Date of Award
12-2023
Document Type
Thesis
Degree Name
Master of Science (MS)
Department
Electrical and Computer Engineering (Holcomb Dept. of)
Committee Chair/Advisor
Behnaz Papari
Committee Member
Christopher Edrington
Committee Member
Fatemeh Afghah
Abstract
A pathway to prevalence for autonomous electrified transportation is reliant upon accurate and reliable information in the vehicle’s sensor data. This thesis provides insight as to the effective cyber-attack placements on an autonomous electric vehicle’s lateral stability control system (LSCS). Here, Data Integrity Attacks, Replay Attacks, and Denial-of-Service attacks are placed on the sensor data describing the vehicle’s actual yaw-rate and sideslip angle. In this study, there are three different forms of detection methods. These detection methods utilize a residual metric that incorporate sensor data, a state-space observer, and a Neural-Network. The vehicle at hand is a four-motor drive autonomous electric vehicle that is propelled using 4-pole, 3-phase Brushless DC motors. Each motor is controlled using the Direct-Torque control motor control scheme that provides fast output torque response time. This vehicle is controlled via multiple layers of control. A Model Predictive Control Layer is used to discern what lateral trajectory commands minimize the difference between the requested and actual lateral position of the vehicle. These lateral motions are discovered through a Linear-Quadratic Regulator. This study was develop using the MATLAB Simulink environment.
Recommended Citation
Scruggs, Douglas, "Cyber-Threat Detection Strategies Governed by an Observer and a Neural-Network for an Autonomous Electric Vehicle" (2023). All Theses. 4186.
https://tigerprints.clemson.edu/all_theses/4186