AI- Enabled Multi-modality Sensing and Data Analytics for Infrastructure Safety
Interdisciplinary Areas: | Data and Engineering Applications, Autonomous and Connected Systems, Smart City, Infrastructure, Transportation |
---|
Project Description
The aging US infrastructure poses significant risks to public safety and the quality of life of its citizens.
Out of about 6 million bridges in the US, 9% are structurally deficient and 13.6% are obsolete, as per
the 2017 Infrastructure Report Card by the American Society of Civil Engineers. On average 180 million trips are still made across each structurally deficient bridge per day causing significant safety
concerns. The lack of accurate real-time information on infrastructure conditions and coordination with traffic flow has resulted in significant loss of lives, time, money, and resources in the United States. The challenge concerning infrastructure safety has become more urgent and critical.
To address these urgent challenges and ensure the safety and prosperity of the US infrastructure
system, and economy, this project aims to build a scalable, coordinated, and AI-based network to acquire real-time infrastructure conditions data, adopt distributed algorithms for scalability. This will be achieved by real-time sensing and monitoring of infrastructure conditions, systematic data processing of infrastructure through machine learning, distributed optimization of heterogeneous sensor networks.
The candidate will work with an interdisciplinary team from Civil Engineering (Luna Lu) and Mechanical Engineering/Mathematics/Statistics (Guang Lin) with expertise in infrastructure materials, structural and materials sensing, data sciences, and machine learning.
Start Date
05/01/2021
Postdoc Qualifications
The postdoc researcher should be research background in the area of materials and mechanics, infrastructure and materials sensing, or machine learning / data science. we strongly encourage applicants from minority and under-represented groups.
Co-Advisors
Prof. Luna Lu from Civil Engineering
Prof. Guang Lin from Mechanical Engineering
References
Su, Y. F., Han, G., Nantung, T. & Lu, N. Novel methodology on direct extraction of the strength information from cementitious materials using piezo-sensor based electromechanical impedance (EMI) method. Constr. Build. Mater. 259, 119848 (2020).
Su, Y., Han, G., Kong, Z., Nantung, T. & Lu, N. Embeddable Piezoelectric Sensors for Strength Gain Monitoring of Cementitious Materials : The Influence of Coating Materials. Eng. Sci. 1–33 (2020).
Kong, Z. & Lu, N. Improved Method to Determine Young’s Modulus for Concrete Cylinder Using Electromechanical Spectrum: Principle and Validation. J. Aerosp. Eng. 33, 04020079 (2020).
Winovich, N., Ramani, K. & Lin, G. ConvPDE-UQ: Convolutional neural networks with quantified uncertainty for heterogeneous elliptic partial differential equations on varied domains. J. Comput. Phys. 394, 263–279 (2019).
Zhang, B., Konomi, B. A., Sang, H., Karagiannis, G. & Lin, G. Full scale multi-output Gaussian process emulator with nonseparable auto-covariance functions. J. Comput. Phys. 300, 623–642 (2015).