A robust deep learning-based damage identification approach for SHM considering missing data

TL;DR

This paper presents a robust deep learning approach using LSTM and dropout in autoencoders to identify damage in structures despite missing data, demonstrated on a cable-stayed bridge.

Contribution

It introduces a unified method combining missing data imputation and damage detection using LSTM and dropout autoencoders, enhancing SHM reliability.

Findings

Effective damage identification with missing data

Unified approach improves data utilization

Validated on real bridge response data

Abstract

Data-driven method for Structural Health Monitoring (SHM), that mine the hidden structural performance from the correlations among monitored time series data, has received widely concerns recently. However, missing data significantly impacts the conduction of this method. Missing data is a frequently encountered issue in time series data in SHM and many other real-world applications, that harms to the standardized data mining and downstream tasks, such as condition assessment. Imputation approaches based on spatiotemporal relations among monitoring data are developed to handle this issue, however, no additional information is added during imputation. This paper thus develops a robust method for damage identification that considers the missing data occasions, based on long-short term memory (LSTM) model and dropout mechanism in the autoencoder (AE) framework. Inputs channels are randomly dropped to simulate the missing data in training, and reconstruction errors are used as the loss function and the damage indicator. Quasi-static response (cable tension) of a cable-stayed bridge released in 1st IPC-SHM is employed to verify this proposed method, and results show that the missing data imputation and damage identification can be implemented together in a unified way.