Time-frequency informed stacked long short-term memory-based generative adversarial network for missing data imputation in sensor networks

To monitor the health condition of civil infrastructures, the continuous acquisition of high-quality sensor data is crucial. However, in harsh environments, data can be lost due to sensor faults, data acquisition system malfunctions, or communication errors. In this study, we propose a stacked long...

Full description

Saved in:

Bibliographic Details
Published in:	Engineering applications of artificial intelligence Vol. 155; p. 110973
Main Authors:	Wang, Zixin, Kachireddy, Malleswari, Mondal, Tarutal Ghosh, Tang, Wen, Jahanshahi, Mohammad R.
Format:	Journal Article
Language:	English
Published:	Elsevier Ltd 01.09.2025
Subjects:	Deep learning Generative adversarial network Long short-term memory Missing data imputation Structural health monitoring Time-frequency information Missing data imputation Deep learning Long short-term memory Time-frequency information Structural health monitoring Generative adversarial network
ISSN:	0952-1976
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	To monitor the health condition of civil infrastructures, the continuous acquisition of high-quality sensor data is crucial. However, in harsh environments, data can be lost due to sensor faults, data acquisition system malfunctions, or communication errors. In this study, we propose a stacked long short-term memory (LSTM)-based generative adversarial network (GAN) approach to impute missing acceleration data from faulty sensors. The stacked LSTM-based GAN model is trained by incorporating time-frequency domain information and minimizing both reconstruction and adversarial losses. The reconstruction loss is calculated based on errors in acceleration data and power spectral density (PSD). The GAN’s generator employs a stacked LSTM network to capture long-term dependencies in sequential data. The performance of our proposed approach is compared with multiple state-of-the-art methods based on GANs and variational autoencoders (VAEs). When used as baseline approaches, GANs employ a deep convolutional autoencoder (CAE) in their generators, utilizing skip connections to facilitate the flow of information from the encoder to the decoder. The proposed approach is numerically studied using a three-span continuous bridge model and the American Society of Civil Engineers (ASCE) benchmark model and experimentally validated using the physical ASCE benchmark structure and the Qatar University Grandstand Simulator (QUGS) benchmark structure. Our approach demonstrates promising performance in reconstructing missing data in both the time and frequency domains, showcasing its potential to enhance sensor fault tolerance in safety-critical systems by accurately restoring faulty sensor data. •An end-to-end stacked LSTM-based GAN framework is proposed.•A novel time-frequency-informed training strategy is developed.•The approach outperforms state-of-the-art techniques for missing data imputation.•The approach shows robustness against measurement noise and limited sensor resources.
ISSN:	0952-1976
DOI:	10.1016/j.engappai.2025.110973