Abstract

An application specific multi-platform smartphone application can utilize on-board accelerometer, gyroscope, and GPS sensors, along with software derived signals from the same sensors, to sample vibrational and geolocation datasets to capture pavement distresses such as potholes when mounted in a standardized configuration in a vehicle. Several observations were made with regard to the signals obtained from the accelerometer, gyroscope, and GPS sensors, and it was determined that the raw sensor outputs are capable of sampling statistically significant datasets which can be used to distinguish pavement distress from normal driving conditions. Furthermore, an approximate sensor noise margin is established, and a device specific scaling factor is derived. Finally, a MATLAB trained Optimizable Deep Neural Network was trained using training data collected with the custom-built application, and the favorable results are presented in detail. This system, if utilized in scale, will provide relatively inexpensive pavement condition monitoring and pavement distress classifications and locations in real time, while gathering and cataloging invaluable datasets at scale (big data) for future use, all of which occurs automatically, without the need for specialized equipment or relying on the accuracy of user input.

Date of publication

Fall 10-31-2022

Document Type

Thesis

Language

english

Persistent identifier

http://hdl.handle.net/10950/4098

Committee members

Dr. Mukul Shirvaikar, Dr. Mena Souliman, Dr. Matthew Vechione

Degree

Masters of Science in Electrical Engineering

Available for download on Sunday, December 01, 2024

Share

COinS