Controls and Control Theory Commons^™

Bitcoin Price Prediction Using Neural Networks, Vladislav Killiakov

Electrical Engineering

In this project, I will investigate the performance of several major neural network architectures for the task of Bitcoin price prediction. Bitcoin is a cryptocurrency that is recently becoming increasingly more popular, and more widely adopted as a financial instrument. As a result, more efforts have been made in the past several years to model and predict its price. However, to this moment a large portion of work on Bitcoin price modeling was done using statistical or classical machine learning techniques. At the same time, other artificial intelligence based prediction techniques, and specifically neural networks, have not been explored to …

An Application Of Sliding Mode Control To Model-Based Reinforcement Learning, Aaron Thomas Parisi

Master's Theses

The state-of-art model-free reinforcement learning algorithms can generate admissible controls for complicated systems with no prior knowledge of the system dynamics, so long as sufficient (oftentimes millions) of samples are available from the environ- ment. On the other hand, model-based reinforcement learning approaches seek to leverage known optimal or robust control to reinforcement learning tasks by mod- elling the system dynamics and applying well established control algorithms to the system model. Sliding-mode controllers are robust to system disturbance and modelling errors, and have been widely used for high-order nonlinear system control. This thesis studies the application of sliding mode control …

Utilizing Trajectory Optimization In The Training Of Neural Network Controllers, Nicholas Kimball

Master's Theses

Applying reinforcement learning to control systems enables the use of machine learning to develop elegant and efficient control laws. Coupled with the representational power of neural networks, reinforcement learning algorithms can learn complex policies that can be difficult to emulate using traditional control system design approaches. In this thesis, three different model-free reinforcement learning algorithms, including Monte Carlo Control, REINFORCE with baseline, and Guided Policy Search are compared in simulated, continuous action-space environments. The results show that the Guided Policy Search algorithm is able to learn a desired control policy much faster than the other algorithms. In the inverted pendulum …

Flight Director Embedded System And Mobile Ios Application, Anthony Epshteyn

Computer Engineering

For my senior project, I was asked to assist an Aerospace Engineering professor with the design of his new glider. He needed to create a flight director-type instrument so that his pilot could get the aircraft’s positional data during flight. This positional data came from a powerful sensor mounted on the fuselage. To interface with the sensor, I created an embedded system comprised of a ESP32 micro-controller communicating with the sensor via UART/RS-232. The micro-controller was mounted on a breadboard and connected to the sensor via jumper wires. The ESP32 featured a Bluetooth chip that allowed for communication using the …

Weight Controlled Electric Skateboard, Zachary Barram, Carson Bertozzi, Vishnu Dodballapur

Computer Engineering

Technology and the way that humans interact is becoming more vital and omnipresent with every passing day. However, human interface device designers suffer from the increasingly popular “designed for me or people like me” syndrome. This design philosophy inherently limits accessibility and usability of technology to those like the designer. This places severe limits of usability to those who are not fully able as well as leaves non-traditional human interface devices unexplored. This project set out to explore a previously uncharted human interface device, on an electric skateboard, and compare it send user experience with industry leading human interface devices.

Viewpoint Optimization For Autonomous Strawberry Harvesting With Deep Reinforcement Learning, Jonathon J. Sather

Master's Theses

Autonomous harvesting may provide a viable solution to mounting labor pressures in the United States' strawberry industry. However, due to bottlenecks in machine perception and economic viability, a profitable and commercially adopted strawberry harvesting system remains elusive. In this research, we explore the feasibility of using deep reinforcement learning to overcome these bottlenecks and develop a practical algorithm to address the sub-objective of viewpoint optimization, or the development of a control policy to direct a camera to favorable vantage points for autonomous harvesting. We evaluate the algorithm's performance in a custom, open-source simulated environment and observe affirmative results. Our trained …

Underwater Remotely Operated Vehicle Controller With Pid Stability Regulation, Christian E. Aguirre

Electrical Engineering

The earth’s oceans and rivers remain widely unexplored. Hobbyists and companies across the globe invest money and resources into remotely operated vehicles (ROV) to further expand underwater knowledge. Each ROV includes a controller that operates motors and monitors other crucial system vitals. The ROV Controller project makes the process of designing an ROV simpler and more affordable by providing a multi-purpose programmable controller.

