Date of Award
12-2020
Document Type
Dissertation
Degree Name
Doctor of Philosophy (PhD)
Department
Department of Electrical and Computer Engineering
First Advisor
Robert F. Mills, PhD
Abstract
In the interest of improving the resilience of cyber-physical control systems to better operate in the presence of various cyber-attacks and/or faults, this dissertation presents a novel controller design based on deep-learning networks. This research lays out a controller design that does not rely on fault or cyber-attack detection. Being passive, the controller’s routine operating process is to take in data from the various components of the physical system, holistically assess the state of the physical system using deep-learning networks and decide the subsequent round of commands from the controller. This use of deep-learning methods in passive fault tolerant control (FTC) is unique in the research literature. The proposed controller is applied to both linear and nonlinear systems. Additionally, the application and testing are accomplished with both actuators and sensors being affected by attacks and /or faults.
AFIT Designator
AFIT-ENG-DS-20-D-013
DTIC Accession Number
AD1124108
Recommended Citation
Wardell, Dean C., "Deep Learning-Based, Passive Fault Tolerant Control Facilitated by a Taxonomy of Cyber-Attack Effects" (2020). Theses and Dissertations. 4536.
https://scholar.afit.edu/etd/4536