Abstract
The dataset presented in this work, called ORION-AE, is made of raw AE data streams collected by three different AE sensors and a laser vibrometer during five campaigns of measurements by varying the tightening conditions of two bolted plates submitted to harmonic vibration tests. With seven different operating conditions, this dataset was designed to challenge supervised and unsupervised machine/deep learning as well as signal processing methods which are developed for material characterization or structural health monitoring (SHM). One motivation of this work was to create a common benchmark for comparing data-driven methods dedicated to AE data interpretation. The dataset is made of time series collected during an experiment designed to reproduce the loosening phenomenon observed in aeronautics, automotive, or civil engineering structures where parts are assembled together by means of bolted joints. Monitoring loosening in jointed structures during operation remains challenging because contact and friction in bolted joints induce a nonlinear stochastic behavior.
Highlights
The obtained Acoustic emission (AE) data stream is processed by algorithms to detect AE signals related to damages
AE is used in many laboratories for materials characterization [1] and in industrial applications for real-time monitoring of manufacturing process [2] or storage facilities [3]
AE source identification is an inverse problem which is difficult to solve due to the sensitivity of the sensors which provide many AE signals corrupted by noise, as well as due to the effects of wave propagation in damaged materials which creates wave scattering [4]
Summary
The validation of the results obtained in the previous step is performed in a subjective manner because of the lack of prior knowledge of AE sources. The vibrometer data allows users to evaluate the performance of wave-picking algorithms with low signal-to-noise ratio This can be helpful to validate step 1 in the aforementioned methodology. Data Description The dataset was obtained on a test rig called ORION [24,25] It is constituted of a jointed structure, dynamically loaded with a vibration shaker and monitored with acoustic emission, force, and velocity sensors. This figure (red curve) shows that the control of the displacement of the beam by a feedback from the laser vibrometer, (as explained in the “Methods” section,) leads to a similar displacement during a whole test (about 70 s).
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
