Parallel convolutional neural network toward high efficiency and robust structural damage identification

Abstract

Artificial intelligence has been implemented recently for processing and analyzing monitored data for damage detection and identification in the field of structural health monitoring (SHM). Existing machine learning methods such as convolutional neural networks (CNNs) usually rely on inputs from a single domain (time or frequency), which may only provide partial information for damage identification. To address this issue, this work proposes a parallel convolutional neural network (P-CNN) that extracts multidimensional features assisted by a computer vision technique. The proposed network comprises a one-dimensional (1D) CNN branch, a two-dimensional (2D) CNN branch, and several fully connected layers. The efficiency and robustness of the proposed network were validated by a public experimental dataset. Our results show that (1) the features extracted by the P-CNN were separated more easily compared with those by 1D-CNN or 2D-CNN; (2) when detecting structural damages, the accuracy of the P-CNN is above 99.4%; (3) the P-CNN exhibits a robust performance when subjected to a high (5 dB) signal-to-noise ratio of the original data; and (4) when compared with traditionally used methods such as GoogLenet and Resnet, the P-CNN outperforms on many aspects of damage identification. We envision that the proposed P-CNN can be integrated into advanced SHM systems with high fidelity and intelligence.

Study of structural damage identification through various convolutional neural network models: exploring the accuracy and efficiency

“…For one-dimensional vector data, Z-score normalization can be utilized to enhance the generalization capability of the detector [5] . The specific steps are as follows:…”

“…where * represents the complex conjugate. More details regarding continuous wavelet transform (CWT) could refer to [5] . Figure 6 is a sample of the wavelet signal.…”

“…However, it is important to note that some data may be lost during the information processing due to the implement noise. Based on this, PCNN has been proposed [5] . This type of network can integrate one-dimensional and two-dimensional data, allowing for input of data with more damage characteristics while reducing data loss.…”