The ROV controller features programmable digital inputs/outputs and analog inputs. The controller processes control signals from analog joysticks, digital signals from a gyroscope and utilizes a MUX to expand the analog input capabilities of the Arduino. The …

Asphalt And Adhesive Flow And Level Control, Kajan V. Moorthy

Electrical Engineering

This project entails the design of a flow control system to manage flow rates of asphalt to maintain constant thickness on the fiberglass sheet. By using the proposed system, the amount of scrap created by extremely thick or thin deposits on the mat would be reduced. The design of the proposed system aims to produce a flowrate of 10 gpm while it is also capable of self-correcting and shutting down when unsafe conditions occur. Selection of various components of the control system took place which included the Allen Bradley PLC and Flex I/O, power supply, radars for level sensor, and …

Brushless Direct Current Motor Control For Inspired Flight, Aidan James Mccoy

Computer Science and Software Engineering

Brushless direct current motors have become a very common part of many modern electronics. Although they are more expensive and less robust than conventional brushed direct current motors, they provide large advantages in control, power output, longevity as well as efficiency. To make these motors run, they need more than just power. Each motor needs a separate motor controller that is responsible for taking in a signal for what speed/torque to run the motor at, and then managing the current flow to the motor to keep it spinning while fitting within these boundaries. Brushless direct current motors have a set …

Dynamics Simulation And Optimal Control Of A Multiple-Input And Multiple-Output Balancing Cube, Felix K. Haimerl

Master's Theses

This thesis document outlines the development of a multibody dynamics simulation of an actively stabilized multiple-input, multiple-output, coupled, balancing cube and the process of verifying the results by implementing the control algorithm in hardware. A non-linear simulation of the system was created in Simscape and used to develop a Linear Quadratic Gaussian control algorithm. To implement this algorithm in actual hardware, the system was first designed, manufactured, and assembled. The structure of the cube and the reaction wheels were milled from aluminum. DC brushless motors were installed into the mechanical system. In terms of electronics, a processor, orientation sensor, motor …

Towards Autonomous Localization Of An Underwater Drone, Nathan Sfard

Master's Theses

Autonomous vehicle navigation is a complex and challenging task. Land and aerial vehicles often use highly accurate GPS sensors to localize themselves in their environments. These sensors are ineffective in underwater environments due to signal attenuation. Autonomous underwater vehicles utilize one or more of the following approaches for successful localization and navigation: inertial/dead-reckoning, acoustic signals, and geophysical data. This thesis examines autonomous localization in a simulated environment for an OpenROV Underwater Drone using a Kalman Filter. This filter performs state estimation for a dead reckoning system exhibiting an additive error in location measurements. We evaluate the accuracy of this Kalman …

Artificial Neural Network-Based Robotic Control, Justin Ng

Master's Theses

Artificial neural networks (ANNs) are highly-capable alternatives to traditional problem solving schemes due to their ability to solve non-linear systems with a nonalgorithmic approach. The applications of ANNs range from process control to pattern recognition and, with increasing importance, robotics. This paper demonstrates continuous control of a robot using the deep deterministic policy gradients (DDPG) algorithm, an actor-critic reinforcement learning strategy, originally conceived by Google DeepMind. After training, the robot performs controlled locomotion within an enclosed area. The paper also details the robot design process and explores the challenges of implementation in a real-time system.

Microgrid Protection Student Laboratory: Human-Machine Interface And Scada Database, Nathan P. Martinez

Electrical Engineering

The electric utility system, a ubiquitous and fundamental component of modern life, has changed more in the last 20 years than the last 100. With more homes and businesses installing distributed energy resources (DERs) such as solar panels, battery storage, and other intermittent sources, massive changes need to take place in the electric transmission and distribution systems. Engineers must develop a new skill set for a modern utility industry. This project summarizes a component for a new laboratory class aimed at power engineering students at Cal Poly which supports the laboratory through the creation of a human-machine interface (HMI) and …

Real Time And High Fidelity Quadcopter Tracking System, Tyler Mckay Hall

Computer Engineering

This project was conceived as a desired to have an affordable, flexible and physically compact tracking system for high accuracy spatial and orientation tracking. Specifically, this implementation is focused on providing a low cost motion capture system for future research. It is a tool to enable the further creation of systems that would require the use of accurate placement of landing pads, payload acquires and delivery. This system will provide the quadcopter platform a coordinate system that can be used in addition to GPS.

Field research with quadcopter manufacturers, photographers, agriculture and research organizations were contact and interviewed for information …

Flexible Custom Electric Skateboard, Caleb Adam Kelsay

Electrical Engineering

At Cal Poly traveling long distances only accessible by foot such as across campus or from the car park to class can be tiring and time-consuming. While not physically demanding, the trek consumes time in our tight college life schedule. To improve our time efficiency this project provides a relatively lightweight, powered solution to quickly and effectively travel long distances while maintaining full control and safety even on hills, a current limitation of traditional skateboards.

