Structural Damage Detection with Automatic Feature‐Extraction through Deep Learning

TLDR

Structural damage detection remains challenging due to difficulty extracting damage‑sensitive, noise‑robust features from structural responses. The study proposes a deep‑learning method that automatically extracts features from low‑level sensor data for damage detection. The method uses a deep convolutional neural network to learn features from raw sensor data, and visualizes hidden‑layer representations to provide physical insight into the network’s operation. The network achieves superior damage‑location accuracy on both clean and noisy data compared to a wavelet‑packet‑based detector, and its learned features progress from simple filters to vibration‑mode concepts, explaining its strong performance.

Abstract

Abstract Structural damage detection is still a challenging problem owing to the difficulty of extracting damage‐sensitive and noise‐robust features from structure response. This article presents a novel damage detection approach to automatically extract features from low‐level sensor data through deep learning. A deep convolutional neural network is designed to learn features and identify damage locations, leading to an excellent localization accuracy on both noise‐free and noisy data set, in contrast to another detector using wavelet packet component energy as the input feature. Visualization of the features learned by hidden layers in the network is implemented to get a physical insight into how the network works. It is found the learned features evolve with the depth from rough filters to the concept of vibration mode, implying the good performance results from its ability to learn essential characteristics behind the data.