Automotive Engineering Commons^™

Unsupervised Feature Learning For Point Cloud By Contrasting And Clustering With Graph Convolutional Neural Network, Ling Zhang

Dissertations and Theses

Recently, deep graph neural networks (GNNs) have attracted significant attention for point cloud understanding tasks, including classification, segmentation, and detection. However, the training of such deep networks still requires a large amount of annotated data, which is both expensive and time-consuming. To alleviate the cost of collecting and annotating large-scale point cloud datasets, we propose an unsupervised learning approach to learn features from unlabeled point cloud ”3D object” dataset by using part contrasting and object clustering with GNNs. In the contrast learning step, all the samples in the 3D object dataset are cut into two parts and put into a …

Comparison Of Drag Area Estimation Using Natural Coast Down And Constant Speed Test Methods, Cem Baki Mr

Graduate Theses, Dissertations, and Problem Reports (ETD)

Currently in US, more than 26 percent of the total GHG emissions comes from transportation and mostly from heavy duty vehicles. Similarly, the European Council stated that 25 percent of the emissions comes from heavy duty transportation and they expect it to be further increased in the future. However, with the new coming regulations US EPA and European Council aiming to reduce the emissions by 80 percent in US and 60 percent in EU. In order to keep track and control the emissions, both authorities published new regulations and testing methods for certifying the new vehicles.

Aerodynamic testing is one …

Modeling Of Optimized Neuro-Fuzzy Logic Based Active Vibration Control Method For Automotive Suspension, Mohammad Adom Safiullah

Masters Theses

In this thesis, an active vibration control system was developed. The control system was developed and tested using a quarter car model of an adaptive suspension system. For active vibration control, an actuator was implemented in addition to the commonly used passive spring damper system. Due to nature of unpredictability of force required two different fuzzy inference system (FIS) were developed for the actuator. First a sequential fuzzy set was built, that resulted lower vertical displacement compared to basic damper spring model, but system had limited effect with disturbances of higher magnitude and continuous vibrations (rough road). To improve the …

Investigation And Development Of Exhaust Flow Rate Estimation Methodologies For Heavy-Duty Vehicles, Chakradhar Reddy Vardhireddy

Graduate Theses, Dissertations, and Problem Reports (ETD)

Exhaust gas flow rate from a vehicle tailpipe has a great influence on emission mass rate calculations, as the emission fractions of individual gases in the exhaust are calculated by using the measured exhaust flow rate. The development of high-end sensor technologies and emission pollutant measurement instruments, which can give instantaneous values of volume concentration of pollutants flowing out of the engine are gaining importance because of their ease of operation. The volume concentrations measured can then be used with the instantaneous exhaust flow rate values to obtain mass flow rates of pollutants.

With the recent promulgation of real world …

Roadnet: Robust Adaptive Network For Information Diffusion In Vanet, Priyashraba Misra

Graduate Theses, Dissertations, and Problem Reports (ETD)

The automotive industry has changed more in the last one decade than ever before. Rapid advancements in autonomous driving have opened up opportunities for CAVs (Connected and Automated Vehicles). Vehicles today rely on a sensor-suite to map the surrounding and use that information for safety and navigation. The sensor's view is limited to its line of sight and this drawback can be tapered off by using Vehicle to Vehicle (V2V) and Vehicle to Infrastructure (V2I), generally referred to as Vehicle to Everything (V2X) communication. In this thesis, we specifically focus on utilizing V2V communication using on-board Dedicated Short Range Communication …

Mpc-Based Autonomous Driving Control With Localized Path Planning For Obstacle Avoidance And Navigating Signalized Intersections, Sai Rajeev Devaragudi

Dissertations, Master's Theses and Master's Reports

Connected and autonomous vehicles are becoming the major focus of research for the industry and academia in the automotive field. Many companies and research groups have demonstrated the advantages and the requirement of such technology to improve the energy efficiency of vehicles, decrease the number of crash and road accidents, and control emissions.

This research delves into improving the autonomy of self-driving vehicles by implementing localized path planning algorithms to introduce motion control for obstacle avoidance during uncertainties. Lateral path planning is implemented using the A* algorithm combined with piecewise Bezier curve generation which provides an optimum trajectory reference to …

Benchmarking And Evaluating The Efficiency Of Mass Transit Systems Based On Best Practice Using Data Envelopment Analysis, Jacqueline Nayame, Maoloud Dabab, Timothy Anderson

Engineering and Technology Management Faculty Publications and Presentations

Public transit systems in the USA have been faced with mounting pressure to decrease their operating costs while at the same time expected to increase ridership and meeting multiple societal needs. The primary objective of this study is to measure the efficiencies of mass transit agencies based on best practice in the US, identify the influencing factors leading to their efficiencies, and how these strategies and policies can be used improve inefficiency in transit agencies. Using Data Envelopment Analysis (DEA) method, the study analyzed the mass performance of 334 transit agencies across the US using data from the national transit …

Intelligent Transportation Systems, Hybrid Electric Vehicles, Powertrain Control, Cooperative Adaptive Cruise Control, Model Predictive Control, Hadi Kazemi

Graduate Theses, Dissertations, and Problem Reports (ETD)

