CNN-based structural damage detection using time-series sensor data

Tools

Pathak, Ishan and Jha, Ishan and Sadana, Aditya and Bhowmik, Basuraj (2023) CNN-based structural damage detection using time-series sensor data. Other. arXiv, Ithaca, NY. (https://doi.org/10.48550/arXiv.2311.04252)

[thumbnail of Pathak-etal-arXiv-2023-CNN-based-structural-damage-detection-using-time-series-sensor-data]
Preview
 Text. Filename: Pathak-etal-arXiv-2023-CNN-based-structural-damage-detection-using-time-series-sensor-data.pdf
Final Published Version
License: Creative Commons Attribution 4.0 logo
Download (701kB)| Preview

Abstract

Structural Health Monitoring (SHM) is vital for evaluating structural condition, aiming to detect damage through sensor data analysis. It aligns with predictive maintenance in modern industry, minimizing downtime and costs by addressing potential structural issues. Various machine learning techniques have been used to extract valuable information from vibration data, often relying on prior structural knowledge. This research introduces an innovative approach to structural damage detection, utilizing a new Convolutional Neural Network (CNN) algorithm. In order to extract deep spatial features from time series data, CNNs are taught to recognize long-term temporal connections. This methodology combines spatial and temporal features, enhancing discrimination capabilities when compared to methods solely reliant on deep spatial features. Time series data are divided into two categories using the proposed neural network: undamaged and damaged. To validate its efficacy, the method's accuracy was tested using a benchmark dataset derived from a three-floor structure at Los Alamos National Laboratory (LANL). The outcomes show that the new CNN algorithm is very accurate in spotting structural degradation in the examined structure.

ORCID iDs

Pathak, Ishan, Jha, Ishan, Sadana, Aditya and Bhowmik, Basuraj ORCID logoORCID: https://orcid.org/0000-0001-7782-513X;
CORE (COnnecting REpositories)