Engineering Commons^™

Efficient End-To-End Autonomous Driving, Hesham Eraqi

Theses and Dissertations

Steering a car through traffic is a complex task that is difficult to cast into algorithms. Therefore, researchers turn to train artificial neural networks from front-facing camera data stream along with the associated steering angles. Nevertheless, most existing solutions consider only the visual camera frames as input, thus ignoring the temporal relationship between frames. In this work, we propose a Convolution Long Short-Term Memory Recurrent Neural Network (C-LSTM), which is end-to-end trainable, to learn both visual and dynamic temporal dependencies of driving. Additionally, We introduce posing the steering angle regression problem as classification while imposing a spatial relationship between the …

Thermoplastic Additive Manufacturing For Composites And Molds, Pritesh S. Yeole

Doctoral Dissertations

Recent inventions in the ability of additive manufacturing (AM) to use carbon fiber (CF) reinforced pellets as a feedstock material to manufacture components has complemented its purpose from prototypes to structural load-bearing parts. In the first part of this research, we investigated the processability, microstructure, and mechanical performance of twin-screw compounded short CF reinforced polyphenylene sulfide (PPS) pellets as a feedstock material for extrusion deposition fabrication-additive manufacturing (EDF-AM) using big area AM (BAAM). The performance of the BAAM components was compared to that of traditional processing methods, namely injection molding (IM) and extrusion-compression molding (ECM). It was found that the …

Intelligent Roadside Unit Deployment In Vehicular Network, Xiangyu Xu

Masters Theses

Intelligent Transportation System (ITS) has been an important research area in building the foundational infrastructures of self-driving vehicles and improving traffic efficiency of future transportation systems. Scientists have been hoping to incorporate intelligence into traditional transportation systems to help reduce the risks, accident rates, traffic congestion, and even environmental emissions.

There are many research works that have been focused on the communication part of ITS, such as vehicular networks, which collect data from vehicles and send it to the cloud for analysis. In the vehicular networks, Roadside Unit (RSU) is a key infrastructure as an intermediate layer between the vehicles …

Towards Sensorimotor Coupling Of A Spiking Neural Network And Deep Reinforcement Learning For Robotics Application, Kashu Yamazaki

Mechanical Engineering Undergraduate Honors Theses

Deep reinforcement learning augments the reinforcement learning framework and utilizes the powerful representation of deep neural networks. Recent works have demonstrated the great achievements of deep reinforcement learning in various domains including finance,medicine, healthcare, video games, robotics and computer vision.Deep neural network was started with multi-layer perceptron (1stgeneration) and developed to deep neural networks (2ndgeneration)and it is moving forward to spiking neural networks which are knownas3rdgeneration of neural networks. Spiking neural networks aim to bridge the gap between neuroscience and machine learning, using biologically-realistic models of neurons to carry out computation. In this thesis, we first provide a comprehensive review …

Towards Dynamic Vehicular Clouds, Aida Ghazizadeh

Computer Science Theses & Dissertations

Motivated by the success of the conventional cloud computing, Vehicular Clouds were introduced as a group of vehicles whose corporate computing, sensing, communication, and physical resources can be coordinated and dynamically allocated to authorized users. One of the attributes that set Vehicular Clouds apart from conventional clouds is resource volatility. As vehicles enter and leave the cloud, new computing resources become available while others depart, creating a volatile environment where the task of reasoning about fundamental performance metrics becomes very challenging. The goal of this thesis is to design an architecture and model for a dynamic Vehicular Cloud built on …

Optimized System For On-Route Charging Of Battery Electric Buses And High-Fidelity Modelling And Simulation Of In-Motion Wireless Power Transfer, Yogesh Bappasaheb Jagdale

