Addressing data scarcity in structural health monitoring through generative augmentation

2025-10-19

AI Summary

To address data scarcity, environmental noise interference, and severe class imbalance caused by rare events in bridge structural health monitoring, this paper proposes STFTSynth—a novel generative adversarial framework that models short-time Fourier transform (STFT) spectrograms. STFTSynth integrates dense residual blocks with bidirectional gated recurrent units (BiGRUs) to jointly capture spatial consistency and temporal dependencies within spectrograms. Compared to conventional GANs and MixUp-based approaches, STFTSynth achieves significant improvements in structural similarity (SSIM), peak signal-to-noise ratio (PSNR), and Fréchet Inception Distance (FID), yielding high-resolution, temporally coherent, and high-fidelity synthetic spectrograms. Experimental results demonstrate that the method effectively alleviates the small-sample bottleneck and substantially enhances rare-event detection performance. This work establishes a new paradigm for low-cost, scalable intelligent bridge monitoring.

Technology Category

• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Machine Learning: Deep Generative Models & Autoencoders

Application Category

• Web Mining and Content Analysis: Bridging structured and unstructured data
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Structural Health Monitoring plays a crucial role in ensuring the safety, reliability, and longevity of bridge infrastructures through early damage detection. Although recent advances in deep learning-based models have enabled automated event detection, their performance is often limited by data scarcity, environmental noise, and class imbalance. To address these challenges, this study introduces a customized Generative Adversarial Network model, STFTSynth, designed particularly for generating short-time Fourier transform spectrograms derived from acoustic event signals. In contrast to augmentation techniques such as MixUp, generative adversarial networks can synthesize high-quality spectrograms that mimic real-world events, enhancing dataset diversity and robustness. The proposed model integrates dense residual blocks for spatial consistency with bidirectional gated recurrent units for temporal dependency modeling. Model performance is evaluated against three baseline generative models using qualitative inspection and quantitative metrics, including Structural Similarity Index Measure, Peak Signal-to-Noise Ratio, and Fréchet Inception Distance. Results show that STFTSynth outperforms baseline models, producing high-resolution, temporally consistent spectrograms that align closely with real-world data. These findings indicate the potential of generative-based data augmentation as a scalable and cost-effective solution for bridge monitoring scenarios where rare events, such as prestressing wire breakage, suffer from data scarcity.

Problem

• Addressing data scarcity in structural health monitoring
• Generating synthetic spectrograms for acoustic event detection
• Enhancing dataset diversity to detect rare bridge damage

Innovation

• Customized GAN generates STFT spectrograms for acoustic events
• Integrates dense residual blocks with bidirectional GRU networks
• Produces high-resolution temporally consistent synthetic spectrograms