Edge Structural Health Monitoring (E-SHM) Using Low-Power Wireless Sensing

Abstract

Effective Structural Health Monitoring (SHM) often requires continuous monitoring to capture changes of features of interest in structures, which are often located far from power sources. A key challenge lies in continuous low-power data transmission from sensors. Despite significant developments in long-range, low-power telecommunication (e.g., LoRa NB-IoT), there are inadequate demonstrative benchmarks for low-power SHM. Damage detection is often based on monitoring features computed from acceleration signals where data are extensive due to the frequency of sampling (~100–500 Hz). Low-power, long-range telecommunications are restricted in both the size and frequency of data packets. However, microcontrollers are becoming more efficient, enabling local computing of damage-sensitive features. This paper demonstrates the implementation of an Edge-SHM framework through low-power, long-range, wireless, low-cost and off-the-shelf components. A bespoke setup is developed with a low-power MEM accelerometer and a microcontroller where frequency and time domain features are computed over set time intervals before sending them to a cloud platform. A cantilever beam excited by an electrodynamic shaker is monitored, where damage is introduced through the controlled loosening of bolts at the fixed boundary, thereby introducing rotation at its fixed end. The results demonstrate how an IoT-driven edge platform can benefit continuous monitoring.

An integrated condition monitoring scheme for health state identification of a multi-stage gearbox through Hurst exponent estimates

“…Since the process is data and output can work for different sensors and devices, and also over different sampling rates, the method can be adapted to future decentralized computing and edge applications, or in solutions involving low power Internet of Things (IoT) framework. 47…”

“…Since the process is data and output can work for different sensors and devices, and also over different sampling rates, the method can be adapted to future decentralized computing and edge applications, or in solutions involving low power Internet of Things (IoT) framework. 47 2. The method is sensor agnostic and lends itself easily to a very wide range of post-processing and statistical learning, thereby creating a detection evidence base which can be used for further implementation in other similar systems and can be adapted to them with minimal site-specific calibration.…”

Spiking Neural Networks for Structural Health Monitoring

“…An optimisation problem of transmission is encountered here because Internet of Things (IoT)-focused networks such as LoRaWAN and Narrowband-IoT suffer from low bandwidth, whereas Wi-Fi suffers from short range [ 7 , 8 , 9 ]. Ideally, if damage-sensitive features (DSFs) [ 10 ] could be extracted from the data at the nodes themselves, the transmission required would be reduced to the feature vectors or their changes [ 11 ]. Methods and algorithms oriented towards this approach, as well as using the harvester itself as a sensor, have been reported [ 12 , 13 , 14 , 15 , 16 ].…”

Context-Aware Edge-Based AI Models for Wireless Sensor Networks—An Overview

“…As new wireless technologies such as WiFi Direct, 5G, Zigbee, LoRa, NB-IoT and LiFi are rapidly being developed, Edge Computing (EC) will soon help transition processing and analysis from the cloud to the edge [ 15 , 16 , 17 ].…”