Masters Theses

Electrifying cars, buses and trucks is an attractive means to reduce energy use and emissions, because it involves minimal restructuring of the transportation network. Transit buses drive fixed routes, minimizing driver range anxiety by properly sizing energy storage system but the major challenge to fully electrifying transit buses, is the amount of energy they consume in a day of driving. To enable a full day of operation, batteries need to be large, which is expensive and heavy. This work utilizes real-world transit bus data fed to a battery electric drive-train model to co-optimize charger locations, charger power levels, and vehicle …

Development Of Catalytic Chromia-Based Aerogels, Fiona Fitzgerald

Honors Theses

Over one billion automobiles are in use around the world, the majority of which employ internal combustion engines. Catalytic converters are used to convert the toxic compounds found in car exhaust -- carbon monoxide, nitrogen oxides (NOx) and hydrocarbons -- to less harmful gases. The typical catalytic converter employs as catalysts expensive raw materials (platinum, palladium and/or rhodium) wash-coated onto an alumina-based ceramic substrate. Aerogel materials have high surface area and thermal stability, properties that make them attractive for catalysis applications. Aerogels made with transition metal oxides are candidates to replace platinum in the catalytic converter. Chromium oxide (chromia) materials …

Conducted And Radiated Emi Measurements Of Parallel Buck Converters Under Varying Spread Spectrum Parameters, Elena Postupalskaya, Nathan Wang

Electrical Engineering

The Conducted and Radiated EMI Measurements with Parallel Buck Converters Under Varying Spread Spectrum Parameters research senior project aims to explore the effects from Spread Spectrum Frequency Modulation (SSFM) on the input electromagnetic interference (EMI) or noise of a switching power supply, specifically with LM53601MAEVM hardware. The input EMI is important as the main input bus needs to be clean to provide a reliable source for other sensitive devices connected to it. SSFM can replace a conventional EMI filter and save weight, space, and cost. This project provides a basis in terms of the impacts of variable SSFM in simulation …

Turbulence Investigations In The Core-Flow Of An Internal Combustion Engine, James R. Macdonald

Dissertations

Turbulence significantly impacts the operation of energy conversion devices. In internal combustion (IC) engines, mixing, heat transfer, and combustion are all strongly dependent on the turbulence inside the cylinder. Consequently, knowledge of the state of turbulence is critical for improving our understanding and modeling of engine processes.

Turbulence states may be determined through analysis of the Reynolds stress tensor, which can in turn be experimentally quantified using velocity data. In this research, stereoscopic particle image velocimetry (stereo-PIV) experiments were conducted in a single-cylinder, motored engine with optical access to measure the two-dimensional, three-component (2D-3C) velocity fields throughout the compression stroke. …

Control And Locomotion Of Inertially And Magnetically Actuated Multi-Scale Robotic Systems, Ehab Al Khatib

Mechanical Engineering Research Theses and Dissertations

In this research, two actuation systems were introduced, inertial and magnetic actuation. In the inertial actuation, the robot used the transfer of momentum to navigate, and this momentum could be generated by spinning masses and wheels. Recent studies in our System Laboratory proved that a wide range of inertially actuated locomotion systems could be generated. This can be achieved by using a family tree approach, starting from a very simple system, and progressively evolving it to more complex ones. The motion diversity of these robots inspired us to extend their locomotion from a macro scale to millimeter and micro scales. …

Nonlinear Least Squares 3-D Geolocation Solutions Using Time Differences Of Arrival, Michael V. Bredemann

Mathematics & Statistics ETDs

This thesis uses a geometric approach to derive and solve nonlinear least squares minimization problems to geolocate a signal source in three dimensions using time differences of arrival at multiple sensor locations. There is no restriction on the maximum number of sensors used. Residual errors reach the numerical limits of machine precision. Symmetric sensor orientations are found that prevent closed form solutions of source locations lying within the null space. Maximum uncertainties in relative sensor positions and time difference of arrivals, required to locate a source within a maximum specified error, are found from these results. Examples illustrate potential requirements …

