| DOI | Resolve DOI: https://doi.org/10.1109/TIM.2023.3300463 |
|---|
| Author | Search for: Yun, HongguangORCID identifier: https://orcid.org/0000-0003-4552-2913; Search for: Feng, KeORCID identifier: https://orcid.org/0000-0003-2338-5161; Search for: Rayhana, RakibaORCID identifier: https://orcid.org/0000-0002-1512-4335; Search for: Pant, Shashank1ORCID identifier: https://orcid.org/0000-0003-3271-5011; Search for: Genest, Marc1ORCID identifier: https://orcid.org/0000-0001-6301-6235; Search for: Liu, ZhengORCID identifier: https://orcid.org/0000-0002-7241-3483 |
|---|
| Affiliation | - National Research Council Canada. Aerospace
|
|---|
| Funder | Search for: National Research Council Canada |
|---|
| Format | Text, Article |
|---|
| Subject | composite laminate; damage localization; data fusion; guided wave; neural networks; ultrasonics; location awareness; transducers; feature extraction; data models; artificial neural networks; signal processing; acoustics |
|---|
| Abstract | Ultrasonic guided wave (UGW)-based damage localization on plate-like composite structures plays a vital role in the structural health monitoring (SHM) of aircraft structures. Precisely locating the damage requires full utilization of high-dimensional UGW signals as well as low-dimensional transducer coordinates. However, current deep learning (DL)-based methods cannot incorporate transducer coordinates in the neural networks. To address this issue, this article proposes a novel multidimensional data fusion neural network framework for damage localization on plate-like composite structures using UGW. The proposed framework includes an encoder and a Fourier feature projection head to integrate high-dimensional wave signals and low-dimensional coordinates. A multilayer perceptron (MLP) is adopted as a decoder to learn features from the encoder and the projection head. Comprehensive experiments demonstrate that the proposed method achieves the state-of-the-art results with less than 2 mm absolute distance error. Moreover, a discussion regarding data availability in the training process is performed. The proposed method demonstrates superior robustness over the state-of-the-art methods with limited training data. |
|---|
| Publication date | 2023-08-01 |
|---|
| Publisher | IEEE |
|---|
| In | |
|---|
| Language | English |
|---|
| Peer reviewed | Yes |
|---|
| Export citation | Export as RIS |
|---|
| Report a correction | Report a correction (opens in a new tab) |
|---|
| Record identifier | 803fe418-6e53-4ab4-b360-918db732418a |
|---|
| Record created | 2024-06-27 |
|---|
| Record modified | 2025-11-03 |
|---|
