Group sparsity-aware convolutional neural network for continuous missing data recovery of structural health monitoring

Abstract

<jats:p> In structural health monitoring, data quality is crucial to the performance of data-driven methods for structural damage identification, condition assessment, and safety warning. However, structural health monitoring systems often suffer from data imperfection, resulting in some entries being unusable in a data matrix. Discrete missing points are relatively easy to recover based on known adjacent points, whereas segments of continuous missing data are more common and also more challenging to recover in a practical scenario. Formulating the data recovery task as an optimization problem for matrix completion, we present a convolutional neural network to achieve simultaneous recovery for multi-channel data with the awareness of group sparsity. The data recovery process based on compressive sensing is formulated as a regression problem and achieved in the neural network. The basis matrix is utilized as the input and the incomplete data matrix as the output to provide partial information for approximation. Basis coefficient optimization is performed via convolutional operation. Group sparsity regularization is applied while updating the kernel of the convolutional layer. The recovery can be readily obtained after optimization (training) without further validation and testing. The proposed method does not need intact data prepared in advance for training; also, it can handle sporadic data loss and make the most of interrupted information. Recovery ability evaluations on synthetic data, field-test data, and monitoring data of seismic response indicate that the proposed method achieves a good recovery result with high loss ratio and continuous data loss. The code is available at https://github.com/dawnnao/Group-sparsity-aware-CNN . </jats:p>

Reconstruction of Missing Samples in Antepartum and Intrapartum FHR Measurements Via Mini-Batch-Based Minimized Sparse Dictionary Learning

“…Analyzing the objective function in formula (11), D and W are free variables, and neither L p −norm nor the regularization term error δ is a prior parameter, which makes it difficult to choose in practice. We developed an L p −norm-based minimized sparse dictionary learning algorithm with a mini-batch version and combined it with a conjugate gradient solution for data recovery and noise term estimation.…”

“…1) First, quantify the constraints of formula (11), and obtain the minimized calculation formula below:…”

“…3) Finally, find an iterative solution of the independent variable δ: δis a regularization term error in formula (11), which is the quantization formula of noise term ε. Calculate the partial derivative of f (w (k) i , δ) with respect to δ, and set it equal to 0, to get:…”

A deep learning approach to rapid regional post‐event seismic damage assessment using time‐frequency distributions of ground motions

“…Kim et al 31 implemented a CNN model to extract the features of structural hysteretic behavior. There are also some studies which use CNN in the field of structural health monitoring or seismic response modeling 32–35 . Xu et al 36,37 uses other kinds of input for near real‐time seismic damage prediction, including the seismic IMs and acceleration records.…”

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

“…There are at least two practical applications for dam structural response estimation. 3,4 First, when the sensor operates normally, the predicted dam structural response can be used to identify the abnormal behavior of dam structures. Second, when one or more sensors are faulty, the predicted dam structural response can be used to recover the missing data of faulty sensors.…”