Comparison Of Optimal Energy Management Strategies Using Dynamic Programming, Model Predictive Control, And Constant Velocity Prediction, Amol Arvind Patil

Masters Theses

Due to the recent advancements in autonomous vehicle technology, future vehicle velocity predictions are becoming more robust which allows fuel economy (FE) improvements in hybrid electric vehicles through optimal energy management strategies (EMS). A real-world highway drive cycle (DC) and a controls-oriented 2017 Toyota Prius Prime model are used to study potential FE improvements. We proposed three important metrics for comparison: (1) perfect full drive cycle prediction using dynamic programming, (2) 10-second prediction horizon model predictive control (MPC), and (3) 10-second constant velocity prediction. These different velocity predictions are put into an optimal EMS derivation algorithm to derive optimal engine …

Vehicle Performance Analysis Of An Autonomous Electric Shuttle Modified For Wheelchair Accessibility, Johan Fanas Rojas

Masters Theses

Autonomous vehicles (AV) have the potential to vastly improve independent, safe, and cost-effective mobility options for individuals with disabilities. However, accessibility considerations are often overlooked in the early stages of design, resulting in AVs that are inaccessible to people with disabilities. The needs of wheeled mobility device users can cause significant vehicle design changes due to requirements for stepless ingress/egress and increased space for onboard circulation and securement. Vehicles serving people with disabilities typically require costly aftermarket modifications for accessibility, which may have unforeseen impacts on vehicle performance and safety, particularly in the case of automated vehicles. In this research, …

Fluid Power Vehicle Challenge, Jacob Torrey, Kayla Londono, Bryson Chan, Aaron Trujillo

Mechanical Engineering

The FPVC combines mechanical engineering disciplines to design and manufacture a vehicle that utilizes hydraulic power. The FDR covers the final manufacturing process and verification processes developed during the front end of research and analysis built upon the Critical Design Review (CDR) and the PDR (Preliminary Design Review). This report showcases the design decisions and extensive research that supports the continuing efforts by the Team Pump My Ride, to build upon the accomplishments of Cal Poly’s previous team, The Incompressibles. The FDR presents how Team Pump My Ride produced the design changes from the CDR and PDR to achieve improvements …

Vehicle Velocity Prediction Using Artificial Neural Networks And Effect Of Real-World Signals On Prediction Window, Tushar Dnyaneshwar Gaikwad

Masters Theses

Prediction of vehicle velocity is essential since it can realize improvements in the fuel economy/energy efficiency, drivability, and safety. Many publications address velocity prediction problems, yet there is a need for the understanding effect of different signals for the prediction. There are numerous new sensor and signal technologies like vehicle-to-vehicle and vehicle-to-infrastructure communication that can be used to obtain comprehensive datasets. Several references considered deterministic and stochastic approaches that use the datasets as input to determine future operation predictions. These approaches include different traffic models and artificial neural networks such as Markov chain, nonlinear autoregressive model, Gaussian function, and recurrent …

Simulation And Design Tool For Supermileage Vehicle (Smv) Club Final Design Report, Kimberly Kodama, Sung Ho An, Justice Aragon

Mechanical Engineering

The purpose of this project is to create a sensitivities tool and start an optimization tool to assist the Cal Poly SMV Team in designing their vehicle, developing a driving strategy for competition, and becoming a contender in endurance events. The development of a user-friendly vehicle simulation and design tool was proposed by Professor Joseph Mello who is the club’s advisor. The SMV Team competes in endurance events such as the Supermileage competition or the Shell Eco-marathon with the goal of achieving the best mileage possible.

This report will present the research that has been conducted to understand and define …

Internal Combustion Engine, Philippe D. Habets, Sam S. Flood, Paing Htet Lin, Jason Wu, Ricardo Cuevas

Mechanical Engineering

The goal of this project is to modify a Honda GX35 engine to improve its fuel efficiency and maximize its competitiveness in the Shell Eco-marathon competitions. This competition has tight restrictions on the type of fuel used to power the engine, but otherwise has very few rules limiting the type of modifications which may be made. Our primary goals are to maximize volumetric efficiency and maintain an efficient operating temperature. Future work might pursue more advanced technologies such as pseudo-atkinson cycle operation.

