Development of Machine Learning based approach to predict fuel consumption and maintenance cost of Heavy-Duty Vehicles using diesel and alternative fuels - Ph.D. Dissertation

Aug 5, 2026

Upload by Patrick

Heavy-duty vehicles contribute substantially to greenhouse-gas emissions, while diesel exhaust also increases health risks from airborne pollutants. Rising pressure to cut emissions and operating expenses requires accurate methods for predicting fuel consumption, maintenance costs, and total cost of ownership. This research develops data-driven machine learning approaches using historical medium- and heavy-duty vehicle data to improve prediction accuracy. The work supports fleet decisions on fuel choice, routing, and maintenance, targeting lower emissions and reduced costs.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages132

Reading Time5 h 33 min

AccessFree to download

Introduction

Motivation and problem statement

Research methodology and data collection

Expected outcomes and modeling approach

Graduate Theses, Dissertations, and Problem Reports 2023 Development of Machine Learning based approach to predict fuel consumption and maintenance cost of Heavy-Duty Vehicles using diesel and alternative fuels Sasanka Katreddi West Virginia University, [gk0037@mix.wvu.edu](gk0037@mix.wvu.edu) Follow this and additional works at: [https://researchrepository.wvu.edu/etd](https://researchrepository.wvu.edu/etd) Part of the Artificial Intelligence and Robotics Commons, Data Science Commons, and the Mechanical Engineering Commons Recommended Citation Katreddi, Sasanka, "Development of Machine Learning based approach to predict fuel consumption and maintenance cost of Heavy-Duty Vehicles using diesel and alternative fuels" (2023) . Graduate Theses, Dissertations, and Problem Reports. 11780. [https://researchrepository.wvu.edu/etd/1](https://researchrepository.wvu.edu/etd/1)1780 This Dissertation is protected by copyright and/or related rights. It has been brought to you by the The Research Repository @ WVU with permission from the rights-holder(s) . You are free to use this Dissertation in any way that is permitted by the copyright and related rights legislation that applies to your use. For other uses you must obtain permission from the rights-holder(s) directly, unless additional rights are indicated by a Creative Commons license in the record and/ or on the work itself. This Dissertation has been accepted for inclusion in WVU Graduate Theses, Dissertations, and Problem Reports collection by an authorized administrator of The Research Repository @ WVU. For more information, please contact [researchrepository@mail.wvu.edu](researchrepository@mail.wvu.edu). Development of Machine Learning based approach to predict fuel consumption and maintenance cost of Heavy-Duty Vehicles using diesel and alternative fuels Sasanka Katreddi Dissertation submitted to the Statler College of Engineering and Mineral Resources at West Virginia University in partial fulfillment of the requirements for the degree of [Ph.D. in](Ph.D. in) Computer Science Natalia A. Schmid, D.Sc. , Chair Arvind Thiruvengadam, Ph.D., Co-Chair Gianfranco Doretto, Ph.D. Xin Li, Ph.D. Vishnu Padmanaban, Ph.D. Lane Department of Computer Science and Electrical Engineering Morgantown, West Virginia 2023 Keywords: Artificial Intelligence, Machine Learning, Neural Networks, Ensemble Models, Mixed Effects Models, Heavy-Duty Vehicles, Fuel Consumption, Maintenance and Repair Cost Copyright 2023 Sasanka Katreddi Abstract Development of Machine Learning based approach to predict fuel consumption and maintenance cost of Heavy-Duty Vehicles using diesel and alternative fuels Sasanka Katreddi One of the major contributors of human-made greenhouse gases (GHG) namely carbon dioxide (CO2 ), methane (CH4 ), and nitrous oxide (NOX) in the transportation sector and heavy-duty vehicles (HDV) contributing to about 27% of the overall fraction. In addition to the rapid increase in global temperature, airborne pollutants from diesel vehicles also present a risk to human health. Even a small improvement that could potentially drive energy savings to the century-old mature diesel technology could yield a significant impact on minimizing greenhouse gas emissions. With the increasing focus on reducing emissions and operating costs, there is a need for efficient and effective methods to predict fuel consumption, maintenance costs, and total cost of ownership for heavy-duty vehicles. Every improvement so achieved in this direction is a direct contributor to driving the reduction in the total cost of ownership for a fleet owner, thereby bringing economic prosperity and reducing oil imports for the economy. Motivated by these crucial goals, the present research considers integrating data-driven techniques using machine learning algorithms on the historical data collected from medium-and heavy-duty vehicles. The primary motivation for this

FAQs

Why is predicting fuel consumption and maintenance cost important for heavy-duty vehicle fleets?

It helps fleets reduce emissions and operating costs by enabling more informed decisions on fuel type, route planning, and maintenance scheduling.

What data sources and fuel types are used in this research?

Data are collected at West Virginia University’s CAFEE lab in collaboration with fleet partners, covering diesel and alternative fuels including compressed natural gas, liquefied propane gas, hydrogen fuel cells, and electric vehicles.

What machine learning outcomes does the dissertation aim to produce?

It targets a neural network model for predicting fuel consumed per trip and additional machine learning models for estimating maintenance-related costs using parameters such as speed, load, route, fuel type, and engine type.

Aug 5, 2026

Upload by Patrick