Date Approved
5-16-2025
Graduate Degree Type
Thesis
Degree Name
Engineering (M.S.E.)
Degree Program
School of Engineering
First Advisor
Dr. Brian Krug
Second Advisor
Dr. Nicholas Baine
Third Advisor
Dr. Farid Jafari
Academic Year
2024/2025
Abstract
This study demonstrates that it is possible to use road surface classification as a means of informing active suspension systems in order to limit their activity. An approach was taken to improve the response of an active suspension control system by classifying road surfaces in near real time. A control system model was developed to represent a full-body vehicle, and an AI was used to analyze road vibration noise. The model was adapted to allow the AI to select from multiple control signals based on the AI’s analysis of road vibration noise. The objective of the study was to demonstrate whether an AI could limit the use of an active suspension system to periods of where vibration energy from a road surface exceeded an identifiable threshold. The AI was successful in classifying road surfaces and in using that classification to identify whether vibration energy exceeded a specified threshold. The AI was subsequently successful in using the adapted control model to limit the use of the active suspension system to periods of activity in which vibration noise exceeded the specified threshold.
ScholarWorks Citation
Butz, David A., "Effect of Using Machine Learning to Improve Active Suspension Control for Vehicle Stability" (2025). Masters Theses. 1143.
https://scholarworks.gvsu.edu/theses/1143