Pedestrian Navigation Using Artificial Neural Networks And Classical Filtering Techniques, David J. Ellis

Theses and Dissertations

The objective of this thesis is to explore the improvements achieved through using classical filtering methods with Artificial Neural Network (ANN) for pedestrian navigation techniques. ANN have been improving dramatically in their ability to approximate various functions. These neural network solutions have been able to surpass many classical navigation techniques. However, research using ANN to solve problems appears to be solely focused on the ability of neural networks alone. The combination of ANN with classical filtering methods has the potential to bring beneficial aspects of both techniques to increase accuracy in many different applications. Pedestrian navigation is used as a …

Geometric State Observers For Autonomous Navigation Systems, Miaomiao Wang

Electronic Thesis and Dissertation Repository

The development of reliable state estimation algorithms for autonomous navigation systems is of great interest in the control and robotics communities. This thesis studies the state estimation problem for autonomous navigation systems. The first part of this thesis is devoted to the pose estimation on the Special Euclidean group $\SE(3)$. A generic globally exponentially stable hybrid estimation scheme for pose (orientation and position) and velocity-bias estimation on $\SE(3)\times \mathbb{R}^6$ is proposed. Moreover, an explicit hybrid observer, using inertial and landmark position measurements, is provided.

The second part of this thesis is devoted to the problem of simultaneous estimation of the …

Development Of An Eco Approach And Departure Application To Improve Energy Consumption Of A Plug-In Hybrid Vehicle In Charge Depleting Mode, Brandon Narodzonek

Dissertations, Master's Theses and Master's Reports

A recent study at Michigan Technological University as part of the NEXTCAR DOE APRA-E Project was conducted to determine the potential energy savings of a plug-in hybrid electric vehicle (PHEV) equipped with various Connected and Automated Vehicle (CAV) Technologies. One aspect of this study focused on the development of an Eco Approach and Departure (Eco AnD) Application that would further reduce the energy consumed around a signalized intersection.

Many modern intersections are equipped with traffic signals that can broadcast Basic Safety (BSM), MAP, and Signal Phase and Timing (SPaT) message sets that contain intersection ID, location, current phase, and cyclic …

Electrathon Vehicle: Front Suspension, Christopher Clark

All Undergraduate Projects

Central Washington University does not currently have a competition field-able Electrathon America electric vehicle with adequate front suspension. The aim of this project was to provide the vehicle with handling that supports sound ground contact throughout the competition environment. Handling that supports sound ground contact is important for vehicles so they can go around corners without a loss of traction or flipping over. The solution to this engineering problem was designed and tested through various requirements. The requirements at hand were that the suspension components weigh less than 50 pounds, that there be no more than 3 inches of suspension …

Sensor Fusion And Non-Linear Mpc Controller Development Studies For Intelligent Autonomous Vehicular Systems, Ahammad Basha Dudekula

Dissertations, Master's Theses and Master's Reports

The demand for safety and fuel efficiency on ground vehicles and advancement in embedded systems created the opportunity to develop Autonomous controller. The present thesis work is three fold and it encompasses all elements that are required to prototype the autonomous intelligent system including simulation, state handling and real time implementation. The Autonomous vehicle operation is mainly dependent upon accurate state estimation and thus a major concern of implementing the autonomous navigation is obtaining robust and accurate data from sensors. This is especially true, in case of Inertial Measurement Unit (IMU) sensor data. The IMU consists of a 3-axis gyro, …

Data Driven Sensor Fusion For Cycle-Cycle Imep Estimation, Cooper Heyne Minehart

Dissertations, Master's Theses and Master's Reports

As the world searches for ways to reduce humanity’s impact on the environment, the automotive industry looks to extend the viable use of the gasoline engine by improving efficiency. One way to improve engine efficiency is through more effective control – effective control systems require a feedback signal. Indicated mean effective pressure (IMEP) is a useful feedback signal for automotive control but is costly to measure directly.

