Yildirim receives NSF CRII grant to better leverage vehicle sensor data for fleet operations

Murat Yildirim and a Ph.D. student looking at data on a laptop

Modern vehicles produce roughly 25 gigabytes of data per hour, a figure that will grow exponentially as autonomous and connected vehicles become more pervasive. Vehicular sensor data is generating a wealth of information that can be used to develop accurate predictions on vehicle health. To date, it remains a key challenge to integrate these predictions into large-scale decision optimization models to improve fleet-level operations.

Murat Yildirim, assistant professor of industrial and systems engineering at Wayne State University, is working to harness the full value of this data as they apply to vehicle fleet management. His project, "A Decentralized and Differentially Private Framework for Sensing, Operations and Respond Logistics in Large-Scale Vehicle Fleets," was awarded a two-year, $173,977 grant through the National Science Foundation's Computer and Information Science and Engineering Research Initiation Initiative. This prestigious, highly competitive grant is awarded to early-career investigators to launch their research and academic careers.

Harnessing the true value of sensor data in a fleet management application requires an integrated and detailed modeling of fleet-level interactions, along with a seamless integration of sensor-driven learning and decision-making capabilities. “There are significant and dynamic interdependencies in large-scale vehicle fleets that include continuous component-to-component interactions in degradation and failure risks; dependencies across vehicles related to operational coordination and use of shared resources; and interactions between spare part logistics, maintenance, and operations,” said Yildirim.

This project focuses on developing a decentralized and differentially private decision-making framework that integrates sensor-driven asset life predictions within a joint decision optimization model to identify optimal operations, maintenance and spare part logistics schedule. The proposed framework explicitly models dynamically evolving predictions on vehicle condition, failure risks and other operational uncertainties.

The award number for this NSF grant is 2104455.


← Back to listing