About this Research Topic
The field of structural health monitoring (SHM) has witnessed the rapid advances of robotics, networked sensing, and computer vision technologies. Data collected by robots (e.g., unmanned aerial vehicles), sensing networks (e.g., wireless sensor networks), and vision systems (e.g., cameras, laser scanning systems) bring in salient information to assess structural health state and guide decision-making in protecting infrastructure against potential hazards. However, the vast volume and high level of complexity of these data demand advanced analysis tools and computational models to properly extract critical SHM information under practical and yet complex settings. In recent years, machine learning methods and big data analytics have been proposed and developed for data processing, damage identification, condition assessment, and life-cycle evaluation for SHM. This rapidly developing field has demonstrated great potential in deciphering SHM information from complex data with efficient and robust performance.
Through the organization of this research topic, we aim to highlight the introduction and recent developments of machine learning methods and big data analytics in SHM, identify the future research trends with novel models and analysis tools in this realm, and broaden the spectrum of applications using such methods and techniques. This research topic promotes asset management research where data analytics combine with physics-based structural behavior models to provide predictions for retrofit, repair and replacement scenarios. Studies submitted to this research topic must focus on the use of experimental data acquired from practice, field, or laboratory.
This research topic invites, but not limited to, the contributions in the following aspects:
• Machine learning (including deep learning) based SHM data mining, processing, modeling, analysis, and condition assessment;
• Physics informed machine learning methods for SHM;
• Structural response or performance prediction using machine learning and big data analytics;
• Big data processing and management, especially based on long-term monitoring practice;
• Vision or image based SHM;
• Probabilistic and uncertainty quantification methods for machine learning and big data analytics;
• Other related subjects.
Keywords: Machine Learning, Deep Learning, Big Data, Structural Health Monitoring, Computer Vision
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.