Successful machine learning based sensor fusion requires effective feature extraction and model creation. Through a multistage application of machine learning to both the feature extraction process and the IMEP estimation process we are …

Real-Time Predictive Control Of Connected Vehicle Powertrains For Improved Energy Efficiency, Joseph Oncken

Dissertations, Master's Theses and Master's Reports

The continued push for the reduction of energy consumption across the automotive vehicle fleet has led to widespread adoption of hybrid and plug-in hybrid electric vehicles (PHEV) by auto manufacturers. In addition, connected and automated vehicle (CAV) technologies have seen rapid development in recent years and bring with them the potential to significantly impact vehicle energy consumption. This dissertation studies predictive control methods for PHEV powertrains that are enabled by CAV technologies with the goal of reducing vehicle energy consumption.

First, a real-time predictive powertrain controller for PHEV energy management is developed. This controller utilizes predictions of future vehicle velocity …

Design Of An Anti-Jerk Controller For Both Locked And Slipping Torque Converter Conditions In A Vehicle, Syed Ahmad Nadeem

Dissertations, Master's Theses and Master's Reports

With the advancement in the automotive technologies, the customer scrutiny on the ride comfort of automobiles has come to light. Vehicle drivability is one of the important aspects that defines the ride comfort for a vehicle. Drivability of a vehicle is a qualitative measure and may differ from person to person, however, researches have come up to highlight a few parameters that can categorize the drivability performance of a vehicle into good or bad for a majority of the targeted audience. One of those parameters include shuffle, which is defined as the longitudinal oscillations that occurs in the drivetrain when …

A Study Of Model-Based Control Strategy For A Gasoline Turbocharged Direct Injection Spark Ignited Engine, Xin Wang

Dissertations, Master's Theses and Master's Reports

To meet increasingly stringent fuel economy and emissions legislation, more advanced technologies have been added to spark-ignition (SI) engines, thus exponentially increase the complexity and calibration work of traditional map-based engine control. To achieve better engine performance without introducing significant calibration efforts and make the developed control system easily adapt to future engines upgrades and designs, this research proposes a model-based optimal control system for cycle-by-cycle Gasoline Turbocharged Direct Injection (GTDI) SI engine control, which aims to deliver the requested torque output and operate the engine to achieve the best achievable fuel economy and minimum emission under wide range of …

Atv Dynamics And Pediatric Rider Safety, James T. Auxier Ii

Theses and Dissertations--Biomedical Engineering

It has been observed through numerous academic and governmental agency studies that pediatric all-terrain vehicle ridership carries significant risk of injury and death. While no doubt valuable to safety, the post-hoc approach employed in these studies does little to explain the why and how behind the risk factors. Furthermore, there has been no prolonged, widespread, organized, and concerted effort to reconstruct and catalog the details and causes of the large (20,000+) number of ATV-related injuries that occur each year as has been done for road-based motor vehicle accidents. This dissertation takes the opposite approach from a meta-analysis and instead examines …

Route Planning For Long-Term Robotics Missions, Christopher Alexander Arend Tatsch

Graduate Theses, Dissertations, and Problem Reports

Many future robotic applications such as the operation in large uncertain environment depend on a more autonomous robot. The robotics long term autonomy presents challenges on how to plan and schedule goal locations across multiple days of mission duration. This is an NP-hard problem that is infeasible to solve for an optimal solution due to the large number of vertices to visit. In some cases the robot hardware constraints also adds the requirement to return to a charging station multiple times in a long term mission. The uncertainties in the robot model and environment require the robot planner to account …

