A feature learning-based method for impact load reconstruction and localization of the plate-rib assembled structure:

TL;DR: Based on the idea of deep metric learning and total least squares, a two-stage method is proposed for random impact force localization and reconstruction in this paper , which can obtain quite low localization errors on the three-dimensional composite structure, while robust and accurate reconstruction can be achieved even under high noise level.

TL;DR: In this paper , a hierarchical and sequential framework for uncertainty-oriented impact force identification of composite structures is developed, and an optimum sensor allocation method based on the interval possibility model and condition number indicators is proposed to enhance the identification precision.

TL;DR: In this paper , a novel intelligent fault diagnosis framework, called the convolutional capsule auto-encoder-based unsupervised directed hierarchical graph network with clustering representation (CCAE-UDHGN-CR), is established and employed in unlabeled scenarios.

TL;DR: This paper proposes Distance-assisted Graph Neural Network (DAGNN) for simultaneous impact force localization and history reconstruction, outperforming conventional GNN, GCN, and ANN models, with infused physical distances improving accuracy and enabling impact localization.

TL;DR: Quantitative assessments show that SegNet provides good performance with competitive inference time and most efficient inference memory-wise as compared to other architectures, including FCN and DeconvNet.

TL;DR: A new intelligent method named deep convolutional transfer learning network (DCTLN) is proposed, which facilitates the 1-D CNN to learn domain-invariant features by maximizing domain recognition errors and minimizing the probability distribution distance.

TL;DR: A novel method based on deep convolutional neural networks to identify and localise damages of building structures equipped with smart control devices that has outstanding generalisation capacity and higher identification accuracy than other commonly used machine learning methods is proposed.

TL;DR: In this paper, a loading force identification method based on the least square error between the simulated and measured system responses is used as the objective function, and the method is applied to the identification of wheel-rail contact forces during rail vehicle operation.