Dataset: Impact Events for Structural Health Monitoring of a Plastic Thin Plate

This repository contains a novel time-series dataset for impact detection and localization on a plastic thin-plate, towards Structural Health Monitoring applications, using ceramic piezoelectric transducers (PZTs) connected to an Internet of Things (IoT) device. The dataset was collected from an experimental procedure of low-velocity, low-energy impact events that includes at least 3 repetitions for each unique experiment, while the input measurements come from 4 PZT sensors placed at the corners of the plate. For each repetition and sensor, 5000 values are stored with 100 KHz sampling rate. The system is excited with a steel ball, and the height from which it is released varies from 10 cm to 20 cm.

To the best of our knowledge, we are the first, to publish a public dataset that contains PZT sensors measurements concerning low-velocity, low-energy impact events in a thin plastic plate. In addition, we also contribute with our methodology on data collection using an SHM IoT system with resource constraints (based on Arduino NANO 33 MCU), as opposed to the majority of the literature that uses Oscilloscopes for data acquisition. This concept of an MCU-based system for data collection in SHM is especially important nowadays, due to the fast rise of extreme-edge and embedded machine learning practices solutions that enable a variety of real-time data-driven SHM applications. Finally, we wish to highlight that by using this specific Microcontroller Unit (MCU) and sensors, the proposed implementation aims for an overall low-cost data collection solution.

The dataset has been published as a dataset paper in 20th ACM Conference on Embedded Networked Sensor Systems (SenSys 2022), in the following workshop:  The Fifth International Workshop on Data: Acquisition To Analysis (DATA '22).

The dataset is also available at https://github.com/Smart-Objects/Impact-Events-Dataset.