System Identification at the Extreme Edge for SHM

In this collaborative work, led by Federica Zonzini (Uni Bologna), with Dr. Vasilis Dertimanis (SMM group), Eleni Chatzi (SMM group) and Luca De March (Uni Bologna), we explore System ID at the Extreme Edge. Mechanical complexity, wide dimensions and big data volume may hamper the implementation of Internet-of-Things (IoT)-enabled Structural Health Monitoring (SHM) systems. One of the most important challenges lies in reduction of the data payload to be transmitted over the monitoring network.

Addressing the problem in the context of vibration-based SHM, this work explores System Identification (SysId) based on autoregressive models as an innovative strategy for data compression at the extreme edge. This parametric model-based SysId is a signal processing technique aiming at finding a very reduced (i.e., less then one tenth of the total signal length) set of meaningful parameters, which can provide an alternative, yet completely equivalent, frequency characterization of the structure. In the proposed approach, an embedded system-oriented adaptation of the Sequential Tall-Skinny QR decomposition (eS-TSQR) from the dense linear algebra domain has been exploited to tackle both the memory and computational complexity of the involved algorithms. This allows for embedment of input--output and output-only SysId models into a resource constrained device (i.e., an STM32L5 microcontoller unit), targeted on low-power and low-cost SHM applications, proving high effectiveness for the structural assessment of civil and industrial plants.

A cost-benefit analysis is further presented, in which the energy saving brought by SysId running in a sensor-near manner is comprehensively measured against the power consumption due to data transmission, as implied by state-of-the-art communication protocols for IoT. Results demonstrate that SysId is 1.19x and 2.78x less energy demanding (with a payload reduction of 9x and 45x) w.r.t. compressed sensing-driven and compression-free solutions, respectively.
 

read more in the latest external page IEEE Internet of Things Journal issue