Abstract
Ultrasonic nondestructive testing is a promising method for performing damage assessments on concrete subjected to alkali-silica reactions (ASRs). Previous research incorporated only some ultrasonic wave parameters, and the other information from the ultrasonic signals was discarded. In this work, 13 features, including wave velocity and wavelet features, were extracted from the ultrasonic signals. A curve-fitting method was used to fit a polynomial relationship between the wave velocity and expansion of one concrete sample subjected to ASR to predict the expansion of another concrete sample subjected to ASR. Support vector regression (SVR), a machine learning model, was trained using all 13 features derived from the ultrasonic data obtained from the ASR samples. The SVR was then tested using the datasets from the ASR-2D sample. The performance showed that the curve-fitting method and the SVR had poor prediction results on the expansion of the ASR-2D sample. With feature selection, the performance of the SVR model using six selected features was significantly improved.
Original language | English |
---|---|
Title of host publication | Structural Health Monitoring 2021 |
Subtitle of host publication | Enabling Next-Generation SHM for Cyber-Physical Systems - Proceedings of the 13th International Workshop on Structural Health Monitoring, IWSHM 2021 |
Editors | Saman Farhangdoust, Alfredo Guemes, Fu-Kuo Chang |
Publisher | DEStech Publications Inc. |
Pages | 729-736 |
Number of pages | 8 |
ISBN (Electronic) | 9781605956879 |
State | Published - 2021 |
Event | 13th International Workshop on Structural Health Monitoring: Enabling Next-Generation SHM for Cyber-Physical Systems, IWSHM 2021 - Stanford, United States Duration: Mar 15 2022 → Mar 17 2022 |
Publication series
Name | Structural Health Monitoring 2021: Enabling Next-Generation SHM for Cyber-Physical Systems - Proceedings of the 13th International Workshop on Structural Health Monitoring, IWSHM 2021 |
---|
Conference
Conference | 13th International Workshop on Structural Health Monitoring: Enabling Next-Generation SHM for Cyber-Physical Systems, IWSHM 2021 |
---|---|
Country/Territory | United States |
City | Stanford |
Period | 03/15/22 → 03/17/22 |
Funding
Notice: This manuscript has been authored by UT-Battelle, LLC, under contract DE-AC05-00OR22725 with the US Department of Energy (DOE). The publisher acknowledges the US government license to provide public access under the DOE Public Access Plan (http://energy.gov/downloads/doe-public-access-plan). Hongbin Sun, Oak Ridge National Laboratory, 1 Bethel Valley Rd., Oak Ridge, TN, 37830, USA. Jinying Zhu, University of Nebraska-Lincoln, 1110 S 67th St., Omaha, NE, 68182, USA. Pradeep Ramuhalli, Oak Ridge National Laboratory, 1 Bethel Valley Rd., Oak Ridge, TN, 37830, USA. The experiment data was collected during the first author’s Ph.D. study and it was supported by the U.S. Department of Energy-Nuclear Energy University Program (NEUP) under Contract No. DE-NE0008544.