na porabo goriva v simulatorju vožnje tovornih vozil
ID Nemec, Vid (Author), ID Kozjek, Dominik (Mentor) More about this mentor... This link opens in a new window, ID Luštrek, Mitja (Comentor)

.pdfPDF - Presentation file, Download (12,48 MB)
MD5: 6B0C64AA0F58AAD7D09F32E2125EA926

Abstract
Cilj magistrskega dela je razviti metodologijo za prepoznavanje neučinkovitih delov vožnje ter pripravo vozniku razumljivih povratnih informacij za izboljšanje porabe goriva pri vožnji tovornih vozil na simulatorjih. Ker trenutna poraba goriva ni odvisna le od vozniškega vedenja, temveč tudi od cestnega in prometnega konteksta, metodologija temelji na lokalnem vrednotenju porabe. Iz primerljivih delov vožnje je določena referenčna poraba, odstopanje od nje pa predstavlja ciljno spremenljivko za model strojnega učenja. Metodologija je bila razvita in ovrednotena na podatkih profesionalnih voznikov v simulatorju vožnje tovornih vozil. Za napovedovanje odstopanja porabe je bil uporabljen model LightGBM, njegova razlaga pa je bila izvedena z metodo SHAP. Za pretvorbo razlag v vozniku razumljive povratne informacije je bil uporabljen veliki jezikovni model. Rezultati kažejo, da je mogoče z razvito metodologijo uspešno napovedovati neučinkovite dele vožnje ter prepoznati ključne dejavnike, ki vplivajo na povečano porabo goriva. Razvita metodologija predstavlja osnovo za sisteme, ki voznikom omogočajo razumljive, lokalno prilagojene in razložljive povratne informacije za izboljšanje energijske učinkovitosti vožnje.

Language:Slovenian
Keywords:poraba goriva, vozniško vedenje, simulator vožnje, strojno učenje, LightGBM, SHAP, eko-vožnja
Work type:Master's thesis/paper
Typology:2.09 - Master's Thesis
Organization:FS - Faculty of Mechanical Engineering
Place of publishing:Ljubljana
Publisher:[V. Nemec]
Year:2026
Number of pages:XXII, 69 str.
PID:20.500.12556/RUL-190141 This link opens in a new window
UDC:621.43:004.94:656.052(043.2)
COBISS.SI-ID:302529027 This link opens in a new window
Publication date in RUL:23.10.2026
Views:131
Downloads:26
Metadata:XML DC-XML DC-RDF
:
Copy citation
Share:Bookmark and Share

Secondary language

Language:English
Title:Development of a methodology for analysing the impact of driving behaviour on fuel consumption in a truck driving simulator
Abstract:
The aim of this master's thesis is to develop a methodology for identifying inefficient segments of a drive and generating feedback that is understandable to the driver, with the goal of improving fuel efficiency in truck driving simulator. Since instantaneous fuel consumption depends not only on driving behaviour but also on road and traffic conditions, the methodology is based on a localized assessment of consumption. A reference consumption level is determined from comparable driving segments, and the deviation from this baseline serves as the target variable for a machine learning model. The methodology was developed and evaluated using data from professional drivers obtained in a truck driving simulator. A LightGBM model was employed to predict consumption deviations, and the SHAP method was used to interpret the model's predictions. A Large Language Model (LLM) was utilized to translate these interpretations into feedback that is easily understood by drivers. The results demonstrate that the developed methodology can successfully predict inefficient driving segments and identify the key factors contributing to increased fuel consumption. This methodology provides a foundation for systems that offer drivers understandable, context-specific, and explainable feedback to enhance driving energy efficiency.

Keywords:fuel consumption, driving behaviour, driving simulator, machine learning, LightGBM, SHAP, eco-driving

Similar documents

Similar works from RUL:
Similar works from other Slovenian collections:

Back