I-Corps: Edge Intelligence Platform for Continuous Monitoring in Smart Infrastructures

Texas State University - San Marcos, San Marcos TX

Investigators

Abstract

The broader impact/commercial potential of this I-Corps project is the development of sensor-based surveying used by both mature and emerging industries to solve complicated problems. The proposed solution will improve edge data intelligence efficiency in the most-needed sectors, such as mining and construction, where continuous hazard monitoring is needed to protect people from fatal disasters; geothermal and carbon capture and storage (CCS) facilities where a cost-effective continuous site monitoring is required to scale up; naval applications where real-time and continuous structural monitoring can dramatically reduce vessel sinking causing deaths and catastrophic pollution. When looking at CCS, important considerations include proper site selection and characterization (technical issues) and the overall cost of continuous monitoring (economic issue). These issues hinder scaling up both the volume and the number of injection sites that are required for successful CCS projects. Our solution can significantly reduce uncertainties in site selection and reduce cost by managing large volumes of monitoring data intelligently. This project minimizes a myriad of technical and economic concerns and makes the federal government and private and/or public companies more interested in CCS, which can promote carbon storage towards the number one climate change mitigation approach. Thus, this project will greatly boost the market of continuous monitoring and potentially will deepen our capability to detect, forecast, and prevent environmental and life-threatening risks in many industries.  This I-Corps project is based on the development of a turnkey system with real-time diagnostic and prognostic capabilities. A series of advanced data intelligence modules at the edge (i.e., light-weight data reduction and fusion algorithms), secure sensing architectures (i.e., hardware and edge computing optimization) and cloud-deployable software (i.e., interactive visualization) will be designed to minimize the rigorous setup, time, cost, and complexity that the industry is currently facing when handling, modeling, and visualizing multidimensional data, especially distributed sensing data. This secure and reliable pipeline for high data throughput will satisfy minimum computational complexity, memory consumption, and run-time. The proposed solution is novel and can penetrate the market, because all current technologies are limited as a result of the extremely large data volume. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.