This electric skateboard includes the battery capacity to travel all around campus on a single charge with a compact and flexible skateboard design that provides …

Two Senior Projects: 2.4 Ghz, 40% Efficiency Radio Frequency Amplifier, Ieee Design Contest, & Design And Implementation Of A Software Costas Loop For Audio Frequencies, Robert J. Tong

Electrical Engineering

How to Read this Document:

This document combines two senior project reports. The first senior project documents designing a class AB RF amplifier. The second, discusses the design and implementation of a software Costas loop for audio frequencies. The first report begins on the next page, while the Costas loop report starts on page 24. The two reports are orthogonal from one another. It is not a prerequisite to read the RF amplifier report before reading the Costas loop report. This document is merely two reports combined into one document. The second report, about the Costas loop, was written as …

Modeling And Charging Control Of A Lithium Ion Battery System For Solar Panels, Garrett David Heinen

Master's Theses

The advancement in solar panel and battery technology makes them useful for energy supply and storage. This thesis involves the modeling and charging control of a lithium ion battery system for solar panels. The proposed model is based on the parameters and characteristics of a realistic battery and solar panel system; and the hybrid control approach combines the advantages of the adaptive incremental conductance method and the perturb and observe method to track the maximum power point of the solar panel for charging the battery unit. Computer simulation results demonstrate that this proposed approach offers a faster convergence rate than …

Acceleration Amplitude Control System For Oscillating Silicon Oil Physics Experiment, Eric Chen

Electrical Engineering

This project is an ‘acceleration amplitude control system’ for use in an ‘oscillating silicon oil physics experiment’. The physics experiment has a tray of silicon oil. This tray must oscillate vertically at a specific amplitude (either at or just below the level for Faraday Waves). This control systems manages taking measurements of acceleration amplitude, and also manages correcting the shaker’s driving signal to obtain the correct acceleration. Features of the control system are designed for ease of use, because the system will mostly be operated by professor/ students without background knowledge in electrical engineering.

Dc House Energy Management System, Zachary L. Eldredge, Zoe M. Hay

Electrical Engineering

In this work, a previously completed proof of concept for an Energy Management System (EMS) for the DC House project has been revised and re-implemented. The implemented design changes will improve the performance and reproducibility of the system. This new design of the EMS replaces the two-separate buck and boost DC-DC converters with a single bidirectional DC-DC converter to reduce components and improve efficiency. Analysis of the bidirectional DC-DC converter shows high efficiency especially at larger load currents. The code of the previous work was updated for smoother operation as well as to accommodate an LCD capable of displaying more …

Dc-Dc Converter Control System For The Energy Harvesting From Exercise Machines System, Alexander Sireci

Master's Theses

Current exercise machines create resistance to motion and dissipate energy as heat. Some companies create ways to harness this energy, but not cost-effectively. The Energy Harvesting from Exercise Machines (EHFEM) project reduces the cost of harnessing the renewable energy. The system architecture includes the elliptical exercise machines outputting power to DC-DC converters, which then connects to the microinverters. All microinverter outputs tie together and then connect to the grid. The control system, placed around the DC-DC converters, quickly detects changes in current, and limits the current to prevent the DC-DC converters and microinverters from entering failure states.

An artificial neural …

Light Sensing Automated Blinds, Andrew B. Hodges, Ryan C. Flick

Electrical Engineering

This project is solving the problem of wasted energy within buildings and homes, because currently the lights turned on inside building do not utilize natural, ambient light from the sun. Rather than having unnecessary light from a light source, the automated light sensing smart blinds can sense the amount of light outside the window and in the room, and then adjust the angle of the blinds to save energy by utilizing the available outdoor light. This way, the light source will not be running at maximum power output while there is excess light coming through the window. This project aims …

Mini High Temperature Test Unit Final Design Report, Kevin Liu, Juan P. Castillo

Mechanical Engineering

Lawrence Livermore National Laboratory has invested considerable effort to develop new standard for nuclear grade HEPA filters that can withstand high temperatures along with methods to optimally test not only the experimental filter media, but also new frame seals and media binders. Therefore, LLNL in collaboration with Cal Poly has designed and built a Mini High Temperature Testing Unit (MHTTU) to recreate conditions observed during a fire and to test different materials in an effective, inexpensive, regulated and reliable method. The existing prototype was unable to achieve the ideal testing conditions of 1000°F air at the low flow rates of …

Optimizing Control Of Shell Eco-Marathon Prototype Vehicle To Minimize Fuel Consumption, Chad Louis Bickel

Master's Theses

Every year the automotive industry strives to increase fuel efficiency in vehicles. When most vehicles are designed, fuel efficiency cannot always come first. The Shell Eco-marathon changes that by challenging students everywhere to develop the most fuel-efficient vehicle possible. There are many different factors that affect fuel efficiency, and different teams focus on different vehicle parameters. Currently, there is no straightforward design tool that can be used to help in Shell Eco-marathon vehicle design. For this reason, it is difficult to optimize every vehicle parameter for maximum fuel efficiency.

