Crack is an important indicator for evaluating the damage level of concrete structures. However, traditional crack detection algorithms have complex implementation and weak generalization. The existing crack detection algorithms based on deep learning are mostly window-level algorithms with low pixel precision. In this article, the CrackUnet model based on deep learning is proposed to solve the above problems. First, crack images collected from the lab, earthquake sites, and the Internet are resized, labeled manually, and augmented to make a dataset (1200 subimages with 256 × 256 × 3 resolutions in total). Then, an improved Unet-based method called CrackUnet is proposed for automated pixel-level crack detection. A new loss function named generalized dice loss is adopted to detect cracks more accurately. How the size of the dataset and the depth of the model affect the training time, detecting accuracy, and speed is researched. The proposed methods are evaluated on the test dataset and a previously published dataset. The highest results can reach 91.45%, 88.67%, and 90.04% on test dataset and 98.72%, 92.84%, and 95.44% on CrackForest Dataset for precision, recall, and F1 score, respectively. By comparing the detecting accuracy, the training time, and the information of datasets, CrackUnet model outperform than other methods. Furthermore, six images with complicated noise are used to investigate the robustness and generalization of CrackUnet models.

Accurate estimation of structural displacement is crucial for assessing the damage state of structures. However, displacement sensors are rarely deployed on practical structures. Moreover, the traditional integration method based on acceleration data entails sophisticated processing steps, such as multiple filtering and baseline correction procedures. Therefore, an end‐to‐end displacement prediction method based on the long short‐term memory (LSTM) model integrated with an attention mechanism is presented herein to mitigate the limitations. The proposed model can predict structural displacement using noisy acceleration data acquired from accelerometer sensors mounted on structures. The overlapping window technique was employed to augment the dataset and enhance training efficiency. Furthermore, an attention mechanism was incorporated to improve prediction accuracy. When compared with the traditional integration method and the LSTM model without the attention mechanism, the proposed Attention‐LSTM model exhibited superior performance on the testing dataset. Additionally, the effects of key parameters were systematically investigated, such as the normalization method, cropping window size, number of LSTM layers, and number of units per layer. It is demonstrated that the proposed Attention‐LSTM model possesses robust generalization capability and antinoise performance, which contributes to the reliable estimation of structural displacement in engineering structures.