Fatigue experiments were conducted on aluminum lap-joint specimens, and lamb wave signals were recorded for each specimen at several time points (i.e., defined as number of cycles in fatigue testing). Signals from piezo actuator-receiver sensor pairs were reported and it was observed that these signals were directly related to the crack lengths developed during fatigue testing. Optical measurements of surface crack lengths are also provided as the ground truth. The data set is split in training and validation to facilitate the application of data-driven methods.
This data set was generated at Arizona State University by Prof. Yongming Liu, Dr. Tishun Peng, and their collaborators. The data set was used for the Prognostics Health Management (PHM) Data Challenge for the 2019 Conference on Prognostics and Health Management. Other than the data set authors, the following individuals helped put together the 2019 PHM data challenge and make the data set publicly available: Matteo Corbetta and Portia Banerjee (KBR, Inc, NASA Ames), Kurt Doughty (Collins Aerospace), Kai Goebel (PARC), and Scott Clements (Lockheed Martin).
Data Set Citation:
Peng T, He J, Xiang Y, Liu Y, Saxena A, Celaya J, Goebel K. Probabilistic fatigue damage prognosis of lap joint using Bayesian updating. Journal of Intelligent Material Systems and Structures. 2015 May;26(8):965-79.
Publication Citation:
He J, Guan X, Peng T, Liu Y, Saxena A, Celaya J, Goebel K. A multi-feature integration method for fatigue crack detection and crack length estimation in riveted lap joints using Lamb waves. Smart Materials and Structures. 2013 Sep 4;22(10):105007.