Spiking Neural Network-Based Near-Sensor Computing for Damage Detection in Structural Health Monitoring

Abstract

In this work, we present an innovative approach for damage detection of infrastructures on-edge devices, exploiting a brain-inspired algorithm. The proposed solution exploits recurrent spiking neural networks (LSNNs), which are emerging for their theoretical energy efficiency and compactness, to recognise damage conditions by processing data from low-cost accelerometers (MEMS) directly on the sensor node. We focus on designing an efficient coding of MEMS data to optimise SNN execution on a low-power microcontroller. We characterised and profiled LSNN performance and energy consumption on a hardware prototype sensor node equipped with an STM32 embedded microcontroller and a digital MEMS accelerometer. We used a hardware-in-the-loop environment with virtual sensors generating data on an SPI interface connected to the physical microcontroller to evaluate the system with a data stream from a real viaduct. We exploited this environment also to study the impact of different on-sensor encoding techniques, mimicking a bio-inspired sensor able to generate events instead of accelerations. Obtained results show that the proposed optimised embedded LSNN (eLSNN), when using a spike-based input encoding technique, achieves 54% lower execution time with respect to a naive LSNN algorithm implementation present in the state-of-the-art. The optimised eLSNN requires around 47 kCycles, which is comparable with the data transfer cost from the SPI interface. However, the spike-based encoding technique requires considerably larger input vectors to get the same classification accuracy, resulting in a longer pre-processing and sensor access time. Overall the event-based encoding techniques leads to a longer execution time (1.49×) but similar energy consumption. Moving this coding on the sensor can remove this limitation leading to an overall more energy-efficient monitoring system.

Intrusion detection method for internet of things based on the spiking neural network and decision tree method

“…In [31], a supervised method is proposed for near-sensor abnormality detection via using a longshortened time period long short-term memory spiking neural networks (LSNN), approach. In LSNN, two classes of signals are classified: healthy and sanitary by using the backpropagation through time (BPTT) technique.…”

A sparse, triangle-shaped sensor array for damage orientation and characterization of composite structures

“…The three sensors of the sparse sensor array form a equilateral triangle. According to the sum and delay algorithm [22][23][24], three damage probability ellipses can be depicted based on the three sensors and the damage position can be pinpointed based on these ellipses. Compared with conventional sensor networks for large-scale structures, a much simpler sensing network can be arranged in each monitoring region by using the proposed triangle-shaped sensor array, as shown in figure 4.…”

Wireless Internet, Multimedia, and Artificial Intelligence: New Applications and Infrastructures

“…An example of this is the work in [1], where the authors present an innovative approach for damage detection of infrastructures on-edge devices by exploiting a braininspired algorithm, or in [2], where, instead, two techniques aimed at supporting the user in making privacy choices about sharing personal content online have been proposed by the authors. Another interesting work, which aimed to estimate the perceived quality of service (PQoS) of video conferencing using only 802.11-specific network performance parameters collected from Wi-Fi access points (APs) on customer premises, has been proposed in [3].…”