International Peer-Reviewed JournalOpen AccessISSN 2456-8880
irejournals@gmail.com+91-7433024337

Home / Current Issue / Paper 1722945

1722945 Vol 10 · Issue 3 Download Paper

A Physics-Informed Multi-Modal Deep Learning Framework for Stochastic Prediction and Reliability Assessment of Human-Induced Vibrations in Lightweight and Composite Floor Systems

Ernest Chidindu Ernest Dr. Chen Deyi

Subject area: Science,Engineering and Technology  ·  Area of research: Human Induced Vibration, Reliability Assessment

DOI: https://doi.org/10.64388/IREV10I3-1722945

Abstract

Human-induced vibrations in lightweight and composite floor systems pose important serviceability concerns because these structures typically have lower stiffness, reduced mass, and higher sensitivity to dynamic loading. Conventional deterministic design methods often overlook the natural variability and short-term amplification effects caused by walking and other intermittent human activities. This study presents a physics-guided, multi-modal data-driven framework for predicting vibration responses and assessing structural reliability under human-induced loading conditions. Monitoring conducted over a 1000-second period shows bounded but dynamically fluctuating acceleration responses ranging between 9.5 m/s² and 10.2 m/s², concentrated around gravitational acceleration. Statistical evaluation indicates an approximately Gaussian distribution with minimal skewness, suggesting stable damping behavior and consistent stiffness properties. Frequency-domain analysis highlights dominant low-frequency components without noticeable resonance amplification within the typical walking frequency range of 1–4 Hz. Rolling mean trends reveal negligible long-term drift, confirming stable structural performance. The framework combines acceleration, strain, and environmental measurements to improve predictive capability and reliability evaluation. Correlation analysis shows that strain measurements strengthen response prediction, while temperature has a comparatively minor effect. Reliability assessment based on a probabilistic threshold model (μ + 2σ) identifies very few exceedance events, indicating a high reliability level and compliance with serviceability requirements. By integrating probabilistic modeling with physics-based structural constraints, the approach enables more accurate forecasting of vibration behavior and real-time reliability assessment. Overall, the results demonstrate improved prediction performance and provide a practical methodology for monitoring and evaluating serviceability in modern lightweight and composite floor systems.

Keywords

Human-Induced Vibrations; Lightweight Floor Systems; Composite Structures; Multi-Modal Data Fusion; Stochastic Modeling; Reliability Assessment; Structural Health Monitoring; Serviceability Analysis.

How to cite this paper

Ernest Chidindu Ernest, Dr. Chen Deyi "A Physics-Informed Multi-Modal Deep Learning Framework for Stochastic Prediction and Reliability Assessment of Human-Induced Vibrations in Lightweight and Composite Floor Systems" Iconic Research And Engineering Journals Volume 10 Issue 3 2026 Page 1287-1315 https://doi.org/10.64388/IREV10I3-1722945
Ernest Chidindu Ernest, Dr. Chen Deyi "A Physics-Informed Multi-Modal Deep Learning Framework for Stochastic Prediction and Reliability Assessment of Human-Induced Vibrations in Lightweight and Composite Floor Systems" Iconic Research And Engineering Journals, vol. 10, no. 3, Sep. 2026, doi: https://doi.org/10.64388/IREV10I3-1722945
Ernest Chidindu Ernest, Dr. Chen Deyi (2026). A Physics-Informed Multi-Modal Deep Learning Framework for Stochastic Prediction and Reliability Assessment of Human-Induced Vibrations in Lightweight and Composite Floor Systems. Iconic Research And Engineering Journals, 10(3). doi: https://doi.org/10.64388/IREV10I3-1722945
Ernest Chidindu Ernest, Dr. Chen Deyi "A Physics-Informed Multi-Modal Deep Learning Framework for Stochastic Prediction and Reliability Assessment of Human-Induced Vibrations in Lightweight and Composite Floor Systems" Iconic Research And Engineering Journals, vol. 10, no. 3, Sep. 2026. Crossref, https://doi.org/10.64388/IREV10I3-1722945
@article{1722945,
      author = {Ernest Chidindu Ernest, Dr. Chen Deyi},
      title = {A Physics-Informed Multi-Modal Deep Learning Framework for Stochastic Prediction and Reliability Assessment of Human-Induced Vibrations in Lightweight and Composite Floor Systems},
      journal = {Iconic Research And Engineering Journals},
      year = {2026},
      volume = {10},
      number = {3},
      pages = {1287-1315},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1722945.pdf},
      abstract = {Human-induced vibrations in lightweight and composite floor systems pose important serviceability concerns because these structures typically have lower stiffness, reduced mass, and higher sensitivity to dynamic loading. Conventional deterministic design methods often overlook the natural variability and short-term amplification effects caused by walking and other intermittent human activities. This study presents a physics-guided, multi-modal data-driven framework for predicting vibration responses and assessing structural reliability under human-induced loading conditions. Monitoring conducted over a 1000-second period shows bounded but dynamically fluctuating acceleration responses ranging between 9.5 m/s² and 10.2 m/s², concentrated around gravitational acceleration. Statistical evaluation indicates an approximately Gaussian distribution with minimal skewness, suggesting stable damping behavior and consistent stiffness properties. Frequency-domain analysis highlights dominant low-frequency components without noticeable resonance amplification within the typical walking frequency range of 1–4 Hz. Rolling mean trends reveal negligible long-term drift, confirming stable structural performance. The framework combines acceleration, strain, and environmental measurements to improve predictive capability and reliability evaluation. Correlation analysis shows that strain measurements strengthen response prediction, while temperature has a comparatively minor effect. Reliability assessment based on a probabilistic threshold model (μ + 2σ) identifies very few exceedance events, indicating a high reliability level and compliance with serviceability requirements. By integrating probabilistic modeling with physics-based structural constraints, the approach enables more accurate forecasting of vibration behavior and real-time reliability assessment. Overall, the results demonstrate improved prediction performance and provide a practical methodology for monitoring and evaluating serviceability in modern lightweight and composite floor systems.},
      keywords = {Human-Induced Vibrations; Lightweight Floor Systems; Composite Structures; Multi-Modal Data Fusion; Stochastic Modeling; Reliability Assessment; Structural Health Monitoring; Serviceability Analysis.},
      month = {September},
      doi = {https://doi.org/10.64388/IREV10I3-1722945}
  }