The performance, durability, and safety of modern buildings are inherently dependent on the mechanical properties of construction materials and the continuous assessment of structural health. Traditional material evaluation and monitoring approaches are limited in scalability, real-time assessment, and predictive capability, creating challenges for high-rise and complex urban structures. Artificial intelligence (AI) has emerged as a transformative solution, enabling predictive modeling of material strength, anomaly detection, and proactive structural health monitoring (SHM) through integration with advanced sensing networks and digital infrastructure. This chapter presents a comprehensive overview of AI-assisted material strength evaluation and SHM, highlighting machine learning and deep learning techniques for predicting concrete, steel, and composite behavior under operational and environmental stresses. Case studies of high-rise buildings demonstrate successful deployment of multi-sensor networks, digital twins, and Building Information Modeling (BIM) for real-time monitoring, predictive maintenance, and lifecycle optimization. The integration of AI with smart building systems facilitates data-driven decision-making, enhances safety standards, and promotes sustainable construction practices by minimizing resource-intensive repairs and prolonging structural service life. Emerging trends, including explainable AI, hybrid predictive models, and IoT-enabled infrastructures, offer opportunities for improved reliability and operational efficiency in building management. The insights presented in this chapter provide a framework for researchers, engineers, and practitioners to implement intelligent, proactive, and resilient material and structural assessment strategies in contemporary urban environments.
The structural integrity and longevity of modern buildings are fundamentally dependent on the mechanical properties of construction materials [1]. Materials such as concrete, steel, timber, and advanced composites must endure a wide range of static and dynamic loads while maintaining resilience under environmental stresses including wind, seismic forces, and thermal fluctuations [2]. Material strength directly affects safety, serviceability, and overall performance, making accurate evaluation an essential component of structural engineering. Conventional laboratory-based tests, such as compressive, tensile, and flexural evaluations, provide precise measurements under controlled conditions [3]. These tests, while reliable for initial design verification, are limited in capturing material behavior in real operational conditions, especially in large-scale or high-rise structures. Non-destructive techniques, including ultrasonic pulse velocity, rebound hammer tests, and radiographic inspections, enable field-based evaluation but often provide only localized or partial insights into structural performance [4]. Heterogeneity in material composition, construction quality, and environmental exposure introduces variability in results, highlighting the need for continuous monitoring methods that can evaluate materials under actual service conditions. The combination of accurate material characterization and structural analysis forms the foundation for safety, sustainability, and cost-effective building management, creating a critical need for advanced approaches that overcome the limitations of conventional evaluation techniques [5].
Structural health monitoring (SHM) has emerged as a vital technology for maintaining building performance throughout its lifecycle [6]. By integrating sensors, data acquisition systems, and analytical frameworks, SHM enables continuous tracking of structural responses under operational loads, environmental effects, and aging-induced material degradation [7]. Traditional inspection methods, relying on periodic visual checks or manual measurements, often fail to detect early-stage structural anomalies, resulting in delayed interventions and higher maintenance costs. Advanced SHM systems employ vibration-based measurements, acoustic emission sensing, strain monitoring, and thermal imaging to provide detailed insight into stress distribution, crack propagation, and localized deterioration [8]. These systems generate large volumes of heterogeneous data, necessitating advanced computational approaches for effective interpretation. Multi-sensor data fusion enhances assessment accuracy by correlating information from diverse sources, allowing comprehensive evaluation of structural performance across large buildings. Real-time monitoring facilitates proactive maintenance strategies by identifying potential failures before critical thresholds are reached [9]. The integration of SHM with predictive models ensures timely decision-making, reduces operational risks, and improves the overall resilience of structures. Such capabilities position SHM as a critical component for intelligent urban infrastructure management, bridging the gap between traditional inspection methods and predictive, data-driven maintenance strategies [10].
Artificial intelligence has revolutionized approaches to material strength evaluation and structural health monitoring by enabling predictive, data-driven analysis of complex systems [11]. Machine learning algorithms process large datasets from laboratory experiments, in-situ sensors, and historical building performance to model material behavior and identify structural vulnerabilities [12]. Supervised learning methods can predict mechanical properties, while unsupervised algorithms detect anomalies indicative of early-stage deterioration or unexpected load effects. Deep learning architectures, including convolutional and recurrent neural networks, are particularly effective at processing high-dimensional sensor outputs such as vibration signals, thermal images, and acoustic emission data [13]. Hybrid modeling approaches, combining physics-based simulations with AI predictions, enhance generalizability and robustness across varying material types and structural configurations. AI-driven systems enable automated risk assessment, scenario simulation, and proactive maintenance scheduling, surpassing the reactive capabilities of conventional inspection and evaluation techniques [14]. The application of AI transforms raw sensor data into actionable insights, allowing engineers to identify weak points, predict potential failures, and optimize material utilization. Integration with digital infrastructure platforms and building models enhances interpretability and supports lifecycle management. This shift from descriptive assessment to predictive intelligence represents a paradigm change in the field of structural engineering and material science [15].