In this study, a simulation is developed by using basic vehicle …

Automatic Water Pump Controller, Alam D. Salguero, Kyle Russell Marquez Weeks

Electrical Engineering

In countries including Indonesia, Mexico, Guatemala, and El Salvador, a city water authority supplies the clean water and pumps it into large ground-level storage tanks. A resident’s water pump then pumps the water to a water tank on top of his/her house. When the water level in the ground-level storage tank becomes too low, the pump siphons air and shuts down, requiring a resident to manually prime the water pump to get it running again. Residents struggle to monitor the water level of the tanks effectively and keep the pump running properly. To remedy the issue, the Automatic Water Pump …

A Stroke Therapy Brace Design, Evan Kirkbride

Electrical Engineering

Victims of stroke often have difficulty with rehabilitation. With limited movement on their affected arm, patients often do not want to move much for physical therapy. In this project, we design a robotic brace that helps stroke patients move their arm more effectively in a reaching or pulling motion. By giving patients more movement in their affected arm than they would have otherwise, patients gain more from rehabilitation. The brace also adapts to the patient’s needs, providing more inclination or resistance as needed for their physical therapy. This kind of therapy engages patients rather than relying on their likely dwindled …

Cal Poly Supermileage Electronic Fuel Injection, Alexander Pink

Electrical Engineering

Cal Poly Supermileage is a student-run engineering club that builds prototype gasoline vehicles optimized maximum fuel-efficiency. To power their vehicles, the Supermileage team makes use of single-cylinder, 4-stroke, electronically fuel-injected (EFI) gasoline engines. This report details the development, iterative design & test cycles, and integration of an EFI system for the Supermileage club. This project develops an EFI system that interfaces to the most common types of sensors found in the low-power Supermileage-range of engines, including throttle-position sensors, manifold absolute pressure sensors, gear-tooth hall-effect sensors, variable-reluctance position sensors, engine coolant temperature sensors, intake air temperature sensors, and exhaust oxygen sensors. …

Exertion Control, Travis Taylor

Electrical Engineering

Current wearable fitness devices give the user after-the-fact fitness data, but little real-time feedback. Exertion Control, a new wearable device, continuously measures the user’s heart rate, creates a heart rate target, and helps the user reach it. This project completes the senior design and master’s thesis requirements and contains two milestones. The senior design product continuously measures the wearer’s heart rate and logs it with a user-friendly interface. This data models the heart’s exertion response and recovery response. The master’s thesis device refines the closed control loop with the user to give them a workout optimized to fit their needs.

Out-Of-Loop Compensation Method For Op-Amps Driving Heavy Capacitive Loads, Shubham Gandhi

Master's Theses

It is well known that real op-amps do not share most of the desirable characteristics of an ideal one, particularly those of gain and output impedance. When presented with a capacitive load, such as a MOSFET or ADC, feedback in an op-amp circuit can quickly become unstable. This thesis studies and characterizes an op-amp’s output impedance and how its interaction with this type of load creates a parasitic pole which leads to instability. Applying ideas from feedback control theory, a model for studying the problem is developed from which a generalized method for compensating the undesirable circumstance is formulated.

Even …

A Lidar Based Semi-Autonomous Collision Avoidance System And The Development Of A Hardware-In-The-Loop Simulator To Aid In Algorithm Development And Human Studies, Thomas F. Stevens

Master's Theses

In this paper, the architecture and implementation of an embedded controller for a steering based semi-autonomous collision avoidance system on a 1/10^th scale model is presented. In addition, the development of a 2D hardware-in-the-loop simulator with vehicle dynamics based on the bicycle model is described. The semi-autonomous collision avoidance software is fully contained onboard a single-board computer running embedded GNU/Linux. To eliminate any wired tethers that limit the system’s abilities, the driver operates the vehicle at a user-control-station through a wireless Bluetooth interface. The user-control-station is outfitted with a game-controller that provides standard steering wheel and pedal controls along …

Forest Sign Maker, Victor Espinosa Iii, Kevin Ly, Lisa Yip

Mechanical Engineering

Executive Summary:

The Inyo National Forest is arguably one of the most beautiful locations in California, containing natural masterpieces such as Mount Whitney and the Ancient Bristlecone Pine Forest. Despite its magnificence, the Inyo National Forest can be a treacherous region. The Friends of the Inyo take pride in being able to facilitate the viewing experience for all outdoorsmen by maintaining the mountain trails, which includes providing adequate trail signage.

Unfortunately, there is a fundamental issue with the recent state of trail signage in the Inyo National Forest: the rate at which signs are being vandalized or naturally destroyed is …