Implementation Of Radial Basis Function Artificial Neural Network Into An Adaptive Equivalent Consumption Minimization Strategy For Optimized Control Of A Hybrid Electric Vehicle, Thomas P. Harris

Graduate Theses, Dissertations, and Problem Reports

Continued increases in the emission of greenhouse gases by passenger vehicles has accelerated the production of hybrid electric vehicles. With this increase in production, there has been a parallel demand for continuously improving strategies of hybrid electric vehicle control. The goal of an ideal control strategy is to maximize fuel economy while minimizing emissions. The design and implementation of an optimized control strategy is a complex challenge. Methods exist by which the globally optimal control strategy may be found. However, these methods are not applicable in real-world driving applications since these methods require a priori knowledge of the upcoming drive …

ผลกระทบจากกรรมวิธีทางความร้อนในการฟื้นฟูโครงสร้างจุลภาคในโลหะผสมพิเศษเนื้อพื้นนิกเกิลที่ได้จากการหล่อและผ่านการให้ความร้อนมาเป็นระยะเวลานาน, วรา วัชรถานนท์

Chulalongkorn University Theses and Dissertations (Chula ETD)

งานวิจัยนี้ได้ทำการศึกษาและประเมินผลของการทำกรรมวิธีทางความร้อน ซึ่งประกอบด้วยการทำละลายที่อุณหภูมิ 1175 องศาเซลเซียส เป็นเวลา 4 ชั่วโมง แล้วปล่อยให้เย็นตัวในอากาศ และการบ่มแข็งที่อุณหภูมิ 845 องศาเซลเซียส เป็นเวลา 24 ชั่วโมง แล้วปล่อยให้เย็นตัวในอากาศ เพื่อปรับปรุงและฟื้นฟูโครงสร้างจุลภาคในโลหะผสมพิเศษเนื้อพื้นนิกเกิลเกรดจีทีดี-111 ที่มีการเติมธาตุอะลูมิเนียม, นิกเกิล และ/หรือโคบอลต์เพิ่มเติม หลังจากผ่านการจำลองการใช้งานจริงที่อุณหภูมิ 900 องศาเซลเซียส และ 1000 องศาเซลเซียส เป็นเวลา 400 ชั่วโมง พบว่าการทำกรรมวิธีทางความร้อนด้วยเงื่อนไขนี้เหมาะสมกับชิ้นงานที่ผ่านการจำลองการใช้งานจริงที่อุณหภูมิ 900 องศาเซลเซียส แต่โครงสร้างจุลภาคที่เกิดขึ้นยังไม่สามารถกลับคืนสู่สภาพเดิมได้ทั้งหมด เมื่อเปรียบเทียบกับโครงสร้างจุลภาคของชิ้นงานดั้งเดิมที่ยังไม่ผ่านการจำลองการใช้งานจริงจากงานวิจัยก่อนหน้านี้ ซึ่งแสดงให้เห็นว่าอุณหภูมิ และ/หรือเวลาที่ใช้ในการทำละลายยังไม่มากเพียงพอต่อการละลายอนุภาคแกมมาไพรม์แบบหยาบให้กลับสู่เนื้อพื้นแกมมาได้ สำหรับแนวโน้มของการเติมธาตุผสมทั้งสามต่อขนาดของอนุภาคแกมมาไพรม์และสัดส่วนเชิงพื้นที่ของเฟสแกมมาไพรม์ที่เกิดขึ้นหลังจากการทำกรรมวิธีทางความร้อน มีความใกล้เคียงกับผลที่ได้จากชิ้นงานดั้งเดิมมาก แต่อย่างไรก็ตามค่าต่าง ๆ ที่ได้จากการวิเคราะห์ด้วยภาพถ่าย โดยเฉพาะอย่างยิ่งขนาดของอนุภาคแกมมาไพรม์มีค่าน้อยกว่าชิ้นงานดั้งเดิม