A new dam structural response estimation paradigm powered by deep learning and transfer learning techniques

Abstract

With the rapid development of information and communication techniques, dam structural health assessment based on data collected from structural health monitoring systems has become a trend. This allows for applying data-driven methods for dam safety analysis. However, data-driven models in most related literature are statistical and shallow machine learning models, which cannot capture the time series patterns or learn from long-term dependencies of dam structural response time series. Furthermore, the effectiveness and applicability of these models are only validated in a small data set and part of monitoring points in a dam structural health monitoring system. To address the problems, this article proposes a new modeling paradigm based on various deep learning and transfer learning techniques. The paradigm utilizes one-dimensional convolutional neural networks to extract the inherent features from dam structural response–related environmental quantity monitoring data. Then bidirectional gated recurrent unit with a self-attention mechanism is used to learn from long-term dependencies, and transfer learning is utilized to transfer knowledge learned from the typical monitoring point to the others. The proposed paradigm integrates the powerful modeling capability of deep learning networks and the flexible transferability of transfer learning. Rather than traditional models that rely on experience for feature selection, the proposed deep learning–based paradigm directly utilizes environmental monitoring time series as inputs to accurately estimate dam structural response changes. A high arch dam in long-term service is selected as the case study, and three monitoring items, including dam displacement, crack opening displacement, and seepage are used as the research objects. The experimental results show that the proposed paradigm outperforms conventional and shallow machine learning–based methods in all 41 tested monitoring points, which indicates that the proposed paradigm is capable of dealing with dam structural response estimation with high accuracy and robustness.

Hybrid artificial intelligence-based inference models for accurately predicting dam body displacements: A case study of the Fei Tsui dam

“…In addition to using machine learning models, convolutional neural network–based deep learning techniques have been put forward to recognized structural behavior response of dam body. 23,24 Undoubtedly, the AI-based inference models have lifted the early prediction of dam deformations to a higher level.…”

Correlation model of deflection, vehicle load, and temperature for in‐service bridge using deep learning and structural health monitoring

“…GRU neural network, a kind of deep learning neural network, is a variant of LSTM neural network which is developed from recurrent neural network (RNN) by introducing gating operation units. 34 For comparison, LSTM neural network is also used in this study to establish the correlation model. LSTM neural network can use not only current characteristic information but also intermediate results generated by previous training.…”

An integrated underwater structural multi-defects automatic identification and quantification framework for hydraulic tunnel via machine vision and deep learning

“…DCNN has been regarded as a state-of-the-art and human-competitive tool in image classification, semantic segmentation, instance segmentation, and so on. 33,34 However, to fully mine the features and information contained in the images, DCNN develops in the direction of deeper architecture and larger scale parameters. Training an original DCNN built from scratch is still a challenging task, which relies on an iterative trial-and-error process and numerous hyperparameters and network architecture tuning.…”