Back to search

Georgia Institute of Technology

Utilizing Diagnostic Trouble Codes to Predict Electric Vehicle Battery Integrity Post-Collision

Abstract

dc:description.abstract

Collisions involving electric vehicles (EVs) may compromise the integrity of the battery, a critical and expensive component, thereby significantly reducing the vehicle's residual market value. Current methods of evaluation, such as CARFAX, rely primarily on police reports and service history to evaluate the severity of a collision. However, these reports do not necessarily provide an in-depth assessment of what components were damaged and whether this damage propagates to the battery. This thesis investigates how Diagnostic Trouble Codes (DTCs) can be leveraged to more accurately assess and predict the health of a battery post-collision. DTCs are 5-digit codes indicating a malfunction has been detected within the vehicle and are utilized by all major automotive manufacturers. While DTCs are primarily used for automotive repairs, this thesis explores how DTCs can be leveraged to provide predictive insight to insurers through machine learning applications. By looking at DTCs that occur due to a collision, as well as DTCs that occur within a fixed period after the collision, DTCs will provide a new perspective on how collisions impact the battery and its health over time. This DTC evaluation framework has the potential to be generalized to predict other critical faults such as tire alignment issues and expand to gasoline powered vehicles in future work.

Degree

thesis:*
Level thesis:degree_level
Masters
Department dc:contributor.department
Mechanical Engineering
Grantor dc:publisher
Georgia Institute of Technology
Year dc:date.issued
2025

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • McDonald, Kiyono
Advisor dc:contributor.advisor
  • Tinskey, Mike
Committee members dc:contributor.committeemember
  • Bras, Bert
  • Ramachandran, Karthik

Subjects

dc:subject × 3

Rights

Language dc:language.iso
en_US

Identifiers

dc:identifier.*
Handle dc:identifier.uri
https://hdl.handle.net/1853/81555

Chain of custody

source
Harvested from
Georgia Tech
Base URL
repository.gatech.edu/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

McDonald, Kiyono. Utilizing Diagnostic Trouble Codes to Predict Electric Vehicle Battery Integrity Post-Collision. Masters thesis, Georgia Institute of Technology, 2025. https://hdl.handle.net/1853/81555