{
  "abstract": "Vibration-based structural health monitoring (SHM) detects damage by identifying subtle changes in a structure’s dynamic response. Deep learning models have shown strong potential for automating this classification task. However, most existing architectures share a key limitation: they either process signals purely in the time domain, or apply a global frequency-domain transform that discards information about when each frequency component occurs. This is a serious drawback, because structural damage typically manifests as short, localised events confined to specific frequency bands. This paper proposes SpectralTCN, a temporal convolutional network augmented with a Wavelet Gating Module (WGM) that performs learnable, data-dependent multi-resolution filtering within each convolutional block. The WGM decomposes intermediate features via the Discrete Wavelet Transform (DWT) into physically interpretable sub-bands corresponding to distinct structural vibration modes, applies input-adaptive sigmoid gates independently at each decomposition level, and reconstructs the filtered signal via the Inverse DWT (IDWT) with a learnable residual connection initialised to zero. Unlike FFT-based approaches, the DWT simultaneously preserves both time and frequency information, enabling the network to detect both the timing and the spectral location of damage-induced anomalies. Combined with Generalized Mean (GeM) pooling and large-kernel causal depthwise convolutions, SpectralTCN is evaluated on two benchmark datasets: the Z24 Bridge benchmark and a finite element model (FEM)-derived dataset of the My Thuan cable-stayed bridge. Experiments against 10 baseline models and 4 ablation variants, evaluated via stratified 5-fold cross-validation, demonstrate the effectiveness and generalisation capability of the proposed approach: SpectralTCN attains the highest mean accuracy on both benchmarks (92.2% on Z24 and 92.1% on My Thuan) and outperforms the strongest baseline in the 5-fold cross-validation protocol. In addition, the proposed architecture operates on short, streaming acceleration windows with a purely convolutional backbone of moderate computational cost, making SpectralTCN suitable for near-real-time, online damage detection in continuous bridge monitoring.",
  "abstract_shown": true,
  "affiliations": [
    "Faculty of Civil Engineering, University of Transport Technology, Ha Noi, Viet Nam",
    "Application of Artificial Intelligence for Structural Health Monitoring (AI-SHM) Research Group (R2026-UTC-01), Faculty of Civil and Environmental Engineering, University of Transport and Communications, Hanoi, Vietnam"
  ],
  "article_type": "Research Article",
  "arxiv": null,
  "author_total": 5,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Quan Pham Hong"
    },
    {
      "affs": [
        1
      ],
      "name": "Trung Vu Manh"
    },
    {
      "name": "Bich Nguyen Thach"
    },
    {
      "name": "Le Nguyen Dan"
    },
    {
      "name": "Hoa Tran Ngoc"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/9cnk7a5s4t46n.bib",
  "cited_by": 0,
  "doi": "10.1371/journal.pone.0358224",
  "fulltext_url": null,
  "id": "9cnk7a5s4t46n",
  "issns": [
    "1932-6203"
  ],
  "landing_url": "https://doi.org/10.1371/journal.pone.0358224",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "2205|Structural Health Monitoring Techniques"
    ],
    [
      "plos",
      "/Biology and life sciences/Anatomy/Biological tissue/Connective tissue/Tendons"
    ],
    [
      "plos",
      "/Computer and information sciences/Artificial intelligence/Machine learning/Deep learning"
    ],
    [
      "plos",
      "/Computer and information sciences/Software engineering/Preprocessing"
    ],
    [
      "plos",
      "/Engineering and technology/Signal processing/Signal filtering"
    ],
    [
      "plos",
      "/Engineering and technology/Software engineering/Preprocessing"
    ],
    [
      "plos",
      "/Medicine and health sciences/Anatomy/Biological tissue/Connective tissue/Tendons"
    ],
    [
      "plos",
      "/Physical sciences/Materials science/Material properties/Mechanical properties/Stiffness"
    ],
    [
      "plos",
      "/Physical sciences/Mathematics/Optimization"
    ],
    [
      "plos",
      "/Physical sciences/Physics/Classical mechanics/Vibration"
    ],
    [
      "plos",
      "/Research and analysis methods/Mathematical and statistical techniques/Mathematical functions/Convolution"
    ]
  ],
  "openalex": "W7213891783",
  "pdf_url": "https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0358224&type=printable",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-21",
  "publisher": "Public Library of Science",
  "ris": "https://research.draconitic.com/paper/9cnk7a5s4t46n.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:43Z",
      "native_id": "10.1371/journal.pone.0358224",
      "source": "plos",
      "url": "https://doi.org/10.1371/journal.pone.0358224"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "plos:materials science",
      "subfield": "materials-polymers"
    },
    {
      "field": "medicine",
      "origin": "plos:anatomy",
      "subfield": "physiology"
    }
  ],
  "title": "SpectralTCN: A multi-resolution wavelet gating network for vibration-based structural damage detection",
  "title_text": "SpectralTCN: A multi-resolution wavelet gating network for vibration-based structural damage detection",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:17:43Z",
  "url": "https://research.draconitic.com/paper/9cnk7a5s4t46n",
  "venue": "PLOS One",
  "versions": []
}