In nature, two species often interact to their mutual benefit. Birds called oxpeckers, for example, ride around on the backs of large grazing animals like rhinos and zebras, eating parasites such as the ticks and flies that pester their hosts. In a new research project led by CEE Professor Nora El-Gohary, this principle of “mutualism” is being applied to improve damage sensing in infrastructure through the development of a new cyber-physical system, thanks to a $1.2 million grant from the National Science Foundation (NSF).
“Drawing inspiration from mutualism in biology where two species interact in a way that benefits both, the cyber and the physical interact in a way that they simultaneously benefit from and contribute to each other to enhance the ability of a Cyber-Physical System (CPS) to predict, reconfigure and adapt,” El-Gohary writes.
The CPS envisioned by El-Gohary’s project will feature three integrated components: (1) data-driven, knowledge-informed deep learning methods for generalizable damage prognostics to predict the onset and propagation of infrastructure damages, providing information about target damages to inform reconfigurable sensing, (2) signal difference maximization theory-based reconfigurable sensing methods to optimize and physically control the configurations of the sensors to actively seek to monitor each of the predicted target damages, providing damage-seeking feedback to inform damage prognostics, and (3) quality-aware edge cloud computing methods for efficient and effective damage information extraction from raw sensing signals, serving as the bridge between damage prognostics and reconfigurable sensing.
Cyber-physical systems “are transforming the way people interact with engineered systems,” according to NSF. “Cyber-physical systems integrate sensing, computation, control and networking into physical objects and infrastructure, connecting them to the Internet and to each other.”
The proposed CPS will be tested in multi-damage monitoring of bridges using simulation-based and actual CPS prototypes; and would be generalized to monitoring other civil infrastructure in the future. The proposed CPS methods have the potential to transform the way we design, create and operate CPS to enable the next-generation CPS that have greater predictive ability, reconfigurability and adaptability, El-Gohary writes.
In the civil infrastructure systems domain, the mutualistic interaction-enabled CPS will allow for reconfiguring a single type of sensor, adaptively based on damage prognostics, to monitor multiple classes of infrastructure damages – thereby improving the cost-effectiveness of multi-damage infrastructure monitoring by reducing the types and number of sensors needed and maximizing the timeliness and accuracy of damage assessment and prediction at the same time.
El-Gohary is collaborating with University of Illinois Department of Computer Science Professor Vikram Adve and with Stevens Institute of Technology.