Information obtainable from Intelligent Transportation Systems (ITS) provides the possibility of improving the safety and efficiency of vehicles at different levels. In particular, such information has the potential to be utilized for prediction of driving conditions and traffic flow, which allows us to improve the performance of the control systems in different vehicular applications, such as Hybrid Electric Vehicles (HEVs) powertrain control and Cooperative Adaptive Cruise Control (CACC). In the first part of this work, we study the design of an MPC controller for a Cooperative Adaptive Cruise Control (CACC) system, which is an automated application that provides the drivers …

การตรวจสอบรอยแตกร้าวบนพื้นผิวคอนกรีตในรูปแบบมัลติสเกลโดยการประมวลผลภาพ, ปิยวัฒน์ ตันติ์ศรีสกุล

Chulalongkorn University Theses and Dissertations (Chula ETD)

รอยร้าวบนพื้นผิวคอนกรีตอาจจะมีลักษณะความแตกต่างตามสาเหตุที่เกิดขึ้น หากได้มีการตรวจสอบในระดับที่ใกล้ชิดกับพื้นผิวรอยร้าว แล้วสามารถนำมาวิเคราะห์แยกลักษณะความแตกต่างของรอยร้าวตามสาเหตุที่เกิดขึ้นได้ ก็จะได้รูปแบบที่จะช่วยลดขั้นตอนการตรวจสอบและเพิ่มขีดความสามารถของบุคลากรในการตรวจสอบรอยร้าวได้ งานวิจัยนี้เป็นกรณีศึกษา โดยตั้งสมมติฐานลักษณะความแตกต่างของรอยร้าวตามสาเหตุที่ได้กำหนด จากนั้นทำการหล่อและทดสอบตัวอย่างคอนกรีตที่ได้กำหนดไว้ คือ การทดสอบแรงดัด การทดสอบแรงเฉือนและการทดสอบแรงดึง จากนั้นนำ Chula Smart Lens ที่มีกำลังขยาย 20, 40 และ 50 เท่า มาใช้งานร่วมกับโทรศัพท์มือถือ Iphone7 ในการถ่ายรูปรอยร้าวที่เกิดขึ้นบนพื้นผิวคอนกรีตและนำภาพถ่ายไปวิเคราะห์โดยการสร้างแบบจำลองและกระบวนการประมวลผลภาพ เพื่อหาลักษณะความแตกต่างและตรวจวัดรอยร้าวที่เกิดขึ้นที่พื้นผิวบนคอนกรีต ผลจากงานวิจัยลักษณะรอยร้าวบนพื้นผิวคอนกรีตจากการสร้างแบบจำลองและการประมวลผลภาพ พบว่ามีบางส่วนเป็นไปตามสมมติฐาน แต่มีบางส่วนที่ไม่เป็นไปตามสมมติฐาน ดังนั้น สมมติฐานลักษณะความแตกต่างของรอยร้าวที่ได้ตั้งไว้ตามสาเหตุที่ได้กำหนดจึงไม่เป็นจริง ส่วนการตรวจวัดรอยร้าวคอนกรีตนั้นสามารถหาค่าความกว้าง ความยาวและพื้นที่ของรอยร้าวที่เกิดขึ้นได้การการประมวลผลภาพ เมื่อรู้ค่าดังกล่าวแล้วสามารถที่จะนำไปหาวิธีในการซ่อมแซมบำรุงรักษาต่อไป

Combined Trajectory, Propulsion, And Battery Mass Optimization For Solar-Regenerative High-Altitude Long Endurance Unmanned Aircraft, Nathaniel S. Gates, Kevin R. Moore, Andrew Ning, John D. Hedengren

Faculty Publications

Combined optimization of propulsion system design, flight trajectory planning and battery mass optimization for solar-regenerative high-altitude long endurance (SRHALE) aircraft through a sequential iterative approach yields an increase of 20.2% in the end-of-day energy available on the winter solstice at 35 deg N latitude, resulting in an increase in flight time of 2.36 hours. The optimized flight path is obtained by using nonlinear model predictive control to solve flight and energy system dynamics over a 24 hour period with a 15 second time resolution. The optimization objective is to maximize the total energy in the system while flying a station-keeping …

Reduction Of Nox Emissions In A Single Cylinder Diesel Engine Using Sncr With In-Cylinder Injection Of Aqueous Urea, Anthony Timpanaro

UNF Graduate Theses and Dissertations

The subject of this study is the effect of in-cylinder selective non-catalytic reduction (SNCR) of NO_x emissions in diesel exhaust gas by means of direct injection of aqueous urea ((NH₂)₂CO) into the combustion chamber. A single cylinder diesel test engine was modified to accept an electronically controlled secondary common rail injection system to deliver the aqueous urea directly into the cylinder during engine operation.

Direct in-cylinder injection was chosen in order to ensure precise delivery of the reducing agent without the risk of any premature reactions taking place. Unlike direct in-cylinder injection of neat water, …

The Effect Of Communication And Vehicle Properties On The Search Performance Of A Swarm Of Unmanned Aerial Vehicles, Jenna E. Newcomb, Andrew Ning

Faculty Publications

An unmanned aerial vehicle (UAV) swarm allows for a more time-efficient method of searching a specified area than a single UAV or piloted plane. There are a variety of factors that affect how well an area is surveyed. We specifically analyzed the effect both vehicle properties and communication had on the swarm search performance. We used non-dimensionalization to examine the effect vehicle properties had on search performance so the results can be applied to any domain size with any number and type of vehicle. We found that even if vehicles could only sense 10% of the grid area at any …